{"current_steps": 5, "total_steps": 38150, "loss": 6.7986, "lr": 5.2424639580602885e-08, "epoch": 0.001310615989515072, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "2:27:04", "throughput": 1023.59, "total_tokens": 1184} {"current_steps": 10, "total_steps": 38150, "loss": 6.459, "lr": 1.1795543905635651e-07, "epoch": 0.002621231979030144, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:41:54", "throughput": 1527.05, "total_tokens": 2448} {"current_steps": 15, "total_steps": 38150, "loss": 6.3342, "lr": 1.8348623853211012e-07, "epoch": 0.003931847968545216, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:29:22", "throughput": 1957.09, "total_tokens": 4128} {"current_steps": 20, "total_steps": 38150, "loss": 6.3733, "lr": 2.490170380078637e-07, "epoch": 0.005242463958060288, "percentage": 0.05, "elapsed_time": "0:00:02", "remaining_time": "1:22:08", "throughput": 2191.02, "total_tokens": 5664} {"current_steps": 25, "total_steps": 38150, "loss": 6.993, "lr": 3.1454783748361734e-07, "epoch": 0.00655307994757536, "percentage": 0.07, "elapsed_time": "0:00:03", "remaining_time": "1:17:02", "throughput": 2322.32, "total_tokens": 7040} {"current_steps": 30, "total_steps": 38150, "loss": 6.2515, "lr": 3.8007863695937093e-07, "epoch": 0.007863695937090432, "percentage": 0.08, "elapsed_time": "0:00:03", "remaining_time": "1:13:37", "throughput": 2402.37, "total_tokens": 8352} {"current_steps": 35, "total_steps": 38150, "loss": 6.3401, "lr": 4.4560943643512453e-07, "epoch": 0.009174311926605505, "percentage": 0.09, "elapsed_time": "0:00:03", "remaining_time": "1:11:08", "throughput": 2469.35, "total_tokens": 9680} {"current_steps": 40, "total_steps": 38150, "loss": 6.0357, "lr": 5.111402359108782e-07, "epoch": 0.010484927916120577, "percentage": 0.1, "elapsed_time": "0:00:04", "remaining_time": "1:10:11", "throughput": 2584.56, "total_tokens": 11424} {"current_steps": 45, "total_steps": 38150, "loss": 6.1273, "lr": 5.766710353866317e-07, "epoch": 0.011795543905635648, "percentage": 0.12, "elapsed_time": "0:00:04", "remaining_time": "1:08:22", "throughput": 2589.26, "total_tokens": 12544} {"current_steps": 50, "total_steps": 38150, "loss": 5.9301, "lr": 6.422018348623854e-07, "epoch": 0.01310615989515072, "percentage": 0.13, "elapsed_time": "0:00:05", "remaining_time": "1:07:58", "throughput": 2636.61, "total_tokens": 14112} {"current_steps": 55, "total_steps": 38150, "loss": 6.1987, "lr": 7.07732634338139e-07, "epoch": 0.014416775884665793, "percentage": 0.14, "elapsed_time": "0:00:05", "remaining_time": "1:06:50", "throughput": 2630.44, "total_tokens": 15232} {"current_steps": 60, "total_steps": 38150, "loss": 5.5467, "lr": 7.732634338138926e-07, "epoch": 0.015727391874180863, "percentage": 0.16, "elapsed_time": "0:00:06", "remaining_time": "1:06:27", "throughput": 2676.96, "total_tokens": 16816} {"current_steps": 65, "total_steps": 38150, "loss": 5.162, "lr": 8.387942332896462e-07, "epoch": 0.01703800786369594, "percentage": 0.17, "elapsed_time": "0:00:06", "remaining_time": "1:05:31", "throughput": 2646.79, "total_tokens": 17760} {"current_steps": 70, "total_steps": 38150, "loss": 4.9736, "lr": 9.043250327653998e-07, "epoch": 0.01834862385321101, "percentage": 0.18, "elapsed_time": "0:00:07", "remaining_time": "1:04:47", "throughput": 2655.34, "total_tokens": 18976} {"current_steps": 75, "total_steps": 38150, "loss": 4.9793, "lr": 9.698558322411533e-07, "epoch": 0.019659239842726082, "percentage": 0.2, "elapsed_time": "0:00:07", "remaining_time": "1:04:24", "throughput": 2675.69, "total_tokens": 20368} {"current_steps": 80, "total_steps": 38150, "loss": 4.6473, "lr": 1.035386631716907e-06, "epoch": 0.020969855832241154, "percentage": 0.21, "elapsed_time": "0:00:08", "remaining_time": "1:03:50", "throughput": 2665.23, "total_tokens": 21456} {"current_steps": 85, "total_steps": 38150, "loss": 4.7327, "lr": 1.1009174311926608e-06, "epoch": 0.022280471821756225, "percentage": 0.22, "elapsed_time": "0:00:08", "remaining_time": "1:03:23", "throughput": 2659.75, "total_tokens": 22592} {"current_steps": 90, "total_steps": 38150, "loss": 4.7761, "lr": 1.1664482306684142e-06, "epoch": 0.023591087811271297, "percentage": 0.24, "elapsed_time": "0:00:08", "remaining_time": "1:02:51", "throughput": 2660.61, "total_tokens": 23728} {"current_steps": 95, "total_steps": 38150, "loss": 4.1649, "lr": 1.2319790301441677e-06, "epoch": 0.02490170380078637, "percentage": 0.25, "elapsed_time": "0:00:09", "remaining_time": "1:02:25", "throughput": 2659.17, "total_tokens": 24864} {"current_steps": 100, "total_steps": 38150, "loss": 4.3159, "lr": 1.2975098296199214e-06, "epoch": 0.02621231979030144, "percentage": 0.26, "elapsed_time": "0:00:09", "remaining_time": "1:02:08", "throughput": 2681.31, "total_tokens": 26272} {"current_steps": 105, "total_steps": 38150, "loss": 4.3612, "lr": 1.363040629095675e-06, "epoch": 0.027522935779816515, "percentage": 0.28, "elapsed_time": "0:00:10", "remaining_time": "1:01:44", "throughput": 2665.13, "total_tokens": 27248} {"current_steps": 110, "total_steps": 38150, "loss": 3.3342, "lr": 1.4285714285714286e-06, "epoch": 0.028833551769331587, "percentage": 0.29, "elapsed_time": "0:00:10", "remaining_time": "1:01:38", "throughput": 2682.59, "total_tokens": 28688} {"current_steps": 115, "total_steps": 38150, "loss": 4.3775, "lr": 1.4941022280471821e-06, "epoch": 0.03014416775884666, "percentage": 0.3, "elapsed_time": "0:00:11", "remaining_time": "1:01:20", "throughput": 2677.07, "total_tokens": 29792} {"current_steps": 120, "total_steps": 38150, "loss": 3.5152, "lr": 1.559633027522936e-06, "epoch": 0.03145478374836173, "percentage": 0.31, "elapsed_time": "0:00:11", "remaining_time": "1:01:28", "throughput": 2700.12, "total_tokens": 31424} {"current_steps": 125, "total_steps": 38150, "loss": 3.867, "lr": 1.6251638269986893e-06, "epoch": 0.0327653997378768, "percentage": 0.33, "elapsed_time": "0:00:12", "remaining_time": "1:01:10", "throughput": 2684.23, "total_tokens": 32384} {"current_steps": 130, "total_steps": 38150, "loss": 3.8969, "lr": 1.690694626474443e-06, "epoch": 0.03407601572739188, "percentage": 0.34, "elapsed_time": "0:00:12", "remaining_time": "1:01:01", "throughput": 2700.52, "total_tokens": 33808} {"current_steps": 135, "total_steps": 38150, "loss": 3.6425, "lr": 1.7562254259501965e-06, "epoch": 0.035386631716906945, "percentage": 0.35, "elapsed_time": "0:00:12", "remaining_time": "1:00:48", "throughput": 2694.49, "total_tokens": 34912} {"current_steps": 140, "total_steps": 38150, "loss": 3.5186, "lr": 1.8217562254259502e-06, "epoch": 0.03669724770642202, "percentage": 0.37, "elapsed_time": "0:00:13", "remaining_time": "1:00:52", "throughput": 2718.47, "total_tokens": 36576} {"current_steps": 145, "total_steps": 38150, "loss": 3.6483, "lr": 1.8872870249017041e-06, "epoch": 0.03800786369593709, "percentage": 0.38, "elapsed_time": "0:00:13", "remaining_time": "1:00:44", "throughput": 2708.85, "total_tokens": 37664} {"current_steps": 150, "total_steps": 38150, "loss": 3.6386, "lr": 1.9528178243774574e-06, "epoch": 0.039318479685452164, "percentage": 0.39, "elapsed_time": "0:00:14", "remaining_time": "1:00:31", "throughput": 2707.8, "total_tokens": 38816} {"current_steps": 155, "total_steps": 38150, "loss": 3.2565, "lr": 2.0183486238532113e-06, "epoch": 0.04062909567496723, "percentage": 0.41, "elapsed_time": "0:00:14", "remaining_time": "1:00:33", "throughput": 2717.24, "total_tokens": 40272} {"current_steps": 160, "total_steps": 38150, "loss": 3.3967, "lr": 2.083879423328965e-06, "epoch": 0.04193971166448231, "percentage": 0.42, "elapsed_time": "0:00:15", "remaining_time": "1:00:24", "throughput": 2711.86, "total_tokens": 41392} {"current_steps": 165, "total_steps": 38150, "loss": 3.648, "lr": 2.1494102228047183e-06, "epoch": 0.04325032765399738, "percentage": 0.43, "elapsed_time": "0:00:15", "remaining_time": "1:00:28", "throughput": 2738.11, "total_tokens": 43152} {"current_steps": 170, "total_steps": 38150, "loss": 3.3635, "lr": 2.2149410222804718e-06, "epoch": 0.04456094364351245, "percentage": 0.45, "elapsed_time": "0:00:16", "remaining_time": "1:00:42", "throughput": 2759.39, "total_tokens": 44992} {"current_steps": 175, "total_steps": 38150, "loss": 3.0703, "lr": 2.2804718217562257e-06, "epoch": 0.045871559633027525, "percentage": 0.46, "elapsed_time": "0:00:16", "remaining_time": "1:00:32", "throughput": 2759.11, "total_tokens": 46192} {"current_steps": 180, "total_steps": 38150, "loss": 3.4704, "lr": 2.346002621231979e-06, "epoch": 0.047182175622542594, "percentage": 0.47, "elapsed_time": "0:00:17", "remaining_time": "1:00:22", "throughput": 2749.46, "total_tokens": 47216} {"current_steps": 185, "total_steps": 38150, "loss": 2.6495, "lr": 2.4115334207077327e-06, "epoch": 0.04849279161205767, "percentage": 0.48, "elapsed_time": "0:00:17", "remaining_time": "1:00:29", "throughput": 2767.49, "total_tokens": 48944} {"current_steps": 190, "total_steps": 38150, "loss": 2.7644, "lr": 2.4770642201834866e-06, "epoch": 0.04980340760157274, "percentage": 0.5, "elapsed_time": "0:00:18", "remaining_time": "1:00:21", "throughput": 2773.92, "total_tokens": 50288} {"current_steps": 195, "total_steps": 38150, "loss": 2.5845, "lr": 2.54259501965924e-06, "epoch": 0.05111402359108781, "percentage": 0.51, "elapsed_time": "0:00:18", "remaining_time": "1:00:13", "throughput": 2776.72, "total_tokens": 51552} {"current_steps": 200, "total_steps": 38150, "loss": 3.2747, "lr": 2.6081258191349936e-06, "epoch": 0.05242463958060288, "percentage": 0.52, "elapsed_time": "0:00:19", "remaining_time": "1:00:17", "throughput": 2797.25, "total_tokens": 53328} {"current_steps": 205, "total_steps": 38150, "loss": 2.5992, "lr": 2.673656618610747e-06, "epoch": 0.053735255570117955, "percentage": 0.54, "elapsed_time": "0:00:19", "remaining_time": "1:00:12", "throughput": 2799.51, "total_tokens": 54640} {"current_steps": 210, "total_steps": 38150, "loss": 2.7476, "lr": 2.739187418086501e-06, "epoch": 0.05504587155963303, "percentage": 0.55, "elapsed_time": "0:00:19", "remaining_time": "1:00:08", "throughput": 2792.19, "total_tokens": 55776} {"current_steps": 215, "total_steps": 38150, "loss": 2.5949, "lr": 2.8047182175622545e-06, "epoch": 0.0563564875491481, "percentage": 0.56, "elapsed_time": "0:00:20", "remaining_time": "1:00:04", "throughput": 2800.67, "total_tokens": 57216} {"current_steps": 220, "total_steps": 38150, "loss": 2.7169, "lr": 2.870249017038008e-06, "epoch": 0.057667103538663174, "percentage": 0.58, "elapsed_time": "0:00:21", "remaining_time": "1:00:27", "throughput": 2821.08, "total_tokens": 59360} {"current_steps": 225, "total_steps": 38150, "loss": 2.8786, "lr": 2.935779816513762e-06, "epoch": 0.05897771952817824, "percentage": 0.59, "elapsed_time": "0:00:21", "remaining_time": "1:00:17", "throughput": 2813.91, "total_tokens": 60384} {"current_steps": 230, "total_steps": 38150, "loss": 2.463, "lr": 3.0013106159895154e-06, "epoch": 0.06028833551769332, "percentage": 0.6, "elapsed_time": "0:00:21", "remaining_time": "1:00:16", "throughput": 2821.08, "total_tokens": 61888} {"current_steps": 235, "total_steps": 38150, "loss": 2.2599, "lr": 3.066841415465269e-06, "epoch": 0.061598951507208385, "percentage": 0.62, "elapsed_time": "0:00:22", "remaining_time": "1:00:06", "throughput": 2809.23, "total_tokens": 62800} {"current_steps": 240, "total_steps": 38150, "loss": 2.3209, "lr": 3.1323722149410228e-06, "epoch": 0.06290956749672345, "percentage": 0.63, "elapsed_time": "0:00:22", "remaining_time": "1:00:02", "throughput": 2817.26, "total_tokens": 64256} {"current_steps": 245, "total_steps": 38150, "loss": 2.4618, "lr": 3.1979030144167763e-06, "epoch": 0.06422018348623854, "percentage": 0.64, "elapsed_time": "0:00:23", "remaining_time": "1:00:04", "throughput": 2820.84, "total_tokens": 65728} {"current_steps": 250, "total_steps": 38150, "loss": 2.6133, "lr": 3.2634338138925293e-06, "epoch": 0.0655307994757536, "percentage": 0.66, "elapsed_time": "0:00:23", "remaining_time": "0:59:58", "throughput": 2818.61, "total_tokens": 66912} {"current_steps": 255, "total_steps": 38150, "loss": 2.2286, "lr": 3.328964613368283e-06, "epoch": 0.06684141546526867, "percentage": 0.67, "elapsed_time": "0:00:24", "remaining_time": "0:59:50", "throughput": 2810.45, "total_tokens": 67904} {"current_steps": 260, "total_steps": 38150, "loss": 2.3407, "lr": 3.394495412844037e-06, "epoch": 0.06815203145478375, "percentage": 0.68, "elapsed_time": "0:00:24", "remaining_time": "0:59:47", "throughput": 2821.24, "total_tokens": 69456} {"current_steps": 265, "total_steps": 38150, "loss": 2.8786, "lr": 3.4600262123197906e-06, "epoch": 0.06946264744429882, "percentage": 0.69, "elapsed_time": "0:00:25", "remaining_time": "0:59:45", "throughput": 2823.89, "total_tokens": 70832} {"current_steps": 270, "total_steps": 38150, "loss": 2.7456, "lr": 3.5255570117955437e-06, "epoch": 0.07077326343381389, "percentage": 0.71, "elapsed_time": "0:00:25", "remaining_time": "0:59:46", "throughput": 2833.83, "total_tokens": 72448} {"current_steps": 275, "total_steps": 38150, "loss": 2.5068, "lr": 3.591087811271298e-06, "epoch": 0.07208387942332896, "percentage": 0.72, "elapsed_time": "0:00:26", "remaining_time": "0:59:46", "throughput": 2838.77, "total_tokens": 73920} {"current_steps": 280, "total_steps": 38150, "loss": 2.5438, "lr": 3.6566186107470515e-06, "epoch": 0.07339449541284404, "percentage": 0.73, "elapsed_time": "0:00:26", "remaining_time": "0:59:47", "throughput": 2845.44, "total_tokens": 75472} {"current_steps": 285, "total_steps": 38150, "loss": 2.4037, "lr": 3.7221494102228046e-06, "epoch": 0.07470511140235911, "percentage": 0.75, "elapsed_time": "0:00:26", "remaining_time": "0:59:46", "throughput": 2851.26, "total_tokens": 76976} {"current_steps": 290, "total_steps": 38150, "loss": 2.3192, "lr": 3.787680209698558e-06, "epoch": 0.07601572739187418, "percentage": 0.76, "elapsed_time": "0:00:27", "remaining_time": "0:59:42", "throughput": 2860.21, "total_tokens": 78496} {"current_steps": 295, "total_steps": 38150, "loss": 1.9689, "lr": 3.853211009174312e-06, "epoch": 0.07732634338138926, "percentage": 0.77, "elapsed_time": "0:00:27", "remaining_time": "0:59:42", "throughput": 2866.48, "total_tokens": 80032} {"current_steps": 300, "total_steps": 38150, "loss": 1.6909, "lr": 3.918741808650066e-06, "epoch": 0.07863695937090433, "percentage": 0.79, "elapsed_time": "0:00:28", "remaining_time": "0:59:35", "throughput": 2862.27, "total_tokens": 81104} {"current_steps": 305, "total_steps": 38150, "loss": 1.7138, "lr": 3.984272608125819e-06, "epoch": 0.0799475753604194, "percentage": 0.8, "elapsed_time": "0:00:28", "remaining_time": "0:59:28", "throughput": 2858.98, "total_tokens": 82224} {"current_steps": 310, "total_steps": 38150, "loss": 1.7154, "lr": 4.049803407601573e-06, "epoch": 0.08125819134993446, "percentage": 0.81, "elapsed_time": "0:00:29", "remaining_time": "0:59:38", "throughput": 2870.94, "total_tokens": 84160} {"current_steps": 315, "total_steps": 38150, "loss": 2.0075, "lr": 4.115334207077327e-06, "epoch": 0.08256880733944955, "percentage": 0.83, "elapsed_time": "0:00:29", "remaining_time": "0:59:34", "throughput": 2872.92, "total_tokens": 85488} {"current_steps": 320, "total_steps": 38150, "loss": 2.203, "lr": 4.18086500655308e-06, "epoch": 0.08387942332896461, "percentage": 0.84, "elapsed_time": "0:00:30", "remaining_time": "0:59:30", "throughput": 2872.97, "total_tokens": 86768} {"current_steps": 325, "total_steps": 38150, "loss": 1.6721, "lr": 4.246395806028834e-06, "epoch": 0.08519003931847968, "percentage": 0.85, "elapsed_time": "0:00:30", "remaining_time": "0:59:25", "throughput": 2869.67, "total_tokens": 87920} {"current_steps": 330, "total_steps": 38150, "loss": 2.5713, "lr": 4.311926605504588e-06, "epoch": 0.08650065530799476, "percentage": 0.87, "elapsed_time": "0:00:31", "remaining_time": "0:59:24", "throughput": 2866.29, "total_tokens": 89136} {"current_steps": 335, "total_steps": 38150, "loss": 1.9157, "lr": 4.377457404980341e-06, "epoch": 0.08781127129750983, "percentage": 0.88, "elapsed_time": "0:00:31", "remaining_time": "0:59:19", "throughput": 2868.54, "total_tokens": 90464} {"current_steps": 340, "total_steps": 38150, "loss": 1.8514, "lr": 4.442988204456095e-06, "epoch": 0.0891218872870249, "percentage": 0.89, "elapsed_time": "0:00:31", "remaining_time": "0:59:17", "throughput": 2875.73, "total_tokens": 91984} {"current_steps": 345, "total_steps": 38150, "loss": 1.3482, "lr": 4.508519003931848e-06, "epoch": 0.09043250327653997, "percentage": 0.9, "elapsed_time": "0:00:32", "remaining_time": "0:59:10", "throughput": 2870.76, "total_tokens": 93024} {"current_steps": 350, "total_steps": 38150, "loss": 1.499, "lr": 4.574049803407602e-06, "epoch": 0.09174311926605505, "percentage": 0.92, "elapsed_time": "0:00:32", "remaining_time": "0:59:11", "throughput": 2872.91, "total_tokens": 94464} {"current_steps": 355, "total_steps": 38150, "loss": 1.7817, "lr": 4.639580602883356e-06, "epoch": 0.09305373525557012, "percentage": 0.93, "elapsed_time": "0:00:33", "remaining_time": "0:59:07", "throughput": 2871.31, "total_tokens": 95664} {"current_steps": 360, "total_steps": 38150, "loss": 1.4435, "lr": 4.705111402359109e-06, "epoch": 0.09436435124508519, "percentage": 0.94, "elapsed_time": "0:00:33", "remaining_time": "0:59:02", "throughput": 2862.42, "total_tokens": 96608} {"current_steps": 365, "total_steps": 38150, "loss": 1.3371, "lr": 4.7706422018348626e-06, "epoch": 0.09567496723460026, "percentage": 0.96, "elapsed_time": "0:00:34", "remaining_time": "0:58:59", "throughput": 2865.16, "total_tokens": 97968} {"current_steps": 370, "total_steps": 38150, "loss": 1.185, "lr": 4.8361730013106165e-06, "epoch": 0.09698558322411534, "percentage": 0.97, "elapsed_time": "0:00:34", "remaining_time": "0:58:54", "throughput": 2864.09, "total_tokens": 99152} {"current_steps": 375, "total_steps": 38150, "loss": 1.2584, "lr": 4.9017038007863695e-06, "epoch": 0.0982961992136304, "percentage": 0.98, "elapsed_time": "0:00:35", "remaining_time": "0:58:52", "throughput": 2868.41, "total_tokens": 100592} {"current_steps": 380, "total_steps": 38150, "loss": 1.0506, "lr": 4.9672346002621235e-06, "epoch": 0.09960681520314547, "percentage": 1.0, "elapsed_time": "0:00:35", "remaining_time": "0:58:49", "throughput": 2868.66, "total_tokens": 101856} {"current_steps": 385, "total_steps": 38150, "loss": 1.079, "lr": 5.032765399737877e-06, "epoch": 0.10091743119266056, "percentage": 1.01, "elapsed_time": "0:00:35", "remaining_time": "0:58:45", "throughput": 2866.41, "total_tokens": 103024} {"current_steps": 390, "total_steps": 38150, "loss": 0.7351, "lr": 5.0982961992136304e-06, "epoch": 0.10222804718217562, "percentage": 1.02, "elapsed_time": "0:00:36", "remaining_time": "0:58:46", "throughput": 2869.46, "total_tokens": 104512} {"current_steps": 395, "total_steps": 38150, "loss": 0.7511, "lr": 5.163826998689384e-06, "epoch": 0.10353866317169069, "percentage": 1.04, "elapsed_time": "0:00:36", "remaining_time": "0:58:44", "throughput": 2872.24, "total_tokens": 105904} {"current_steps": 400, "total_steps": 38150, "loss": 0.8194, "lr": 5.229357798165138e-06, "epoch": 0.10484927916120576, "percentage": 1.05, "elapsed_time": "0:00:37", "remaining_time": "0:58:40", "throughput": 2870.45, "total_tokens": 107088} {"current_steps": 405, "total_steps": 38150, "loss": 1.0875, "lr": 5.294888597640891e-06, "epoch": 0.10615989515072084, "percentage": 1.06, "elapsed_time": "0:00:37", "remaining_time": "0:58:37", "throughput": 2867.92, "total_tokens": 108240} {"current_steps": 410, "total_steps": 38150, "loss": 0.818, "lr": 5.360419397116645e-06, "epoch": 0.10747051114023591, "percentage": 1.07, "elapsed_time": "0:00:38", "remaining_time": "0:58:34", "throughput": 2866.87, "total_tokens": 109472} {"current_steps": 415, "total_steps": 38150, "loss": 0.8605, "lr": 5.425950196592398e-06, "epoch": 0.10878112712975098, "percentage": 1.09, "elapsed_time": "0:00:38", "remaining_time": "0:58:37", "throughput": 2870.78, "total_tokens": 111056} {"current_steps": 420, "total_steps": 38150, "loss": 0.6954, "lr": 5.491480996068152e-06, "epoch": 0.11009174311926606, "percentage": 1.1, "elapsed_time": "0:00:39", "remaining_time": "0:58:36", "throughput": 2872.77, "total_tokens": 112448} {"current_steps": 425, "total_steps": 38150, "loss": 0.8871, "lr": 5.557011795543906e-06, "epoch": 0.11140235910878113, "percentage": 1.11, "elapsed_time": "0:00:39", "remaining_time": "0:58:33", "throughput": 2871.53, "total_tokens": 113648} {"current_steps": 430, "total_steps": 38150, "loss": 1.2326, "lr": 5.622542595019659e-06, "epoch": 0.1127129750982962, "percentage": 1.13, "elapsed_time": "0:00:40", "remaining_time": "0:58:32", "throughput": 2868.82, "total_tokens": 114864} {"current_steps": 435, "total_steps": 38150, "loss": 0.8113, "lr": 5.688073394495413e-06, "epoch": 0.11402359108781127, "percentage": 1.14, "elapsed_time": "0:00:40", "remaining_time": "0:58:28", "throughput": 2865.63, "total_tokens": 115968} {"current_steps": 440, "total_steps": 38150, "loss": 0.8079, "lr": 5.753604193971167e-06, "epoch": 0.11533420707732635, "percentage": 1.15, "elapsed_time": "0:00:40", "remaining_time": "0:58:31", "throughput": 2872.03, "total_tokens": 117680} {"current_steps": 445, "total_steps": 38150, "loss": 0.7636, "lr": 5.81913499344692e-06, "epoch": 0.11664482306684142, "percentage": 1.17, "elapsed_time": "0:00:41", "remaining_time": "0:58:28", "throughput": 2867.45, "total_tokens": 118720} {"current_steps": 450, "total_steps": 38150, "loss": 0.5719, "lr": 5.884665792922674e-06, "epoch": 0.11795543905635648, "percentage": 1.18, "elapsed_time": "0:00:41", "remaining_time": "0:58:28", "throughput": 2872.6, "total_tokens": 120288} {"current_steps": 455, "total_steps": 38150, "loss": 0.701, "lr": 5.950196592398428e-06, "epoch": 0.11926605504587157, "percentage": 1.19, "elapsed_time": "0:00:42", "remaining_time": "0:58:29", "throughput": 2873.64, "total_tokens": 121728} {"current_steps": 460, "total_steps": 38150, "loss": 0.6586, "lr": 6.015727391874181e-06, "epoch": 0.12057667103538663, "percentage": 1.21, "elapsed_time": "0:00:42", "remaining_time": "0:58:26", "throughput": 2871.19, "total_tokens": 122880} {"current_steps": 465, "total_steps": 38150, "loss": 0.7658, "lr": 6.081258191349935e-06, "epoch": 0.1218872870249017, "percentage": 1.22, "elapsed_time": "0:00:43", "remaining_time": "0:58:23", "throughput": 2871.33, "total_tokens": 124112} {"current_steps": 470, "total_steps": 38150, "loss": 0.954, "lr": 6.146788990825689e-06, "epoch": 0.12319790301441677, "percentage": 1.23, "elapsed_time": "0:00:43", "remaining_time": "0:58:23", "throughput": 2873.75, "total_tokens": 125568} {"current_steps": 475, "total_steps": 38150, "loss": 0.6385, "lr": 6.212319790301442e-06, "epoch": 0.12450851900393185, "percentage": 1.25, "elapsed_time": "0:00:44", "remaining_time": "0:58:25", "throughput": 2878.34, "total_tokens": 127216} {"current_steps": 480, "total_steps": 38150, "loss": 0.9186, "lr": 6.277850589777196e-06, "epoch": 0.1258191349934469, "percentage": 1.26, "elapsed_time": "0:00:44", "remaining_time": "0:58:25", "throughput": 2877.78, "total_tokens": 128560} {"current_steps": 485, "total_steps": 38150, "loss": 0.6429, "lr": 6.343381389252949e-06, "epoch": 0.127129750982962, "percentage": 1.27, "elapsed_time": "0:00:45", "remaining_time": "0:58:25", "throughput": 2878.69, "total_tokens": 129952} {"current_steps": 490, "total_steps": 38150, "loss": 0.8343, "lr": 6.408912188728703e-06, "epoch": 0.12844036697247707, "percentage": 1.28, "elapsed_time": "0:00:45", "remaining_time": "0:58:22", "throughput": 2874.05, "total_tokens": 130976} {"current_steps": 495, "total_steps": 38150, "loss": 0.4068, "lr": 6.474442988204456e-06, "epoch": 0.12975098296199214, "percentage": 1.3, "elapsed_time": "0:00:46", "remaining_time": "0:58:19", "throughput": 2875.07, "total_tokens": 132256} {"current_steps": 500, "total_steps": 38150, "loss": 0.8403, "lr": 6.539973787680211e-06, "epoch": 0.1310615989515072, "percentage": 1.31, "elapsed_time": "0:00:46", "remaining_time": "0:58:25", "throughput": 2884.17, "total_tokens": 134256} {"current_steps": 505, "total_steps": 38150, "loss": 0.5071, "lr": 6.605504587155964e-06, "epoch": 0.13237221494102228, "percentage": 1.32, "elapsed_time": "0:00:46", "remaining_time": "0:58:23", "throughput": 2884.99, "total_tokens": 135584} {"current_steps": 510, "total_steps": 38150, "loss": 0.6415, "lr": 6.671035386631718e-06, "epoch": 0.13368283093053734, "percentage": 1.34, "elapsed_time": "0:00:47", "remaining_time": "0:58:19", "throughput": 2880.47, "total_tokens": 136576} {"current_steps": 515, "total_steps": 38150, "loss": 0.5982, "lr": 6.736566186107471e-06, "epoch": 0.1349934469200524, "percentage": 1.35, "elapsed_time": "0:00:47", "remaining_time": "0:58:17", "throughput": 2882.5, "total_tokens": 137952} {"current_steps": 520, "total_steps": 38150, "loss": 0.5363, "lr": 6.8020969855832246e-06, "epoch": 0.1363040629095675, "percentage": 1.36, "elapsed_time": "0:00:48", "remaining_time": "0:58:13", "throughput": 2879.42, "total_tokens": 139024} {"current_steps": 525, "total_steps": 38150, "loss": 0.5653, "lr": 6.867627785058978e-06, "epoch": 0.13761467889908258, "percentage": 1.38, "elapsed_time": "0:00:48", "remaining_time": "0:58:14", "throughput": 2880.36, "total_tokens": 140464} {"current_steps": 530, "total_steps": 38150, "loss": 0.5365, "lr": 6.933158584534731e-06, "epoch": 0.13892529488859764, "percentage": 1.39, "elapsed_time": "0:00:49", "remaining_time": "0:58:14", "throughput": 2880.73, "total_tokens": 141824} {"current_steps": 535, "total_steps": 38150, "loss": 0.5991, "lr": 6.9986893840104855e-06, "epoch": 0.1402359108781127, "percentage": 1.4, "elapsed_time": "0:00:49", "remaining_time": "0:58:11", "throughput": 2877.13, "total_tokens": 142864} {"current_steps": 540, "total_steps": 38150, "loss": 0.8474, "lr": 7.064220183486239e-06, "epoch": 0.14154652686762778, "percentage": 1.42, "elapsed_time": "0:00:50", "remaining_time": "0:58:07", "throughput": 2872.51, "total_tokens": 143856} {"current_steps": 545, "total_steps": 38150, "loss": 0.5345, "lr": 7.1297509829619924e-06, "epoch": 0.14285714285714285, "percentage": 1.43, "elapsed_time": "0:00:50", "remaining_time": "0:58:08", "throughput": 2872.96, "total_tokens": 145248} {"current_steps": 550, "total_steps": 38150, "loss": 0.5313, "lr": 7.195281782437746e-06, "epoch": 0.14416775884665792, "percentage": 1.44, "elapsed_time": "0:00:51", "remaining_time": "0:58:08", "throughput": 2878.61, "total_tokens": 146912} {"current_steps": 555, "total_steps": 38150, "loss": 0.5775, "lr": 7.260812581913499e-06, "epoch": 0.145478374836173, "percentage": 1.45, "elapsed_time": "0:00:51", "remaining_time": "0:58:08", "throughput": 2878.48, "total_tokens": 148224} {"current_steps": 560, "total_steps": 38150, "loss": 0.5419, "lr": 7.326343381389253e-06, "epoch": 0.14678899082568808, "percentage": 1.47, "elapsed_time": "0:00:51", "remaining_time": "0:58:05", "throughput": 2880.17, "total_tokens": 149568} {"current_steps": 565, "total_steps": 38150, "loss": 0.6886, "lr": 7.391874180865006e-06, "epoch": 0.14809960681520315, "percentage": 1.48, "elapsed_time": "0:00:52", "remaining_time": "0:58:05", "throughput": 2880.62, "total_tokens": 150912} {"current_steps": 570, "total_steps": 38150, "loss": 0.6381, "lr": 7.457404980340761e-06, "epoch": 0.14941022280471822, "percentage": 1.49, "elapsed_time": "0:00:52", "remaining_time": "0:58:04", "throughput": 2882.75, "total_tokens": 152352} {"current_steps": 575, "total_steps": 38150, "loss": 0.4535, "lr": 7.522935779816514e-06, "epoch": 0.15072083879423329, "percentage": 1.51, "elapsed_time": "0:00:53", "remaining_time": "0:58:03", "throughput": 2883.91, "total_tokens": 153728} {"current_steps": 580, "total_steps": 38150, "loss": 1.0023, "lr": 7.588466579292268e-06, "epoch": 0.15203145478374835, "percentage": 1.52, "elapsed_time": "0:00:53", "remaining_time": "0:58:03", "throughput": 2885.55, "total_tokens": 155200} {"current_steps": 585, "total_steps": 38150, "loss": 0.6087, "lr": 7.653997378768021e-06, "epoch": 0.15334207077326342, "percentage": 1.53, "elapsed_time": "0:00:54", "remaining_time": "0:58:01", "throughput": 2882.93, "total_tokens": 156288} {"current_steps": 590, "total_steps": 38150, "loss": 0.6053, "lr": 7.719528178243775e-06, "epoch": 0.15465268676277852, "percentage": 1.55, "elapsed_time": "0:00:54", "remaining_time": "0:58:01", "throughput": 2882.94, "total_tokens": 157664} {"current_steps": 595, "total_steps": 38150, "loss": 0.3845, "lr": 7.785058977719529e-06, "epoch": 0.1559633027522936, "percentage": 1.56, "elapsed_time": "0:00:55", "remaining_time": "0:57:58", "throughput": 2881.87, "total_tokens": 158832} {"current_steps": 600, "total_steps": 38150, "loss": 0.5163, "lr": 7.850589777195281e-06, "epoch": 0.15727391874180865, "percentage": 1.57, "elapsed_time": "0:00:55", "remaining_time": "0:57:56", "throughput": 2880.14, "total_tokens": 159984} {"current_steps": 605, "total_steps": 38150, "loss": 0.5095, "lr": 7.916120576671037e-06, "epoch": 0.15858453473132372, "percentage": 1.59, "elapsed_time": "0:00:56", "remaining_time": "0:57:55", "throughput": 2879.06, "total_tokens": 161248} {"current_steps": 610, "total_steps": 38150, "loss": 0.6285, "lr": 7.981651376146789e-06, "epoch": 0.1598951507208388, "percentage": 1.6, "elapsed_time": "0:00:56", "remaining_time": "0:57:53", "throughput": 2880.71, "total_tokens": 162608} {"current_steps": 615, "total_steps": 38150, "loss": 0.5152, "lr": 8.047182175622543e-06, "epoch": 0.16120576671035386, "percentage": 1.61, "elapsed_time": "0:00:56", "remaining_time": "0:57:50", "throughput": 2878.36, "total_tokens": 163696} {"current_steps": 620, "total_steps": 38150, "loss": 0.6275, "lr": 8.112712975098297e-06, "epoch": 0.16251638269986893, "percentage": 1.63, "elapsed_time": "0:00:57", "remaining_time": "0:57:51", "throughput": 2878.13, "total_tokens": 165056} {"current_steps": 625, "total_steps": 38150, "loss": 0.4361, "lr": 8.17824377457405e-06, "epoch": 0.16382699868938402, "percentage": 1.64, "elapsed_time": "0:00:57", "remaining_time": "0:57:54", "throughput": 2883.14, "total_tokens": 166848} {"current_steps": 630, "total_steps": 38150, "loss": 0.6254, "lr": 8.243774574049803e-06, "epoch": 0.1651376146788991, "percentage": 1.65, "elapsed_time": "0:00:58", "remaining_time": "0:57:54", "throughput": 2883.48, "total_tokens": 168240} {"current_steps": 635, "total_steps": 38150, "loss": 0.7787, "lr": 8.309305373525557e-06, "epoch": 0.16644823066841416, "percentage": 1.66, "elapsed_time": "0:00:58", "remaining_time": "0:57:56", "throughput": 2885.93, "total_tokens": 169840} {"current_steps": 640, "total_steps": 38150, "loss": 0.6294, "lr": 8.374836173001311e-06, "epoch": 0.16775884665792923, "percentage": 1.68, "elapsed_time": "0:00:59", "remaining_time": "0:57:55", "throughput": 2886.64, "total_tokens": 171152} {"current_steps": 645, "total_steps": 38150, "loss": 0.7506, "lr": 8.440366972477065e-06, "epoch": 0.1690694626474443, "percentage": 1.69, "elapsed_time": "0:00:59", "remaining_time": "0:57:51", "throughput": 2883.04, "total_tokens": 172144} {"current_steps": 650, "total_steps": 38150, "loss": 0.5968, "lr": 8.505897771952819e-06, "epoch": 0.17038007863695936, "percentage": 1.7, "elapsed_time": "0:01:00", "remaining_time": "0:57:51", "throughput": 2882.42, "total_tokens": 173440} {"current_steps": 655, "total_steps": 38150, "loss": 0.6292, "lr": 8.571428571428573e-06, "epoch": 0.17169069462647443, "percentage": 1.72, "elapsed_time": "0:01:00", "remaining_time": "0:57:52", "throughput": 2883.37, "total_tokens": 174928} {"current_steps": 660, "total_steps": 38150, "loss": 0.5797, "lr": 8.636959370904325e-06, "epoch": 0.17300131061598953, "percentage": 1.73, "elapsed_time": "0:01:01", "remaining_time": "0:57:53", "throughput": 2889.1, "total_tokens": 176672} {"current_steps": 665, "total_steps": 38150, "loss": 0.883, "lr": 8.702490170380079e-06, "epoch": 0.1743119266055046, "percentage": 1.74, "elapsed_time": "0:01:01", "remaining_time": "0:57:52", "throughput": 2884.61, "total_tokens": 177712} {"current_steps": 670, "total_steps": 38150, "loss": 0.773, "lr": 8.768020969855833e-06, "epoch": 0.17562254259501967, "percentage": 1.76, "elapsed_time": "0:01:02", "remaining_time": "0:57:54", "throughput": 2885.71, "total_tokens": 179232} {"current_steps": 675, "total_steps": 38150, "loss": 0.516, "lr": 8.833551769331587e-06, "epoch": 0.17693315858453473, "percentage": 1.77, "elapsed_time": "0:01:02", "remaining_time": "0:57:55", "throughput": 2886.0, "total_tokens": 180688} {"current_steps": 680, "total_steps": 38150, "loss": 0.6025, "lr": 8.89908256880734e-06, "epoch": 0.1782437745740498, "percentage": 1.78, "elapsed_time": "0:01:03", "remaining_time": "0:57:53", "throughput": 2884.65, "total_tokens": 181824} {"current_steps": 685, "total_steps": 38150, "loss": 0.7081, "lr": 8.964613368283094e-06, "epoch": 0.17955439056356487, "percentage": 1.8, "elapsed_time": "0:01:03", "remaining_time": "0:57:50", "throughput": 2880.39, "total_tokens": 182768} {"current_steps": 690, "total_steps": 38150, "loss": 0.7526, "lr": 9.030144167758847e-06, "epoch": 0.18086500655307994, "percentage": 1.81, "elapsed_time": "0:01:03", "remaining_time": "0:57:49", "throughput": 2882.85, "total_tokens": 184240} {"current_steps": 695, "total_steps": 38150, "loss": 0.5776, "lr": 9.0956749672346e-06, "epoch": 0.182175622542595, "percentage": 1.82, "elapsed_time": "0:01:04", "remaining_time": "0:57:47", "throughput": 2878.43, "total_tokens": 185200} {"current_steps": 700, "total_steps": 38150, "loss": 0.4367, "lr": 9.161205766710354e-06, "epoch": 0.1834862385321101, "percentage": 1.83, "elapsed_time": "0:01:04", "remaining_time": "0:57:46", "throughput": 2877.67, "total_tokens": 186464} {"current_steps": 705, "total_steps": 38150, "loss": 0.4508, "lr": 9.226736566186107e-06, "epoch": 0.18479685452162517, "percentage": 1.85, "elapsed_time": "0:01:05", "remaining_time": "0:57:44", "throughput": 2878.09, "total_tokens": 187728} {"current_steps": 710, "total_steps": 38150, "loss": 0.5393, "lr": 9.29226736566186e-06, "epoch": 0.18610747051114024, "percentage": 1.86, "elapsed_time": "0:01:05", "remaining_time": "0:57:43", "throughput": 2876.78, "total_tokens": 188944} {"current_steps": 715, "total_steps": 38150, "loss": 0.641, "lr": 9.357798165137616e-06, "epoch": 0.1874180865006553, "percentage": 1.87, "elapsed_time": "0:01:06", "remaining_time": "0:57:41", "throughput": 2877.93, "total_tokens": 190288} {"current_steps": 720, "total_steps": 38150, "loss": 0.398, "lr": 9.423328964613368e-06, "epoch": 0.18872870249017037, "percentage": 1.89, "elapsed_time": "0:01:06", "remaining_time": "0:57:38", "throughput": 2874.66, "total_tokens": 191264} {"current_steps": 725, "total_steps": 38150, "loss": 0.6598, "lr": 9.488859764089122e-06, "epoch": 0.19003931847968544, "percentage": 1.9, "elapsed_time": "0:01:06", "remaining_time": "0:57:36", "throughput": 2872.44, "total_tokens": 192336} {"current_steps": 730, "total_steps": 38150, "loss": 0.5838, "lr": 9.554390563564876e-06, "epoch": 0.1913499344692005, "percentage": 1.91, "elapsed_time": "0:01:07", "remaining_time": "0:57:34", "throughput": 2872.72, "total_tokens": 193584} {"current_steps": 735, "total_steps": 38150, "loss": 0.5564, "lr": 9.619921363040628e-06, "epoch": 0.1926605504587156, "percentage": 1.93, "elapsed_time": "0:01:07", "remaining_time": "0:57:32", "throughput": 2872.0, "total_tokens": 194800} {"current_steps": 740, "total_steps": 38150, "loss": 0.5241, "lr": 9.685452162516382e-06, "epoch": 0.19397116644823068, "percentage": 1.94, "elapsed_time": "0:01:08", "remaining_time": "0:57:32", "throughput": 2872.98, "total_tokens": 196192} {"current_steps": 745, "total_steps": 38150, "loss": 0.5093, "lr": 9.750982961992136e-06, "epoch": 0.19528178243774574, "percentage": 1.95, "elapsed_time": "0:01:08", "remaining_time": "0:57:30", "throughput": 2869.86, "total_tokens": 197200} {"current_steps": 750, "total_steps": 38150, "loss": 0.7171, "lr": 9.81651376146789e-06, "epoch": 0.1965923984272608, "percentage": 1.97, "elapsed_time": "0:01:09", "remaining_time": "0:57:28", "throughput": 2868.76, "total_tokens": 198384} {"current_steps": 755, "total_steps": 38150, "loss": 0.6555, "lr": 9.882044560943644e-06, "epoch": 0.19790301441677588, "percentage": 1.98, "elapsed_time": "0:01:09", "remaining_time": "0:57:27", "throughput": 2869.18, "total_tokens": 199680} {"current_steps": 760, "total_steps": 38150, "loss": 0.527, "lr": 9.947575360419398e-06, "epoch": 0.19921363040629095, "percentage": 1.99, "elapsed_time": "0:01:10", "remaining_time": "0:57:25", "throughput": 2869.32, "total_tokens": 200960} {"current_steps": 765, "total_steps": 38150, "loss": 0.6909, "lr": 1.0013106159895152e-05, "epoch": 0.20052424639580602, "percentage": 2.01, "elapsed_time": "0:01:10", "remaining_time": "0:57:29", "throughput": 2877.86, "total_tokens": 203120} {"current_steps": 770, "total_steps": 38150, "loss": 0.798, "lr": 1.0078636959370904e-05, "epoch": 0.2018348623853211, "percentage": 2.02, "elapsed_time": "0:01:11", "remaining_time": "0:57:31", "throughput": 2881.54, "total_tokens": 204848} {"current_steps": 775, "total_steps": 38150, "loss": 0.6908, "lr": 1.0144167758846658e-05, "epoch": 0.20314547837483618, "percentage": 2.03, "elapsed_time": "0:01:11", "remaining_time": "0:57:29", "throughput": 2881.19, "total_tokens": 206080} {"current_steps": 780, "total_steps": 38150, "loss": 0.6829, "lr": 1.0209698558322412e-05, "epoch": 0.20445609436435125, "percentage": 2.04, "elapsed_time": "0:01:12", "remaining_time": "0:57:30", "throughput": 2886.78, "total_tokens": 207920} {"current_steps": 785, "total_steps": 38150, "loss": 0.6658, "lr": 1.0275229357798166e-05, "epoch": 0.20576671035386632, "percentage": 2.06, "elapsed_time": "0:01:12", "remaining_time": "0:57:28", "throughput": 2885.08, "total_tokens": 209040} {"current_steps": 790, "total_steps": 38150, "loss": 0.5424, "lr": 1.034076015727392e-05, "epoch": 0.20707732634338138, "percentage": 2.07, "elapsed_time": "0:01:12", "remaining_time": "0:57:27", "throughput": 2886.11, "total_tokens": 210384} {"current_steps": 795, "total_steps": 38150, "loss": 0.6535, "lr": 1.0406290956749674e-05, "epoch": 0.20838794233289645, "percentage": 2.08, "elapsed_time": "0:01:13", "remaining_time": "0:57:30", "throughput": 2887.46, "total_tokens": 212032} {"current_steps": 800, "total_steps": 38150, "loss": 0.6656, "lr": 1.0471821756225426e-05, "epoch": 0.20969855832241152, "percentage": 2.1, "elapsed_time": "0:01:13", "remaining_time": "0:57:27", "throughput": 2882.88, "total_tokens": 212896} {"current_steps": 805, "total_steps": 38150, "loss": 0.8836, "lr": 1.053735255570118e-05, "epoch": 0.21100917431192662, "percentage": 2.11, "elapsed_time": "0:01:14", "remaining_time": "0:57:28", "throughput": 2883.7, "total_tokens": 214352} {"current_steps": 810, "total_steps": 38150, "loss": 0.7186, "lr": 1.0602883355176934e-05, "epoch": 0.21231979030144169, "percentage": 2.12, "elapsed_time": "0:01:14", "remaining_time": "0:57:27", "throughput": 2883.41, "total_tokens": 215664} {"current_steps": 815, "total_steps": 38150, "loss": 0.5419, "lr": 1.0668414154652686e-05, "epoch": 0.21363040629095675, "percentage": 2.14, "elapsed_time": "0:01:15", "remaining_time": "0:57:28", "throughput": 2884.42, "total_tokens": 217104} {"current_steps": 820, "total_steps": 38150, "loss": 0.6325, "lr": 1.0733944954128442e-05, "epoch": 0.21494102228047182, "percentage": 2.15, "elapsed_time": "0:01:15", "remaining_time": "0:57:25", "throughput": 2882.93, "total_tokens": 218224} {"current_steps": 825, "total_steps": 38150, "loss": 0.5473, "lr": 1.0799475753604196e-05, "epoch": 0.2162516382699869, "percentage": 2.16, "elapsed_time": "0:01:16", "remaining_time": "0:57:24", "throughput": 2884.0, "total_tokens": 219584} {"current_steps": 830, "total_steps": 38150, "loss": 0.6417, "lr": 1.0865006553079948e-05, "epoch": 0.21756225425950196, "percentage": 2.18, "elapsed_time": "0:01:16", "remaining_time": "0:57:23", "throughput": 2884.84, "total_tokens": 220912} {"current_steps": 835, "total_steps": 38150, "loss": 0.4998, "lr": 1.0930537352555702e-05, "epoch": 0.21887287024901703, "percentage": 2.19, "elapsed_time": "0:01:17", "remaining_time": "0:57:23", "throughput": 2884.82, "total_tokens": 222272} {"current_steps": 840, "total_steps": 38150, "loss": 0.6581, "lr": 1.0996068152031456e-05, "epoch": 0.22018348623853212, "percentage": 2.2, "elapsed_time": "0:01:17", "remaining_time": "0:57:22", "throughput": 2884.7, "total_tokens": 223600} {"current_steps": 845, "total_steps": 38150, "loss": 0.8038, "lr": 1.1061598951507208e-05, "epoch": 0.2214941022280472, "percentage": 2.21, "elapsed_time": "0:01:18", "remaining_time": "0:57:26", "throughput": 2885.5, "total_tokens": 225232} {"current_steps": 850, "total_steps": 38150, "loss": 0.5353, "lr": 1.1127129750982962e-05, "epoch": 0.22280471821756226, "percentage": 2.23, "elapsed_time": "0:01:18", "remaining_time": "0:57:24", "throughput": 2885.75, "total_tokens": 226512} {"current_steps": 855, "total_steps": 38150, "loss": 0.7659, "lr": 1.1192660550458717e-05, "epoch": 0.22411533420707733, "percentage": 2.24, "elapsed_time": "0:01:18", "remaining_time": "0:57:22", "throughput": 2883.44, "total_tokens": 227552} {"current_steps": 860, "total_steps": 38150, "loss": 0.6396, "lr": 1.125819134993447e-05, "epoch": 0.2254259501965924, "percentage": 2.25, "elapsed_time": "0:01:19", "remaining_time": "0:57:20", "throughput": 2881.31, "total_tokens": 228608} {"current_steps": 865, "total_steps": 38150, "loss": 0.369, "lr": 1.1323722149410223e-05, "epoch": 0.22673656618610746, "percentage": 2.27, "elapsed_time": "0:01:19", "remaining_time": "0:57:21", "throughput": 2882.87, "total_tokens": 230192} {"current_steps": 870, "total_steps": 38150, "loss": 0.5466, "lr": 1.1389252948885977e-05, "epoch": 0.22804718217562253, "percentage": 2.28, "elapsed_time": "0:01:20", "remaining_time": "0:57:22", "throughput": 2884.9, "total_tokens": 231776} {"current_steps": 875, "total_steps": 38150, "loss": 0.7968, "lr": 1.145478374836173e-05, "epoch": 0.22935779816513763, "percentage": 2.29, "elapsed_time": "0:01:20", "remaining_time": "0:57:21", "throughput": 2885.05, "total_tokens": 233104} {"current_steps": 880, "total_steps": 38150, "loss": 0.6053, "lr": 1.1520314547837483e-05, "epoch": 0.2306684141546527, "percentage": 2.31, "elapsed_time": "0:01:21", "remaining_time": "0:57:19", "throughput": 2882.88, "total_tokens": 234128} {"current_steps": 885, "total_steps": 38150, "loss": 0.6386, "lr": 1.1585845347313237e-05, "epoch": 0.23197903014416776, "percentage": 2.32, "elapsed_time": "0:01:21", "remaining_time": "0:57:17", "throughput": 2882.33, "total_tokens": 235312} {"current_steps": 890, "total_steps": 38150, "loss": 0.5435, "lr": 1.1651376146788991e-05, "epoch": 0.23328964613368283, "percentage": 2.33, "elapsed_time": "0:01:22", "remaining_time": "0:57:19", "throughput": 2883.63, "total_tokens": 236896} {"current_steps": 895, "total_steps": 38150, "loss": 0.621, "lr": 1.1716906946264745e-05, "epoch": 0.2346002621231979, "percentage": 2.35, "elapsed_time": "0:01:22", "remaining_time": "0:57:17", "throughput": 2881.21, "total_tokens": 237936} {"current_steps": 900, "total_steps": 38150, "loss": 0.6815, "lr": 1.1782437745740499e-05, "epoch": 0.23591087811271297, "percentage": 2.36, "elapsed_time": "0:01:23", "remaining_time": "0:57:18", "throughput": 2883.31, "total_tokens": 239552} {"current_steps": 905, "total_steps": 38150, "loss": 0.5094, "lr": 1.1847968545216253e-05, "epoch": 0.23722149410222804, "percentage": 2.37, "elapsed_time": "0:01:23", "remaining_time": "0:57:17", "throughput": 2883.61, "total_tokens": 240832} {"current_steps": 910, "total_steps": 38150, "loss": 0.618, "lr": 1.1913499344692005e-05, "epoch": 0.23853211009174313, "percentage": 2.39, "elapsed_time": "0:01:23", "remaining_time": "0:57:16", "throughput": 2883.99, "total_tokens": 242192} {"current_steps": 915, "total_steps": 38150, "loss": 0.6321, "lr": 1.197903014416776e-05, "epoch": 0.2398427260812582, "percentage": 2.4, "elapsed_time": "0:01:24", "remaining_time": "0:57:14", "throughput": 2884.25, "total_tokens": 243456} {"current_steps": 920, "total_steps": 38150, "loss": 0.7367, "lr": 1.2044560943643513e-05, "epoch": 0.24115334207077327, "percentage": 2.41, "elapsed_time": "0:01:24", "remaining_time": "0:57:17", "throughput": 2889.4, "total_tokens": 245424} {"current_steps": 925, "total_steps": 38150, "loss": 0.5099, "lr": 1.2110091743119267e-05, "epoch": 0.24246395806028834, "percentage": 2.42, "elapsed_time": "0:01:25", "remaining_time": "0:57:16", "throughput": 2889.47, "total_tokens": 246752} {"current_steps": 930, "total_steps": 38150, "loss": 0.5029, "lr": 1.2175622542595021e-05, "epoch": 0.2437745740498034, "percentage": 2.44, "elapsed_time": "0:01:25", "remaining_time": "0:57:16", "throughput": 2890.8, "total_tokens": 248256} {"current_steps": 935, "total_steps": 38150, "loss": 0.501, "lr": 1.2241153342070775e-05, "epoch": 0.24508519003931847, "percentage": 2.45, "elapsed_time": "0:01:26", "remaining_time": "0:57:16", "throughput": 2891.28, "total_tokens": 249648} {"current_steps": 940, "total_steps": 38150, "loss": 0.652, "lr": 1.2306684141546527e-05, "epoch": 0.24639580602883354, "percentage": 2.46, "elapsed_time": "0:01:26", "remaining_time": "0:57:20", "throughput": 2895.09, "total_tokens": 251600} {"current_steps": 945, "total_steps": 38150, "loss": 0.5978, "lr": 1.2372214941022281e-05, "epoch": 0.24770642201834864, "percentage": 2.48, "elapsed_time": "0:01:27", "remaining_time": "0:57:18", "throughput": 2891.94, "total_tokens": 252544} {"current_steps": 950, "total_steps": 38150, "loss": 1.0158, "lr": 1.2437745740498035e-05, "epoch": 0.2490170380078637, "percentage": 2.49, "elapsed_time": "0:01:27", "remaining_time": "0:57:16", "throughput": 2891.54, "total_tokens": 253776} {"current_steps": 955, "total_steps": 38150, "loss": 0.4462, "lr": 1.2503276539973787e-05, "epoch": 0.2503276539973788, "percentage": 2.5, "elapsed_time": "0:01:28", "remaining_time": "0:57:16", "throughput": 2892.38, "total_tokens": 255232} {"current_steps": 960, "total_steps": 38150, "loss": 0.6149, "lr": 1.2568807339449543e-05, "epoch": 0.2516382699868938, "percentage": 2.52, "elapsed_time": "0:01:28", "remaining_time": "0:57:16", "throughput": 2892.97, "total_tokens": 256640} {"current_steps": 965, "total_steps": 38150, "loss": 0.5854, "lr": 1.2634338138925295e-05, "epoch": 0.2529488859764089, "percentage": 2.53, "elapsed_time": "0:01:29", "remaining_time": "0:57:15", "throughput": 2891.52, "total_tokens": 257760} {"current_steps": 970, "total_steps": 38150, "loss": 0.4989, "lr": 1.2699868938401049e-05, "epoch": 0.254259501965924, "percentage": 2.54, "elapsed_time": "0:01:29", "remaining_time": "0:57:13", "throughput": 2890.98, "total_tokens": 258960} {"current_steps": 975, "total_steps": 38150, "loss": 0.4653, "lr": 1.2765399737876801e-05, "epoch": 0.25557011795543905, "percentage": 2.56, "elapsed_time": "0:01:30", "remaining_time": "0:57:14", "throughput": 2892.14, "total_tokens": 260528} {"current_steps": 980, "total_steps": 38150, "loss": 0.5024, "lr": 1.2830930537352557e-05, "epoch": 0.25688073394495414, "percentage": 2.57, "elapsed_time": "0:01:30", "remaining_time": "0:57:13", "throughput": 2891.57, "total_tokens": 261744} {"current_steps": 985, "total_steps": 38150, "loss": 0.6827, "lr": 1.289646133682831e-05, "epoch": 0.2581913499344692, "percentage": 2.58, "elapsed_time": "0:01:30", "remaining_time": "0:57:11", "throughput": 2891.17, "total_tokens": 262928} {"current_steps": 990, "total_steps": 38150, "loss": 0.5349, "lr": 1.2961992136304063e-05, "epoch": 0.2595019659239843, "percentage": 2.6, "elapsed_time": "0:01:31", "remaining_time": "0:57:10", "throughput": 2893.06, "total_tokens": 264384} {"current_steps": 995, "total_steps": 38150, "loss": 0.9413, "lr": 1.3027522935779818e-05, "epoch": 0.2608125819134993, "percentage": 2.61, "elapsed_time": "0:01:31", "remaining_time": "0:57:08", "throughput": 2890.48, "total_tokens": 265392} {"current_steps": 1000, "total_steps": 38150, "loss": 0.8985, "lr": 1.309305373525557e-05, "epoch": 0.2621231979030144, "percentage": 2.62, "elapsed_time": "0:01:32", "remaining_time": "0:57:07", "throughput": 2890.03, "total_tokens": 266608} {"current_steps": 1005, "total_steps": 38150, "loss": 0.5641, "lr": 1.3158584534731325e-05, "epoch": 0.2634338138925295, "percentage": 2.63, "elapsed_time": "0:01:32", "remaining_time": "0:57:05", "throughput": 2891.09, "total_tokens": 267984} {"current_steps": 1010, "total_steps": 38150, "loss": 0.7562, "lr": 1.3224115334207077e-05, "epoch": 0.26474442988204455, "percentage": 2.65, "elapsed_time": "0:01:33", "remaining_time": "0:57:03", "throughput": 2888.45, "total_tokens": 268944} {"current_steps": 1015, "total_steps": 38150, "loss": 0.5354, "lr": 1.328964613368283e-05, "epoch": 0.26605504587155965, "percentage": 2.66, "elapsed_time": "0:01:33", "remaining_time": "0:57:04", "throughput": 2891.66, "total_tokens": 270672} {"current_steps": 1020, "total_steps": 38150, "loss": 0.483, "lr": 1.3355176933158586e-05, "epoch": 0.2673656618610747, "percentage": 2.67, "elapsed_time": "0:01:34", "remaining_time": "0:57:04", "throughput": 2893.46, "total_tokens": 272208} {"current_steps": 1025, "total_steps": 38150, "loss": 0.6171, "lr": 1.3420707732634339e-05, "epoch": 0.2686762778505898, "percentage": 2.69, "elapsed_time": "0:01:34", "remaining_time": "0:57:10", "throughput": 2900.13, "total_tokens": 274720} {"current_steps": 1030, "total_steps": 38150, "loss": 2.272, "lr": 1.3486238532110092e-05, "epoch": 0.2699868938401048, "percentage": 2.7, "elapsed_time": "0:01:35", "remaining_time": "0:57:09", "throughput": 2897.18, "total_tokens": 275664} {"current_steps": 1035, "total_steps": 38150, "loss": 0.7778, "lr": 1.3551769331585845e-05, "epoch": 0.2712975098296199, "percentage": 2.71, "elapsed_time": "0:01:35", "remaining_time": "0:57:10", "throughput": 2901.12, "total_tokens": 277568} {"current_steps": 1040, "total_steps": 38150, "loss": 0.493, "lr": 1.36173001310616e-05, "epoch": 0.272608125819135, "percentage": 2.73, "elapsed_time": "0:01:36", "remaining_time": "0:57:10", "throughput": 2900.63, "total_tokens": 278848} {"current_steps": 1045, "total_steps": 38150, "loss": 0.4935, "lr": 1.3682830930537352e-05, "epoch": 0.27391874180865006, "percentage": 2.74, "elapsed_time": "0:01:36", "remaining_time": "0:57:08", "throughput": 2899.38, "total_tokens": 279968} {"current_steps": 1050, "total_steps": 38150, "loss": 0.8195, "lr": 1.3748361730013106e-05, "epoch": 0.27522935779816515, "percentage": 2.75, "elapsed_time": "0:01:37", "remaining_time": "0:57:07", "throughput": 2898.76, "total_tokens": 281184} {"current_steps": 1055, "total_steps": 38150, "loss": 0.4179, "lr": 1.3813892529488862e-05, "epoch": 0.2765399737876802, "percentage": 2.77, "elapsed_time": "0:01:37", "remaining_time": "0:57:06", "throughput": 2899.25, "total_tokens": 282576} {"current_steps": 1060, "total_steps": 38150, "loss": 0.4908, "lr": 1.3879423328964614e-05, "epoch": 0.2778505897771953, "percentage": 2.78, "elapsed_time": "0:01:37", "remaining_time": "0:57:06", "throughput": 2900.64, "total_tokens": 284064} {"current_steps": 1065, "total_steps": 38150, "loss": 0.5646, "lr": 1.3944954128440368e-05, "epoch": 0.27916120576671033, "percentage": 2.79, "elapsed_time": "0:01:38", "remaining_time": "0:57:05", "throughput": 2899.45, "total_tokens": 285200} {"current_steps": 1070, "total_steps": 38150, "loss": 0.5693, "lr": 1.401048492791612e-05, "epoch": 0.2804718217562254, "percentage": 2.8, "elapsed_time": "0:01:38", "remaining_time": "0:57:04", "throughput": 2898.49, "total_tokens": 286432} {"current_steps": 1075, "total_steps": 38150, "loss": 0.5216, "lr": 1.4076015727391876e-05, "epoch": 0.2817824377457405, "percentage": 2.82, "elapsed_time": "0:01:39", "remaining_time": "0:57:04", "throughput": 2899.3, "total_tokens": 287888} {"current_steps": 1080, "total_steps": 38150, "loss": 0.6007, "lr": 1.4141546526867626e-05, "epoch": 0.28309305373525556, "percentage": 2.83, "elapsed_time": "0:01:39", "remaining_time": "0:57:03", "throughput": 2899.06, "total_tokens": 289120} {"current_steps": 1085, "total_steps": 38150, "loss": 0.7544, "lr": 1.4207077326343382e-05, "epoch": 0.28440366972477066, "percentage": 2.84, "elapsed_time": "0:01:40", "remaining_time": "0:57:01", "throughput": 2895.92, "total_tokens": 290032} {"current_steps": 1090, "total_steps": 38150, "loss": 0.4716, "lr": 1.4272608125819138e-05, "epoch": 0.2857142857142857, "percentage": 2.86, "elapsed_time": "0:01:40", "remaining_time": "0:57:00", "throughput": 2896.07, "total_tokens": 291328} {"current_steps": 1095, "total_steps": 38150, "loss": 0.3886, "lr": 1.4338138925294888e-05, "epoch": 0.2870249017038008, "percentage": 2.87, "elapsed_time": "0:01:41", "remaining_time": "0:57:04", "throughput": 2901.58, "total_tokens": 293632} {"current_steps": 1100, "total_steps": 38150, "loss": 0.734, "lr": 1.4403669724770644e-05, "epoch": 0.28833551769331583, "percentage": 2.88, "elapsed_time": "0:01:41", "remaining_time": "0:57:03", "throughput": 2900.8, "total_tokens": 294880} {"current_steps": 1105, "total_steps": 38150, "loss": 0.5104, "lr": 1.4469200524246396e-05, "epoch": 0.28964613368283093, "percentage": 2.9, "elapsed_time": "0:01:42", "remaining_time": "0:57:02", "throughput": 2901.41, "total_tokens": 296208} {"current_steps": 1110, "total_steps": 38150, "loss": 0.5594, "lr": 1.453473132372215e-05, "epoch": 0.290956749672346, "percentage": 2.91, "elapsed_time": "0:01:42", "remaining_time": "0:57:02", "throughput": 2902.96, "total_tokens": 297760} {"current_steps": 1115, "total_steps": 38150, "loss": 0.5377, "lr": 1.4600262123197902e-05, "epoch": 0.29226736566186107, "percentage": 2.92, "elapsed_time": "0:01:42", "remaining_time": "0:57:01", "throughput": 2901.39, "total_tokens": 298832} {"current_steps": 1120, "total_steps": 38150, "loss": 0.559, "lr": 1.4665792922673658e-05, "epoch": 0.29357798165137616, "percentage": 2.94, "elapsed_time": "0:01:43", "remaining_time": "0:56:59", "throughput": 2901.54, "total_tokens": 300112} {"current_steps": 1125, "total_steps": 38150, "loss": 0.634, "lr": 1.4731323722149412e-05, "epoch": 0.2948885976408912, "percentage": 2.95, "elapsed_time": "0:01:43", "remaining_time": "0:56:57", "throughput": 2900.68, "total_tokens": 301248} {"current_steps": 1130, "total_steps": 38150, "loss": 0.5054, "lr": 1.4796854521625164e-05, "epoch": 0.2961992136304063, "percentage": 2.96, "elapsed_time": "0:01:44", "remaining_time": "0:56:57", "throughput": 2901.31, "total_tokens": 302656} {"current_steps": 1135, "total_steps": 38150, "loss": 0.5848, "lr": 1.486238532110092e-05, "epoch": 0.29750982961992134, "percentage": 2.98, "elapsed_time": "0:01:44", "remaining_time": "0:56:56", "throughput": 2901.6, "total_tokens": 304000} {"current_steps": 1140, "total_steps": 38150, "loss": 0.6479, "lr": 1.4927916120576672e-05, "epoch": 0.29882044560943644, "percentage": 2.99, "elapsed_time": "0:01:45", "remaining_time": "0:56:56", "throughput": 2902.49, "total_tokens": 305472} {"current_steps": 1145, "total_steps": 38150, "loss": 0.345, "lr": 1.4993446920052426e-05, "epoch": 0.30013106159895153, "percentage": 3.0, "elapsed_time": "0:01:45", "remaining_time": "0:56:54", "throughput": 2900.24, "total_tokens": 306448} {"current_steps": 1150, "total_steps": 38150, "loss": 0.8363, "lr": 1.5058977719528178e-05, "epoch": 0.30144167758846657, "percentage": 3.01, "elapsed_time": "0:01:46", "remaining_time": "0:56:53", "throughput": 2899.69, "total_tokens": 307632} {"current_steps": 1155, "total_steps": 38150, "loss": 0.3954, "lr": 1.5124508519003932e-05, "epoch": 0.30275229357798167, "percentage": 3.03, "elapsed_time": "0:01:46", "remaining_time": "0:56:51", "throughput": 2898.88, "total_tokens": 308784} {"current_steps": 1160, "total_steps": 38150, "loss": 0.5174, "lr": 1.5190039318479687e-05, "epoch": 0.3040629095674967, "percentage": 3.04, "elapsed_time": "0:01:46", "remaining_time": "0:56:51", "throughput": 2898.95, "total_tokens": 310096} {"current_steps": 1165, "total_steps": 38150, "loss": 1.2299, "lr": 1.525557011795544e-05, "epoch": 0.3053735255570118, "percentage": 3.05, "elapsed_time": "0:01:47", "remaining_time": "0:56:50", "throughput": 2899.48, "total_tokens": 311472} {"current_steps": 1170, "total_steps": 38150, "loss": 0.6401, "lr": 1.5321100917431195e-05, "epoch": 0.30668414154652685, "percentage": 3.07, "elapsed_time": "0:01:47", "remaining_time": "0:56:49", "throughput": 2898.75, "total_tokens": 312704} {"current_steps": 1175, "total_steps": 38150, "loss": 0.4761, "lr": 1.5386631716906946e-05, "epoch": 0.30799475753604194, "percentage": 3.08, "elapsed_time": "0:01:48", "remaining_time": "0:56:48", "throughput": 2898.03, "total_tokens": 313888} {"current_steps": 1180, "total_steps": 38150, "loss": 0.5755, "lr": 1.54521625163827e-05, "epoch": 0.30930537352555704, "percentage": 3.09, "elapsed_time": "0:01:48", "remaining_time": "0:56:47", "throughput": 2896.56, "total_tokens": 315040} {"current_steps": 1185, "total_steps": 38150, "loss": 0.9387, "lr": 1.5517693315858454e-05, "epoch": 0.3106159895150721, "percentage": 3.11, "elapsed_time": "0:01:49", "remaining_time": "0:56:46", "throughput": 2896.88, "total_tokens": 316352} {"current_steps": 1190, "total_steps": 38150, "loss": 0.6202, "lr": 1.5583224115334208e-05, "epoch": 0.3119266055045872, "percentage": 3.12, "elapsed_time": "0:01:49", "remaining_time": "0:56:46", "throughput": 2896.22, "total_tokens": 317616} {"current_steps": 1195, "total_steps": 38150, "loss": 0.6555, "lr": 1.564875491480996e-05, "epoch": 0.3132372214941022, "percentage": 3.13, "elapsed_time": "0:01:50", "remaining_time": "0:56:46", "throughput": 2897.97, "total_tokens": 319184} {"current_steps": 1200, "total_steps": 38150, "loss": 0.5981, "lr": 1.5714285714285715e-05, "epoch": 0.3145478374836173, "percentage": 3.15, "elapsed_time": "0:01:50", "remaining_time": "0:56:46", "throughput": 2899.28, "total_tokens": 320752} {"current_steps": 1205, "total_steps": 38150, "loss": 0.4747, "lr": 1.577981651376147e-05, "epoch": 0.31585845347313235, "percentage": 3.16, "elapsed_time": "0:01:51", "remaining_time": "0:56:45", "throughput": 2899.19, "total_tokens": 322032} {"current_steps": 1210, "total_steps": 38150, "loss": 0.5116, "lr": 1.5845347313237223e-05, "epoch": 0.31716906946264745, "percentage": 3.17, "elapsed_time": "0:01:51", "remaining_time": "0:56:44", "throughput": 2899.5, "total_tokens": 323360} {"current_steps": 1215, "total_steps": 38150, "loss": 0.473, "lr": 1.5910878112712977e-05, "epoch": 0.31847968545216254, "percentage": 3.18, "elapsed_time": "0:01:51", "remaining_time": "0:56:43", "throughput": 2898.67, "total_tokens": 324528} {"current_steps": 1220, "total_steps": 38150, "loss": 0.5086, "lr": 1.5976408912188728e-05, "epoch": 0.3197903014416776, "percentage": 3.2, "elapsed_time": "0:01:52", "remaining_time": "0:56:47", "throughput": 2904.1, "total_tokens": 326928} {"current_steps": 1225, "total_steps": 38150, "loss": 0.4242, "lr": 1.604193971166448e-05, "epoch": 0.3211009174311927, "percentage": 3.21, "elapsed_time": "0:01:53", "remaining_time": "0:56:47", "throughput": 2905.01, "total_tokens": 328432} {"current_steps": 1230, "total_steps": 38150, "loss": 0.5819, "lr": 1.610747051114024e-05, "epoch": 0.3224115334207077, "percentage": 3.22, "elapsed_time": "0:01:53", "remaining_time": "0:56:46", "throughput": 2902.95, "total_tokens": 329440} {"current_steps": 1235, "total_steps": 38150, "loss": 0.3952, "lr": 1.617300131061599e-05, "epoch": 0.3237221494102228, "percentage": 3.24, "elapsed_time": "0:01:53", "remaining_time": "0:56:46", "throughput": 2903.82, "total_tokens": 330912} {"current_steps": 1240, "total_steps": 38150, "loss": 0.5953, "lr": 1.6238532110091743e-05, "epoch": 0.32503276539973786, "percentage": 3.25, "elapsed_time": "0:01:54", "remaining_time": "0:56:45", "throughput": 2904.0, "total_tokens": 332288} {"current_steps": 1245, "total_steps": 38150, "loss": 0.5915, "lr": 1.6304062909567497e-05, "epoch": 0.32634338138925295, "percentage": 3.26, "elapsed_time": "0:01:54", "remaining_time": "0:56:44", "throughput": 2904.31, "total_tokens": 333584} {"current_steps": 1250, "total_steps": 38150, "loss": 0.5593, "lr": 1.636959370904325e-05, "epoch": 0.32765399737876805, "percentage": 3.28, "elapsed_time": "0:01:55", "remaining_time": "0:56:47", "throughput": 2905.88, "total_tokens": 335392} {"current_steps": 1255, "total_steps": 38150, "loss": 0.6625, "lr": 1.6435124508519005e-05, "epoch": 0.3289646133682831, "percentage": 3.29, "elapsed_time": "0:01:55", "remaining_time": "0:56:45", "throughput": 2905.17, "total_tokens": 336560} {"current_steps": 1260, "total_steps": 38150, "loss": 0.634, "lr": 1.650065530799476e-05, "epoch": 0.3302752293577982, "percentage": 3.3, "elapsed_time": "0:01:56", "remaining_time": "0:56:45", "throughput": 2907.23, "total_tokens": 338192} {"current_steps": 1265, "total_steps": 38150, "loss": 0.6497, "lr": 1.6566186107470513e-05, "epoch": 0.3315858453473132, "percentage": 3.32, "elapsed_time": "0:01:56", "remaining_time": "0:56:45", "throughput": 2907.59, "total_tokens": 339568} {"current_steps": 1270, "total_steps": 38150, "loss": 0.4776, "lr": 1.6631716906946267e-05, "epoch": 0.3328964613368283, "percentage": 3.33, "elapsed_time": "0:01:57", "remaining_time": "0:56:43", "throughput": 2906.93, "total_tokens": 340736} {"current_steps": 1275, "total_steps": 38150, "loss": 1.1958, "lr": 1.669724770642202e-05, "epoch": 0.33420707732634336, "percentage": 3.34, "elapsed_time": "0:01:57", "remaining_time": "0:56:42", "throughput": 2904.38, "total_tokens": 341680} {"current_steps": 1280, "total_steps": 38150, "loss": 0.6276, "lr": 1.676277850589777e-05, "epoch": 0.33551769331585846, "percentage": 3.36, "elapsed_time": "0:01:58", "remaining_time": "0:56:40", "throughput": 2903.62, "total_tokens": 342800} {"current_steps": 1285, "total_steps": 38150, "loss": 0.6474, "lr": 1.682830930537353e-05, "epoch": 0.33682830930537355, "percentage": 3.37, "elapsed_time": "0:01:58", "remaining_time": "0:56:39", "throughput": 2903.33, "total_tokens": 344000} {"current_steps": 1290, "total_steps": 38150, "loss": 0.5122, "lr": 1.689384010484928e-05, "epoch": 0.3381389252948886, "percentage": 3.38, "elapsed_time": "0:01:59", "remaining_time": "0:56:41", "throughput": 2906.42, "total_tokens": 345968} {"current_steps": 1295, "total_steps": 38150, "loss": 0.4873, "lr": 1.6959370904325033e-05, "epoch": 0.3394495412844037, "percentage": 3.39, "elapsed_time": "0:01:59", "remaining_time": "0:56:41", "throughput": 2905.42, "total_tokens": 347264} {"current_steps": 1300, "total_steps": 38150, "loss": 0.5323, "lr": 1.702490170380079e-05, "epoch": 0.34076015727391873, "percentage": 3.41, "elapsed_time": "0:02:00", "remaining_time": "0:56:41", "throughput": 2905.87, "total_tokens": 348720} {"current_steps": 1305, "total_steps": 38150, "loss": 0.43, "lr": 1.709043250327654e-05, "epoch": 0.3420707732634338, "percentage": 3.42, "elapsed_time": "0:02:00", "remaining_time": "0:56:40", "throughput": 2906.12, "total_tokens": 350032} {"current_steps": 1310, "total_steps": 38150, "loss": 0.5165, "lr": 1.7155963302752295e-05, "epoch": 0.34338138925294887, "percentage": 3.43, "elapsed_time": "0:02:00", "remaining_time": "0:56:40", "throughput": 2906.4, "total_tokens": 351408} {"current_steps": 1315, "total_steps": 38150, "loss": 0.4325, "lr": 1.722149410222805e-05, "epoch": 0.34469200524246396, "percentage": 3.45, "elapsed_time": "0:02:01", "remaining_time": "0:56:38", "throughput": 2905.51, "total_tokens": 352560} {"current_steps": 1320, "total_steps": 38150, "loss": 0.5998, "lr": 1.7287024901703802e-05, "epoch": 0.34600262123197906, "percentage": 3.46, "elapsed_time": "0:02:01", "remaining_time": "0:56:38", "throughput": 2905.14, "total_tokens": 353824} {"current_steps": 1325, "total_steps": 38150, "loss": 0.4273, "lr": 1.7352555701179553e-05, "epoch": 0.3473132372214941, "percentage": 3.47, "elapsed_time": "0:02:02", "remaining_time": "0:56:38", "throughput": 2906.59, "total_tokens": 355456} {"current_steps": 1330, "total_steps": 38150, "loss": 0.4973, "lr": 1.741808650065531e-05, "epoch": 0.3486238532110092, "percentage": 3.49, "elapsed_time": "0:02:02", "remaining_time": "0:56:37", "throughput": 2904.9, "total_tokens": 356528} {"current_steps": 1335, "total_steps": 38150, "loss": 0.3728, "lr": 1.7483617300131064e-05, "epoch": 0.34993446920052423, "percentage": 3.5, "elapsed_time": "0:02:03", "remaining_time": "0:56:36", "throughput": 2904.17, "total_tokens": 357664} {"current_steps": 1340, "total_steps": 38150, "loss": 0.6563, "lr": 1.7549148099606815e-05, "epoch": 0.35124508519003933, "percentage": 3.51, "elapsed_time": "0:02:03", "remaining_time": "0:56:36", "throughput": 2904.83, "total_tokens": 359136} {"current_steps": 1345, "total_steps": 38150, "loss": 0.3813, "lr": 1.7614678899082572e-05, "epoch": 0.35255570117955437, "percentage": 3.53, "elapsed_time": "0:02:04", "remaining_time": "0:56:35", "throughput": 2905.9, "total_tokens": 360560} {"current_steps": 1350, "total_steps": 38150, "loss": 0.6403, "lr": 1.7680209698558323e-05, "epoch": 0.35386631716906947, "percentage": 3.54, "elapsed_time": "0:02:04", "remaining_time": "0:56:34", "throughput": 2906.65, "total_tokens": 361952} {"current_steps": 1355, "total_steps": 38150, "loss": 0.5332, "lr": 1.7745740498034076e-05, "epoch": 0.35517693315858456, "percentage": 3.55, "elapsed_time": "0:02:05", "remaining_time": "0:56:34", "throughput": 2906.61, "total_tokens": 363360} {"current_steps": 1360, "total_steps": 38150, "loss": 0.6022, "lr": 1.781127129750983e-05, "epoch": 0.3564875491480996, "percentage": 3.56, "elapsed_time": "0:02:05", "remaining_time": "0:56:33", "throughput": 2905.7, "total_tokens": 364480} {"current_steps": 1365, "total_steps": 38150, "loss": 0.7471, "lr": 1.7876802096985584e-05, "epoch": 0.3577981651376147, "percentage": 3.58, "elapsed_time": "0:02:05", "remaining_time": "0:56:31", "throughput": 2904.58, "total_tokens": 365584} {"current_steps": 1370, "total_steps": 38150, "loss": 0.7135, "lr": 1.7942332896461335e-05, "epoch": 0.35910878112712974, "percentage": 3.59, "elapsed_time": "0:02:06", "remaining_time": "0:56:30", "throughput": 2903.67, "total_tokens": 366704} {"current_steps": 1375, "total_steps": 38150, "loss": 0.7771, "lr": 1.8007863695937092e-05, "epoch": 0.36041939711664484, "percentage": 3.6, "elapsed_time": "0:02:06", "remaining_time": "0:56:29", "throughput": 2903.81, "total_tokens": 368000} {"current_steps": 1380, "total_steps": 38150, "loss": 0.4134, "lr": 1.8073394495412846e-05, "epoch": 0.3617300131061599, "percentage": 3.62, "elapsed_time": "0:02:07", "remaining_time": "0:56:29", "throughput": 2903.67, "total_tokens": 369360} {"current_steps": 1385, "total_steps": 38150, "loss": 0.53, "lr": 1.8138925294888597e-05, "epoch": 0.36304062909567497, "percentage": 3.63, "elapsed_time": "0:02:07", "remaining_time": "0:56:29", "throughput": 2904.71, "total_tokens": 370864} {"current_steps": 1390, "total_steps": 38150, "loss": 0.3567, "lr": 1.8204456094364354e-05, "epoch": 0.36435124508519, "percentage": 3.64, "elapsed_time": "0:02:08", "remaining_time": "0:56:27", "throughput": 2903.96, "total_tokens": 372000} {"current_steps": 1395, "total_steps": 38150, "loss": 0.9822, "lr": 1.8269986893840104e-05, "epoch": 0.3656618610747051, "percentage": 3.66, "elapsed_time": "0:02:08", "remaining_time": "0:56:26", "throughput": 2903.39, "total_tokens": 373168} {"current_steps": 1400, "total_steps": 38150, "loss": 0.64, "lr": 1.833551769331586e-05, "epoch": 0.3669724770642202, "percentage": 3.67, "elapsed_time": "0:02:08", "remaining_time": "0:56:25", "throughput": 2902.38, "total_tokens": 374304} {"current_steps": 1405, "total_steps": 38150, "loss": 0.3163, "lr": 1.8401048492791612e-05, "epoch": 0.36828309305373524, "percentage": 3.68, "elapsed_time": "0:02:09", "remaining_time": "0:56:25", "throughput": 2904.03, "total_tokens": 375888} {"current_steps": 1410, "total_steps": 38150, "loss": 0.5838, "lr": 1.8466579292267366e-05, "epoch": 0.36959370904325034, "percentage": 3.7, "elapsed_time": "0:02:09", "remaining_time": "0:56:24", "throughput": 2904.56, "total_tokens": 377296} {"current_steps": 1415, "total_steps": 38150, "loss": 0.4152, "lr": 1.853211009174312e-05, "epoch": 0.3709043250327654, "percentage": 3.71, "elapsed_time": "0:02:10", "remaining_time": "0:56:24", "throughput": 2904.43, "total_tokens": 378608} {"current_steps": 1420, "total_steps": 38150, "loss": 0.4893, "lr": 1.8597640891218874e-05, "epoch": 0.3722149410222805, "percentage": 3.72, "elapsed_time": "0:02:10", "remaining_time": "0:56:24", "throughput": 2905.51, "total_tokens": 380192} {"current_steps": 1425, "total_steps": 38150, "loss": 0.5901, "lr": 1.8663171690694628e-05, "epoch": 0.3735255570117955, "percentage": 3.74, "elapsed_time": "0:02:11", "remaining_time": "0:56:23", "throughput": 2906.53, "total_tokens": 381616} {"current_steps": 1430, "total_steps": 38150, "loss": 0.505, "lr": 1.872870249017038e-05, "epoch": 0.3748361730013106, "percentage": 3.75, "elapsed_time": "0:02:11", "remaining_time": "0:56:22", "throughput": 2905.19, "total_tokens": 382672} {"current_steps": 1435, "total_steps": 38150, "loss": 0.5805, "lr": 1.8794233289646136e-05, "epoch": 0.3761467889908257, "percentage": 3.76, "elapsed_time": "0:02:12", "remaining_time": "0:56:21", "throughput": 2906.58, "total_tokens": 384176} {"current_steps": 1440, "total_steps": 38150, "loss": 0.7246, "lr": 1.8859764089121886e-05, "epoch": 0.37745740498034075, "percentage": 3.77, "elapsed_time": "0:02:12", "remaining_time": "0:56:21", "throughput": 2907.07, "total_tokens": 385584} {"current_steps": 1445, "total_steps": 38150, "loss": 0.4377, "lr": 1.892529488859764e-05, "epoch": 0.37876802096985585, "percentage": 3.79, "elapsed_time": "0:02:13", "remaining_time": "0:56:20", "throughput": 2906.59, "total_tokens": 386832} {"current_steps": 1450, "total_steps": 38150, "loss": 0.4578, "lr": 1.8990825688073397e-05, "epoch": 0.3800786369593709, "percentage": 3.8, "elapsed_time": "0:02:13", "remaining_time": "0:56:21", "throughput": 2907.44, "total_tokens": 388416} {"current_steps": 1455, "total_steps": 38150, "loss": 0.3723, "lr": 1.9056356487549148e-05, "epoch": 0.381389252948886, "percentage": 3.81, "elapsed_time": "0:02:14", "remaining_time": "0:56:20", "throughput": 2907.2, "total_tokens": 389648} {"current_steps": 1460, "total_steps": 38150, "loss": 0.3484, "lr": 1.9121887287024902e-05, "epoch": 0.382699868938401, "percentage": 3.83, "elapsed_time": "0:02:14", "remaining_time": "0:56:19", "throughput": 2906.82, "total_tokens": 390864} {"current_steps": 1465, "total_steps": 38150, "loss": 0.5137, "lr": 1.9187418086500656e-05, "epoch": 0.3840104849279161, "percentage": 3.84, "elapsed_time": "0:02:14", "remaining_time": "0:56:18", "throughput": 2906.82, "total_tokens": 392128} {"current_steps": 1470, "total_steps": 38150, "loss": 0.6429, "lr": 1.925294888597641e-05, "epoch": 0.3853211009174312, "percentage": 3.85, "elapsed_time": "0:02:15", "remaining_time": "0:56:24", "throughput": 2911.06, "total_tokens": 394864} {"current_steps": 1475, "total_steps": 38150, "loss": 0.4161, "lr": 1.9318479685452164e-05, "epoch": 0.38663171690694625, "percentage": 3.87, "elapsed_time": "0:02:16", "remaining_time": "0:56:23", "throughput": 2908.85, "total_tokens": 395776} {"current_steps": 1480, "total_steps": 38150, "loss": 0.7234, "lr": 1.9384010484927918e-05, "epoch": 0.38794233289646135, "percentage": 3.88, "elapsed_time": "0:02:16", "remaining_time": "0:56:21", "throughput": 2907.8, "total_tokens": 396880} {"current_steps": 1485, "total_steps": 38150, "loss": 0.4897, "lr": 1.944954128440367e-05, "epoch": 0.3892529488859764, "percentage": 3.89, "elapsed_time": "0:02:16", "remaining_time": "0:56:22", "throughput": 2909.11, "total_tokens": 398512} {"current_steps": 1490, "total_steps": 38150, "loss": 0.7631, "lr": 1.9515072083879425e-05, "epoch": 0.3905635648754915, "percentage": 3.91, "elapsed_time": "0:02:17", "remaining_time": "0:56:20", "throughput": 2908.42, "total_tokens": 399664} {"current_steps": 1495, "total_steps": 38150, "loss": 0.3469, "lr": 1.958060288335518e-05, "epoch": 0.3918741808650065, "percentage": 3.92, "elapsed_time": "0:02:17", "remaining_time": "0:56:19", "throughput": 2907.92, "total_tokens": 400864} {"current_steps": 1500, "total_steps": 38150, "loss": 0.5932, "lr": 1.964613368283093e-05, "epoch": 0.3931847968545216, "percentage": 3.93, "elapsed_time": "0:02:18", "remaining_time": "0:56:19", "throughput": 2908.69, "total_tokens": 402352} {"current_steps": 1505, "total_steps": 38150, "loss": 0.5632, "lr": 1.9711664482306684e-05, "epoch": 0.3944954128440367, "percentage": 3.94, "elapsed_time": "0:02:18", "remaining_time": "0:56:19", "throughput": 2908.93, "total_tokens": 403744} {"current_steps": 1510, "total_steps": 38150, "loss": 0.5145, "lr": 1.9777195281782438e-05, "epoch": 0.39580602883355176, "percentage": 3.96, "elapsed_time": "0:02:19", "remaining_time": "0:56:18", "throughput": 2909.51, "total_tokens": 405104} {"current_steps": 1515, "total_steps": 38150, "loss": 0.7461, "lr": 1.984272608125819e-05, "epoch": 0.39711664482306686, "percentage": 3.97, "elapsed_time": "0:02:19", "remaining_time": "0:56:16", "throughput": 2908.73, "total_tokens": 406208} {"current_steps": 1520, "total_steps": 38150, "loss": 0.5303, "lr": 1.9908256880733945e-05, "epoch": 0.3984272608125819, "percentage": 3.98, "elapsed_time": "0:02:20", "remaining_time": "0:56:15", "throughput": 2906.4, "total_tokens": 407120} {"current_steps": 1525, "total_steps": 38150, "loss": 0.5914, "lr": 1.99737876802097e-05, "epoch": 0.399737876802097, "percentage": 4.0, "elapsed_time": "0:02:20", "remaining_time": "0:56:14", "throughput": 2904.63, "total_tokens": 408080} {"current_steps": 1530, "total_steps": 38150, "loss": 0.5925, "lr": 2.0039318479685453e-05, "epoch": 0.40104849279161203, "percentage": 4.01, "elapsed_time": "0:02:20", "remaining_time": "0:56:13", "throughput": 2904.35, "total_tokens": 409360} {"current_steps": 1535, "total_steps": 38150, "loss": 0.4984, "lr": 2.0104849279161207e-05, "epoch": 0.40235910878112713, "percentage": 4.02, "elapsed_time": "0:02:21", "remaining_time": "0:56:12", "throughput": 2904.81, "total_tokens": 410720} {"current_steps": 1540, "total_steps": 38150, "loss": 0.5547, "lr": 2.017038007863696e-05, "epoch": 0.4036697247706422, "percentage": 4.04, "elapsed_time": "0:02:21", "remaining_time": "0:56:11", "throughput": 2904.45, "total_tokens": 411904} {"current_steps": 1545, "total_steps": 38150, "loss": 0.574, "lr": 2.023591087811271e-05, "epoch": 0.40498034076015726, "percentage": 4.05, "elapsed_time": "0:02:22", "remaining_time": "0:56:09", "throughput": 2903.33, "total_tokens": 412960} {"current_steps": 1550, "total_steps": 38150, "loss": 0.5387, "lr": 2.030144167758847e-05, "epoch": 0.40629095674967236, "percentage": 4.06, "elapsed_time": "0:02:22", "remaining_time": "0:56:11", "throughput": 2905.26, "total_tokens": 414784} {"current_steps": 1555, "total_steps": 38150, "loss": 0.5704, "lr": 2.0366972477064223e-05, "epoch": 0.4076015727391874, "percentage": 4.08, "elapsed_time": "0:02:23", "remaining_time": "0:56:10", "throughput": 2906.11, "total_tokens": 416208} {"current_steps": 1560, "total_steps": 38150, "loss": 0.4686, "lr": 2.0432503276539973e-05, "epoch": 0.4089121887287025, "percentage": 4.09, "elapsed_time": "0:02:23", "remaining_time": "0:56:09", "throughput": 2905.93, "total_tokens": 417440} {"current_steps": 1565, "total_steps": 38150, "loss": 0.5881, "lr": 2.049803407601573e-05, "epoch": 0.41022280471821754, "percentage": 4.1, "elapsed_time": "0:02:24", "remaining_time": "0:56:09", "throughput": 2906.68, "total_tokens": 419008} {"current_steps": 1570, "total_steps": 38150, "loss": 0.5021, "lr": 2.056356487549148e-05, "epoch": 0.41153342070773263, "percentage": 4.12, "elapsed_time": "0:02:24", "remaining_time": "0:56:08", "throughput": 2907.41, "total_tokens": 420384} {"current_steps": 1575, "total_steps": 38150, "loss": 0.5988, "lr": 2.0629095674967235e-05, "epoch": 0.41284403669724773, "percentage": 4.13, "elapsed_time": "0:02:25", "remaining_time": "0:56:07", "throughput": 2906.18, "total_tokens": 421440} {"current_steps": 1580, "total_steps": 38150, "loss": 0.5494, "lr": 2.069462647444299e-05, "epoch": 0.41415465268676277, "percentage": 4.14, "elapsed_time": "0:02:25", "remaining_time": "0:56:06", "throughput": 2905.68, "total_tokens": 422608} {"current_steps": 1585, "total_steps": 38150, "loss": 0.527, "lr": 2.0760157273918743e-05, "epoch": 0.41546526867627787, "percentage": 4.15, "elapsed_time": "0:02:25", "remaining_time": "0:56:05", "throughput": 2906.17, "total_tokens": 423952} {"current_steps": 1590, "total_steps": 38150, "loss": 0.5064, "lr": 2.0825688073394497e-05, "epoch": 0.4167758846657929, "percentage": 4.17, "elapsed_time": "0:02:26", "remaining_time": "0:56:05", "throughput": 2907.53, "total_tokens": 425552} {"current_steps": 1595, "total_steps": 38150, "loss": 0.6502, "lr": 2.089121887287025e-05, "epoch": 0.418086500655308, "percentage": 4.18, "elapsed_time": "0:02:26", "remaining_time": "0:56:04", "throughput": 2906.51, "total_tokens": 426656} {"current_steps": 1600, "total_steps": 38150, "loss": 0.7287, "lr": 2.0956749672346005e-05, "epoch": 0.41939711664482304, "percentage": 4.19, "elapsed_time": "0:02:27", "remaining_time": "0:56:03", "throughput": 2905.06, "total_tokens": 427696} {"current_steps": 1605, "total_steps": 38150, "loss": 0.5959, "lr": 2.1022280471821755e-05, "epoch": 0.42070773263433814, "percentage": 4.21, "elapsed_time": "0:02:27", "remaining_time": "0:56:01", "throughput": 2903.38, "total_tokens": 428656} {"current_steps": 1610, "total_steps": 38150, "loss": 0.6838, "lr": 2.1087811271297513e-05, "epoch": 0.42201834862385323, "percentage": 4.22, "elapsed_time": "0:02:28", "remaining_time": "0:56:01", "throughput": 2904.09, "total_tokens": 430128} {"current_steps": 1615, "total_steps": 38150, "loss": 0.3815, "lr": 2.1153342070773263e-05, "epoch": 0.4233289646133683, "percentage": 4.23, "elapsed_time": "0:02:28", "remaining_time": "0:56:01", "throughput": 2905.46, "total_tokens": 431792} {"current_steps": 1620, "total_steps": 38150, "loss": 0.4181, "lr": 2.1218872870249017e-05, "epoch": 0.42463958060288337, "percentage": 4.25, "elapsed_time": "0:02:29", "remaining_time": "0:56:01", "throughput": 2906.28, "total_tokens": 433200} {"current_steps": 1625, "total_steps": 38150, "loss": 0.4455, "lr": 2.1284403669724774e-05, "epoch": 0.4259501965923984, "percentage": 4.26, "elapsed_time": "0:02:29", "remaining_time": "0:56:00", "throughput": 2907.35, "total_tokens": 434688} {"current_steps": 1630, "total_steps": 38150, "loss": 0.7561, "lr": 2.1349934469200525e-05, "epoch": 0.4272608125819135, "percentage": 4.27, "elapsed_time": "0:02:29", "remaining_time": "0:55:59", "throughput": 2907.2, "total_tokens": 435920} {"current_steps": 1635, "total_steps": 38150, "loss": 0.5686, "lr": 2.141546526867628e-05, "epoch": 0.42857142857142855, "percentage": 4.29, "elapsed_time": "0:02:30", "remaining_time": "0:56:01", "throughput": 2909.97, "total_tokens": 438000} {"current_steps": 1640, "total_steps": 38150, "loss": 0.5332, "lr": 2.1480996068152033e-05, "epoch": 0.42988204456094364, "percentage": 4.3, "elapsed_time": "0:02:30", "remaining_time": "0:56:00", "throughput": 2909.11, "total_tokens": 439104} {"current_steps": 1645, "total_steps": 38150, "loss": 0.5709, "lr": 2.1546526867627787e-05, "epoch": 0.43119266055045874, "percentage": 4.31, "elapsed_time": "0:02:31", "remaining_time": "0:55:59", "throughput": 2909.33, "total_tokens": 440400} {"current_steps": 1650, "total_steps": 38150, "loss": 0.5826, "lr": 2.1612057667103537e-05, "epoch": 0.4325032765399738, "percentage": 4.33, "elapsed_time": "0:02:31", "remaining_time": "0:56:01", "throughput": 2912.18, "total_tokens": 442592} {"current_steps": 1655, "total_steps": 38150, "loss": 0.6349, "lr": 2.1677588466579294e-05, "epoch": 0.4338138925294889, "percentage": 4.34, "elapsed_time": "0:02:32", "remaining_time": "0:56:01", "throughput": 2912.61, "total_tokens": 444016} {"current_steps": 1660, "total_steps": 38150, "loss": 0.5075, "lr": 2.1743119266055048e-05, "epoch": 0.4351245085190039, "percentage": 4.35, "elapsed_time": "0:02:32", "remaining_time": "0:56:01", "throughput": 2912.74, "total_tokens": 445424} {"current_steps": 1665, "total_steps": 38150, "loss": 0.4579, "lr": 2.18086500655308e-05, "epoch": 0.436435124508519, "percentage": 4.36, "elapsed_time": "0:02:33", "remaining_time": "0:56:00", "throughput": 2913.09, "total_tokens": 446768} {"current_steps": 1670, "total_steps": 38150, "loss": 0.7532, "lr": 2.1874180865006556e-05, "epoch": 0.43774574049803405, "percentage": 4.38, "elapsed_time": "0:02:33", "remaining_time": "0:56:00", "throughput": 2914.06, "total_tokens": 448288} {"current_steps": 1675, "total_steps": 38150, "loss": 0.7297, "lr": 2.1939711664482307e-05, "epoch": 0.43905635648754915, "percentage": 4.39, "elapsed_time": "0:02:34", "remaining_time": "0:55:59", "throughput": 2913.31, "total_tokens": 449440} {"current_steps": 1680, "total_steps": 38150, "loss": 0.4648, "lr": 2.200524246395806e-05, "epoch": 0.44036697247706424, "percentage": 4.4, "elapsed_time": "0:02:34", "remaining_time": "0:55:59", "throughput": 2913.58, "total_tokens": 450832} {"current_steps": 1685, "total_steps": 38150, "loss": 0.6376, "lr": 2.2070773263433814e-05, "epoch": 0.4416775884665793, "percentage": 4.42, "elapsed_time": "0:02:35", "remaining_time": "0:55:57", "throughput": 2913.04, "total_tokens": 451984} {"current_steps": 1690, "total_steps": 38150, "loss": 0.5312, "lr": 2.213630406290957e-05, "epoch": 0.4429882044560944, "percentage": 4.43, "elapsed_time": "0:02:35", "remaining_time": "0:55:56", "throughput": 2913.71, "total_tokens": 453376} {"current_steps": 1695, "total_steps": 38150, "loss": 0.424, "lr": 2.2201834862385322e-05, "epoch": 0.4442988204456094, "percentage": 4.44, "elapsed_time": "0:02:36", "remaining_time": "0:55:56", "throughput": 2913.77, "total_tokens": 454672} {"current_steps": 1700, "total_steps": 38150, "loss": 0.4403, "lr": 2.2267365661861076e-05, "epoch": 0.4456094364351245, "percentage": 4.46, "elapsed_time": "0:02:36", "remaining_time": "0:55:56", "throughput": 2914.74, "total_tokens": 456240} {"current_steps": 1705, "total_steps": 38150, "loss": 0.4756, "lr": 2.233289646133683e-05, "epoch": 0.44692005242463956, "percentage": 4.47, "elapsed_time": "0:02:36", "remaining_time": "0:55:55", "throughput": 2915.02, "total_tokens": 457632} {"current_steps": 1710, "total_steps": 38150, "loss": 0.3792, "lr": 2.239842726081258e-05, "epoch": 0.44823066841415465, "percentage": 4.48, "elapsed_time": "0:02:37", "remaining_time": "0:55:56", "throughput": 2915.62, "total_tokens": 459200} {"current_steps": 1715, "total_steps": 38150, "loss": 0.5779, "lr": 2.2463958060288338e-05, "epoch": 0.44954128440366975, "percentage": 4.5, "elapsed_time": "0:02:37", "remaining_time": "0:55:55", "throughput": 2915.16, "total_tokens": 460384} {"current_steps": 1720, "total_steps": 38150, "loss": 0.5067, "lr": 2.252948885976409e-05, "epoch": 0.4508519003931848, "percentage": 4.51, "elapsed_time": "0:02:38", "remaining_time": "0:55:54", "throughput": 2915.38, "total_tokens": 461712} {"current_steps": 1725, "total_steps": 38150, "loss": 0.3813, "lr": 2.2595019659239842e-05, "epoch": 0.4521625163826999, "percentage": 4.52, "elapsed_time": "0:02:38", "remaining_time": "0:55:52", "throughput": 2914.79, "total_tokens": 462832} {"current_steps": 1730, "total_steps": 38150, "loss": 0.4115, "lr": 2.26605504587156e-05, "epoch": 0.4534731323722149, "percentage": 4.53, "elapsed_time": "0:02:39", "remaining_time": "0:55:52", "throughput": 2914.91, "total_tokens": 464224} {"current_steps": 1735, "total_steps": 38150, "loss": 0.4886, "lr": 2.272608125819135e-05, "epoch": 0.45478374836173, "percentage": 4.55, "elapsed_time": "0:02:39", "remaining_time": "0:55:52", "throughput": 2915.56, "total_tokens": 465696} {"current_steps": 1740, "total_steps": 38150, "loss": 0.542, "lr": 2.2791612057667104e-05, "epoch": 0.45609436435124506, "percentage": 4.56, "elapsed_time": "0:02:40", "remaining_time": "0:55:52", "throughput": 2914.9, "total_tokens": 466944} {"current_steps": 1745, "total_steps": 38150, "loss": 0.5699, "lr": 2.2857142857142858e-05, "epoch": 0.45740498034076016, "percentage": 4.57, "elapsed_time": "0:02:40", "remaining_time": "0:55:51", "throughput": 2915.18, "total_tokens": 468256} {"current_steps": 1750, "total_steps": 38150, "loss": 0.5485, "lr": 2.2922673656618612e-05, "epoch": 0.45871559633027525, "percentage": 4.59, "elapsed_time": "0:02:41", "remaining_time": "0:55:49", "throughput": 2914.43, "total_tokens": 469376} {"current_steps": 1755, "total_steps": 38150, "loss": 0.6248, "lr": 2.2988204456094366e-05, "epoch": 0.4600262123197903, "percentage": 4.6, "elapsed_time": "0:02:41", "remaining_time": "0:55:48", "throughput": 2912.64, "total_tokens": 470336} {"current_steps": 1760, "total_steps": 38150, "loss": 0.6179, "lr": 2.305373525557012e-05, "epoch": 0.4613368283093054, "percentage": 4.61, "elapsed_time": "0:02:41", "remaining_time": "0:55:47", "throughput": 2911.32, "total_tokens": 471360} {"current_steps": 1765, "total_steps": 38150, "loss": 0.6513, "lr": 2.3119266055045874e-05, "epoch": 0.46264744429882043, "percentage": 4.63, "elapsed_time": "0:02:42", "remaining_time": "0:55:46", "throughput": 2911.0, "total_tokens": 472576} {"current_steps": 1770, "total_steps": 38150, "loss": 0.6138, "lr": 2.3184796854521628e-05, "epoch": 0.4639580602883355, "percentage": 4.64, "elapsed_time": "0:02:42", "remaining_time": "0:55:46", "throughput": 2912.32, "total_tokens": 474224} {"current_steps": 1775, "total_steps": 38150, "loss": 0.5069, "lr": 2.325032765399738e-05, "epoch": 0.46526867627785057, "percentage": 4.65, "elapsed_time": "0:02:43", "remaining_time": "0:55:45", "throughput": 2911.84, "total_tokens": 475376} {"current_steps": 1780, "total_steps": 38150, "loss": 0.681, "lr": 2.3315858453473132e-05, "epoch": 0.46657929226736566, "percentage": 4.67, "elapsed_time": "0:02:43", "remaining_time": "0:55:44", "throughput": 2911.23, "total_tokens": 476592} {"current_steps": 1785, "total_steps": 38150, "loss": 0.6823, "lr": 2.3381389252948886e-05, "epoch": 0.46788990825688076, "percentage": 4.68, "elapsed_time": "0:02:44", "remaining_time": "0:55:43", "throughput": 2909.42, "total_tokens": 477504} {"current_steps": 1790, "total_steps": 38150, "loss": 0.5181, "lr": 2.344692005242464e-05, "epoch": 0.4692005242463958, "percentage": 4.69, "elapsed_time": "0:02:44", "remaining_time": "0:55:42", "throughput": 2908.21, "total_tokens": 478560} {"current_steps": 1795, "total_steps": 38150, "loss": 0.4554, "lr": 2.3512450851900394e-05, "epoch": 0.4705111402359109, "percentage": 4.71, "elapsed_time": "0:02:44", "remaining_time": "0:55:41", "throughput": 2908.61, "total_tokens": 479920} {"current_steps": 1800, "total_steps": 38150, "loss": 0.3995, "lr": 2.3577981651376148e-05, "epoch": 0.47182175622542594, "percentage": 4.72, "elapsed_time": "0:02:45", "remaining_time": "0:55:40", "throughput": 2908.98, "total_tokens": 481264} {"current_steps": 1805, "total_steps": 38150, "loss": 0.9633, "lr": 2.36435124508519e-05, "epoch": 0.47313237221494103, "percentage": 4.73, "elapsed_time": "0:02:45", "remaining_time": "0:55:40", "throughput": 2908.97, "total_tokens": 482608} {"current_steps": 1810, "total_steps": 38150, "loss": 0.4989, "lr": 2.3709043250327656e-05, "epoch": 0.4744429882044561, "percentage": 4.74, "elapsed_time": "0:02:46", "remaining_time": "0:55:40", "throughput": 2909.65, "total_tokens": 484096} {"current_steps": 1815, "total_steps": 38150, "loss": 0.5268, "lr": 2.377457404980341e-05, "epoch": 0.47575360419397117, "percentage": 4.76, "elapsed_time": "0:02:46", "remaining_time": "0:55:39", "throughput": 2908.53, "total_tokens": 485120} {"current_steps": 1820, "total_steps": 38150, "loss": 0.3852, "lr": 2.3840104849279163e-05, "epoch": 0.47706422018348627, "percentage": 4.77, "elapsed_time": "0:02:47", "remaining_time": "0:55:37", "throughput": 2907.01, "total_tokens": 486080} {"current_steps": 1825, "total_steps": 38150, "loss": 0.5655, "lr": 2.3905635648754914e-05, "epoch": 0.4783748361730013, "percentage": 4.78, "elapsed_time": "0:02:47", "remaining_time": "0:55:36", "throughput": 2907.06, "total_tokens": 487344} {"current_steps": 1830, "total_steps": 38150, "loss": 0.4897, "lr": 2.397116644823067e-05, "epoch": 0.4796854521625164, "percentage": 4.8, "elapsed_time": "0:02:48", "remaining_time": "0:55:35", "throughput": 2907.0, "total_tokens": 488608} {"current_steps": 1835, "total_steps": 38150, "loss": 0.5226, "lr": 2.4036697247706425e-05, "epoch": 0.48099606815203144, "percentage": 4.81, "elapsed_time": "0:02:48", "remaining_time": "0:55:34", "throughput": 2905.84, "total_tokens": 489664} {"current_steps": 1840, "total_steps": 38150, "loss": 0.4796, "lr": 2.4102228047182176e-05, "epoch": 0.48230668414154654, "percentage": 4.82, "elapsed_time": "0:02:48", "remaining_time": "0:55:34", "throughput": 2906.46, "total_tokens": 491120} {"current_steps": 1845, "total_steps": 38150, "loss": 0.4987, "lr": 2.4167758846657933e-05, "epoch": 0.4836173001310616, "percentage": 4.84, "elapsed_time": "0:02:49", "remaining_time": "0:55:34", "throughput": 2906.51, "total_tokens": 492464} {"current_steps": 1850, "total_steps": 38150, "loss": 0.5534, "lr": 2.4233289646133683e-05, "epoch": 0.4849279161205767, "percentage": 4.85, "elapsed_time": "0:02:49", "remaining_time": "0:55:33", "throughput": 2906.41, "total_tokens": 493712} {"current_steps": 1855, "total_steps": 38150, "loss": 0.4145, "lr": 2.4298820445609437e-05, "epoch": 0.48623853211009177, "percentage": 4.86, "elapsed_time": "0:02:50", "remaining_time": "0:55:31", "throughput": 2905.76, "total_tokens": 494816} {"current_steps": 1860, "total_steps": 38150, "loss": 0.4663, "lr": 2.436435124508519e-05, "epoch": 0.4875491480996068, "percentage": 4.88, "elapsed_time": "0:02:50", "remaining_time": "0:55:31", "throughput": 2906.23, "total_tokens": 496256} {"current_steps": 1865, "total_steps": 38150, "loss": 0.5588, "lr": 2.4429882044560945e-05, "epoch": 0.4888597640891219, "percentage": 4.89, "elapsed_time": "0:02:51", "remaining_time": "0:55:30", "throughput": 2905.16, "total_tokens": 497280} {"current_steps": 1870, "total_steps": 38150, "loss": 0.6248, "lr": 2.44954128440367e-05, "epoch": 0.49017038007863695, "percentage": 4.9, "elapsed_time": "0:02:51", "remaining_time": "0:55:29", "throughput": 2903.11, "total_tokens": 498144} {"current_steps": 1875, "total_steps": 38150, "loss": 0.5519, "lr": 2.4560943643512453e-05, "epoch": 0.49148099606815204, "percentage": 4.91, "elapsed_time": "0:02:52", "remaining_time": "0:55:29", "throughput": 2903.65, "total_tokens": 499648} {"current_steps": 1880, "total_steps": 38150, "loss": 0.4062, "lr": 2.4626474442988207e-05, "epoch": 0.4927916120576671, "percentage": 4.93, "elapsed_time": "0:02:52", "remaining_time": "0:55:29", "throughput": 2905.46, "total_tokens": 501488} {"current_steps": 1885, "total_steps": 38150, "loss": 0.6932, "lr": 2.4692005242463957e-05, "epoch": 0.4941022280471822, "percentage": 4.94, "elapsed_time": "0:02:53", "remaining_time": "0:55:30", "throughput": 2907.92, "total_tokens": 503456} {"current_steps": 1890, "total_steps": 38150, "loss": 0.3835, "lr": 2.4757536041939715e-05, "epoch": 0.4954128440366973, "percentage": 4.95, "elapsed_time": "0:02:53", "remaining_time": "0:55:29", "throughput": 2907.1, "total_tokens": 504544} {"current_steps": 1895, "total_steps": 38150, "loss": 0.5434, "lr": 2.4823066841415465e-05, "epoch": 0.4967234600262123, "percentage": 4.97, "elapsed_time": "0:02:53", "remaining_time": "0:55:28", "throughput": 2906.66, "total_tokens": 505728} {"current_steps": 1900, "total_steps": 38150, "loss": 0.6397, "lr": 2.488859764089122e-05, "epoch": 0.4980340760157274, "percentage": 4.98, "elapsed_time": "0:02:54", "remaining_time": "0:55:27", "throughput": 2904.97, "total_tokens": 506640} {"current_steps": 1905, "total_steps": 38150, "loss": 0.4217, "lr": 2.4954128440366977e-05, "epoch": 0.49934469200524245, "percentage": 4.99, "elapsed_time": "0:02:54", "remaining_time": "0:55:26", "throughput": 2905.11, "total_tokens": 507904} {"current_steps": 1908, "total_steps": 38150, "eval_loss": 0.5446770191192627, "epoch": 0.5001310615989515, "percentage": 5.0, "elapsed_time": "0:03:11", "remaining_time": "1:00:46", "throughput": 2649.37, "total_tokens": 508608} {"current_steps": 1910, "total_steps": 38150, "loss": 0.5547, "lr": 2.501965923984273e-05, "epoch": 0.5006553079947575, "percentage": 5.01, "elapsed_time": "0:03:14", "remaining_time": "1:01:26", "throughput": 2619.46, "total_tokens": 508992} {"current_steps": 1915, "total_steps": 38150, "loss": 0.3163, "lr": 2.5085190039318478e-05, "epoch": 0.5019659239842726, "percentage": 5.02, "elapsed_time": "0:03:14", "remaining_time": "1:01:25", "throughput": 2619.72, "total_tokens": 510256} {"current_steps": 1920, "total_steps": 38150, "loss": 0.5593, "lr": 2.5150720838794235e-05, "epoch": 0.5032765399737876, "percentage": 5.03, "elapsed_time": "0:03:15", "remaining_time": "1:01:23", "throughput": 2620.4, "total_tokens": 511536} {"current_steps": 1925, "total_steps": 38150, "loss": 0.6053, "lr": 2.521625163826999e-05, "epoch": 0.5045871559633027, "percentage": 5.05, "elapsed_time": "0:03:15", "remaining_time": "1:01:22", "throughput": 2621.49, "total_tokens": 512992} {"current_steps": 1930, "total_steps": 38150, "loss": 0.4414, "lr": 2.5281782437745743e-05, "epoch": 0.5058977719528178, "percentage": 5.06, "elapsed_time": "0:03:16", "remaining_time": "1:01:20", "throughput": 2621.71, "total_tokens": 514208} {"current_steps": 1935, "total_steps": 38150, "loss": 0.7122, "lr": 2.5347313237221493e-05, "epoch": 0.5072083879423329, "percentage": 5.07, "elapsed_time": "0:03:16", "remaining_time": "1:01:19", "throughput": 2622.16, "total_tokens": 515536} {"current_steps": 1940, "total_steps": 38150, "loss": 0.6212, "lr": 2.5412844036697247e-05, "epoch": 0.508519003931848, "percentage": 5.09, "elapsed_time": "0:03:17", "remaining_time": "1:01:17", "throughput": 2622.27, "total_tokens": 516720} {"current_steps": 1945, "total_steps": 38150, "loss": 0.4091, "lr": 2.5478374836173e-05, "epoch": 0.509829619921363, "percentage": 5.1, "elapsed_time": "0:03:17", "remaining_time": "1:01:15", "throughput": 2622.08, "total_tokens": 517808} {"current_steps": 1950, "total_steps": 38150, "loss": 0.4856, "lr": 2.554390563564876e-05, "epoch": 0.5111402359108781, "percentage": 5.11, "elapsed_time": "0:03:17", "remaining_time": "1:01:14", "throughput": 2623.31, "total_tokens": 519312} {"current_steps": 1955, "total_steps": 38150, "loss": 0.4891, "lr": 2.5609436435124512e-05, "epoch": 0.5124508519003932, "percentage": 5.12, "elapsed_time": "0:03:18", "remaining_time": "1:01:13", "throughput": 2623.63, "total_tokens": 520528} {"current_steps": 1960, "total_steps": 38150, "loss": 0.4792, "lr": 2.5674967234600263e-05, "epoch": 0.5137614678899083, "percentage": 5.14, "elapsed_time": "0:03:18", "remaining_time": "1:01:11", "throughput": 2624.0, "total_tokens": 521744} {"current_steps": 1965, "total_steps": 38150, "loss": 0.4871, "lr": 2.5740498034076017e-05, "epoch": 0.5150720838794234, "percentage": 5.15, "elapsed_time": "0:03:19", "remaining_time": "1:01:09", "throughput": 2624.15, "total_tokens": 522976} {"current_steps": 1970, "total_steps": 38150, "loss": 0.4985, "lr": 2.580602883355177e-05, "epoch": 0.5163826998689384, "percentage": 5.16, "elapsed_time": "0:03:19", "remaining_time": "1:01:09", "throughput": 2625.54, "total_tokens": 524560} {"current_steps": 1975, "total_steps": 38150, "loss": 0.3378, "lr": 2.5871559633027525e-05, "epoch": 0.5176933158584535, "percentage": 5.18, "elapsed_time": "0:03:20", "remaining_time": "1:01:07", "throughput": 2626.67, "total_tokens": 525968} {"current_steps": 1980, "total_steps": 38150, "loss": 0.5797, "lr": 2.5937090432503282e-05, "epoch": 0.5190039318479686, "percentage": 5.19, "elapsed_time": "0:03:20", "remaining_time": "1:01:07", "throughput": 2628.64, "total_tokens": 527808} {"current_steps": 1985, "total_steps": 38150, "loss": 0.4691, "lr": 2.600262123197903e-05, "epoch": 0.5203145478374837, "percentage": 5.2, "elapsed_time": "0:03:21", "remaining_time": "1:01:07", "throughput": 2630.36, "total_tokens": 529472} {"current_steps": 1990, "total_steps": 38150, "loss": 0.5555, "lr": 2.6068152031454783e-05, "epoch": 0.5216251638269986, "percentage": 5.22, "elapsed_time": "0:03:21", "remaining_time": "1:01:06", "throughput": 2631.18, "total_tokens": 530864} {"current_steps": 1995, "total_steps": 38150, "loss": 0.5429, "lr": 2.613368283093054e-05, "epoch": 0.5229357798165137, "percentage": 5.23, "elapsed_time": "0:03:22", "remaining_time": "1:01:05", "throughput": 2632.53, "total_tokens": 532448} {"current_steps": 2000, "total_steps": 38150, "loss": 0.5112, "lr": 2.6199213630406294e-05, "epoch": 0.5242463958060288, "percentage": 5.24, "elapsed_time": "0:03:22", "remaining_time": "1:01:04", "throughput": 2633.94, "total_tokens": 534064} {"current_steps": 2005, "total_steps": 38150, "loss": 0.6287, "lr": 2.6264744429882045e-05, "epoch": 0.5255570117955439, "percentage": 5.26, "elapsed_time": "0:03:23", "remaining_time": "1:01:03", "throughput": 2634.43, "total_tokens": 535328} {"current_steps": 2010, "total_steps": 38150, "loss": 0.7761, "lr": 2.63302752293578e-05, "epoch": 0.526867627785059, "percentage": 5.27, "elapsed_time": "0:03:23", "remaining_time": "1:01:01", "throughput": 2634.64, "total_tokens": 536576} {"current_steps": 2015, "total_steps": 38150, "loss": 0.3863, "lr": 2.6395806028833552e-05, "epoch": 0.528178243774574, "percentage": 5.28, "elapsed_time": "0:03:24", "remaining_time": "1:00:59", "throughput": 2635.09, "total_tokens": 537792} {"current_steps": 2020, "total_steps": 38150, "loss": 0.4048, "lr": 2.6461336828309306e-05, "epoch": 0.5294888597640891, "percentage": 5.29, "elapsed_time": "0:03:24", "remaining_time": "1:00:58", "throughput": 2635.97, "total_tokens": 539120} {"current_steps": 2025, "total_steps": 38150, "loss": 0.5222, "lr": 2.6526867627785064e-05, "epoch": 0.5307994757536042, "percentage": 5.31, "elapsed_time": "0:03:24", "remaining_time": "1:00:56", "throughput": 2636.11, "total_tokens": 540320} {"current_steps": 2030, "total_steps": 38150, "loss": 0.5513, "lr": 2.659239842726081e-05, "epoch": 0.5321100917431193, "percentage": 5.32, "elapsed_time": "0:03:25", "remaining_time": "1:00:55", "throughput": 2636.7, "total_tokens": 541760} {"current_steps": 2035, "total_steps": 38150, "loss": 0.6737, "lr": 2.6657929226736568e-05, "epoch": 0.5334207077326344, "percentage": 5.33, "elapsed_time": "0:03:25", "remaining_time": "1:00:53", "throughput": 2636.27, "total_tokens": 542784} {"current_steps": 2040, "total_steps": 38150, "loss": 0.6018, "lr": 2.6723460026212322e-05, "epoch": 0.5347313237221494, "percentage": 5.35, "elapsed_time": "0:03:26", "remaining_time": "1:00:51", "throughput": 2636.59, "total_tokens": 543968} {"current_steps": 2045, "total_steps": 38150, "loss": 0.4169, "lr": 2.6788990825688076e-05, "epoch": 0.5360419397116645, "percentage": 5.36, "elapsed_time": "0:03:26", "remaining_time": "1:00:50", "throughput": 2637.13, "total_tokens": 545248} {"current_steps": 2050, "total_steps": 38150, "loss": 0.7056, "lr": 2.685452162516383e-05, "epoch": 0.5373525557011796, "percentage": 5.37, "elapsed_time": "0:03:27", "remaining_time": "1:00:48", "throughput": 2637.22, "total_tokens": 546400} {"current_steps": 2055, "total_steps": 38150, "loss": 0.4569, "lr": 2.692005242463958e-05, "epoch": 0.5386631716906947, "percentage": 5.39, "elapsed_time": "0:03:27", "remaining_time": "1:00:47", "throughput": 2638.53, "total_tokens": 547856} {"current_steps": 2060, "total_steps": 38150, "loss": 0.3972, "lr": 2.6985583224115334e-05, "epoch": 0.5399737876802096, "percentage": 5.4, "elapsed_time": "0:03:28", "remaining_time": "1:00:45", "throughput": 2639.31, "total_tokens": 549152} {"current_steps": 2065, "total_steps": 38150, "loss": 0.4606, "lr": 2.7051114023591088e-05, "epoch": 0.5412844036697247, "percentage": 5.41, "elapsed_time": "0:03:28", "remaining_time": "1:00:44", "throughput": 2640.56, "total_tokens": 550656} {"current_steps": 2070, "total_steps": 38150, "loss": 0.4585, "lr": 2.7116644823066845e-05, "epoch": 0.5425950196592398, "percentage": 5.43, "elapsed_time": "0:03:28", "remaining_time": "1:00:42", "throughput": 2640.1, "total_tokens": 551680} {"current_steps": 2075, "total_steps": 38150, "loss": 0.4549, "lr": 2.7182175622542593e-05, "epoch": 0.5439056356487549, "percentage": 5.44, "elapsed_time": "0:03:29", "remaining_time": "1:00:41", "throughput": 2640.88, "total_tokens": 553088} {"current_steps": 2080, "total_steps": 38150, "loss": 0.4723, "lr": 2.724770642201835e-05, "epoch": 0.54521625163827, "percentage": 5.45, "elapsed_time": "0:03:29", "remaining_time": "1:00:39", "throughput": 2641.23, "total_tokens": 554304} {"current_steps": 2085, "total_steps": 38150, "loss": 0.6532, "lr": 2.7313237221494104e-05, "epoch": 0.546526867627785, "percentage": 5.47, "elapsed_time": "0:03:30", "remaining_time": "1:00:38", "throughput": 2641.38, "total_tokens": 555584} {"current_steps": 2090, "total_steps": 38150, "loss": 0.4908, "lr": 2.7378768020969858e-05, "epoch": 0.5478374836173001, "percentage": 5.48, "elapsed_time": "0:03:30", "remaining_time": "1:00:36", "throughput": 2641.55, "total_tokens": 556768} {"current_steps": 2095, "total_steps": 38150, "loss": 0.4112, "lr": 2.744429882044561e-05, "epoch": 0.5491480996068152, "percentage": 5.49, "elapsed_time": "0:03:31", "remaining_time": "1:00:35", "throughput": 2642.42, "total_tokens": 558208} {"current_steps": 2100, "total_steps": 38150, "loss": 0.5277, "lr": 2.7509829619921362e-05, "epoch": 0.5504587155963303, "percentage": 5.5, "elapsed_time": "0:03:31", "remaining_time": "1:00:34", "throughput": 2643.71, "total_tokens": 559664} {"current_steps": 2105, "total_steps": 38150, "loss": 0.5098, "lr": 2.7575360419397116e-05, "epoch": 0.5517693315858454, "percentage": 5.52, "elapsed_time": "0:03:32", "remaining_time": "1:00:32", "throughput": 2643.64, "total_tokens": 560800} {"current_steps": 2110, "total_steps": 38150, "loss": 0.521, "lr": 2.7640891218872873e-05, "epoch": 0.5530799475753604, "percentage": 5.53, "elapsed_time": "0:03:32", "remaining_time": "1:00:32", "throughput": 2645.75, "total_tokens": 562640} {"current_steps": 2115, "total_steps": 38150, "loss": 0.5802, "lr": 2.7706422018348627e-05, "epoch": 0.5543905635648755, "percentage": 5.54, "elapsed_time": "0:03:33", "remaining_time": "1:00:30", "throughput": 2645.73, "total_tokens": 563760} {"current_steps": 2120, "total_steps": 38150, "loss": 0.4479, "lr": 2.777195281782438e-05, "epoch": 0.5557011795543906, "percentage": 5.56, "elapsed_time": "0:03:33", "remaining_time": "1:00:29", "throughput": 2646.85, "total_tokens": 565280} {"current_steps": 2125, "total_steps": 38150, "loss": 0.4951, "lr": 2.7837483617300132e-05, "epoch": 0.5570117955439057, "percentage": 5.57, "elapsed_time": "0:03:34", "remaining_time": "1:00:28", "throughput": 2647.25, "total_tokens": 566560} {"current_steps": 2130, "total_steps": 38150, "loss": 0.3798, "lr": 2.7903014416775886e-05, "epoch": 0.5583224115334207, "percentage": 5.58, "elapsed_time": "0:03:34", "remaining_time": "1:00:26", "throughput": 2647.53, "total_tokens": 567776} {"current_steps": 2135, "total_steps": 38150, "loss": 0.6738, "lr": 2.796854521625164e-05, "epoch": 0.5596330275229358, "percentage": 5.6, "elapsed_time": "0:03:34", "remaining_time": "1:00:24", "throughput": 2647.7, "total_tokens": 568960} {"current_steps": 2140, "total_steps": 38150, "loss": 0.5387, "lr": 2.8034076015727394e-05, "epoch": 0.5609436435124509, "percentage": 5.61, "elapsed_time": "0:03:35", "remaining_time": "1:00:24", "throughput": 2648.38, "total_tokens": 570432} {"current_steps": 2145, "total_steps": 38150, "loss": 0.5822, "lr": 2.8099606815203144e-05, "epoch": 0.562254259501966, "percentage": 5.62, "elapsed_time": "0:03:35", "remaining_time": "1:00:22", "throughput": 2647.71, "total_tokens": 571408} {"current_steps": 2150, "total_steps": 38150, "loss": 0.508, "lr": 2.8165137614678898e-05, "epoch": 0.563564875491481, "percentage": 5.64, "elapsed_time": "0:03:36", "remaining_time": "1:00:20", "throughput": 2647.87, "total_tokens": 572592} {"current_steps": 2155, "total_steps": 38150, "loss": 0.5673, "lr": 2.8230668414154655e-05, "epoch": 0.564875491480996, "percentage": 5.65, "elapsed_time": "0:03:36", "remaining_time": "1:00:19", "throughput": 2648.62, "total_tokens": 573968} {"current_steps": 2160, "total_steps": 38150, "loss": 0.5048, "lr": 2.829619921363041e-05, "epoch": 0.5661861074705111, "percentage": 5.66, "elapsed_time": "0:03:37", "remaining_time": "1:00:17", "throughput": 2648.68, "total_tokens": 575088} {"current_steps": 2165, "total_steps": 38150, "loss": 0.5669, "lr": 2.8361730013106163e-05, "epoch": 0.5674967234600262, "percentage": 5.67, "elapsed_time": "0:03:37", "remaining_time": "1:00:16", "throughput": 2648.93, "total_tokens": 576368} {"current_steps": 2170, "total_steps": 38150, "loss": 0.6036, "lr": 2.8427260812581914e-05, "epoch": 0.5688073394495413, "percentage": 5.69, "elapsed_time": "0:03:38", "remaining_time": "1:00:14", "throughput": 2649.12, "total_tokens": 577520} {"current_steps": 2175, "total_steps": 38150, "loss": 0.7618, "lr": 2.8492791612057668e-05, "epoch": 0.5701179554390564, "percentage": 5.7, "elapsed_time": "0:03:38", "remaining_time": "1:00:13", "throughput": 2650.71, "total_tokens": 579152} {"current_steps": 2180, "total_steps": 38150, "loss": 0.3917, "lr": 2.855832241153342e-05, "epoch": 0.5714285714285714, "percentage": 5.71, "elapsed_time": "0:03:38", "remaining_time": "1:00:12", "throughput": 2652.14, "total_tokens": 580720} {"current_steps": 2185, "total_steps": 38150, "loss": 0.4119, "lr": 2.862385321100918e-05, "epoch": 0.5727391874180865, "percentage": 5.73, "elapsed_time": "0:03:39", "remaining_time": "1:00:11", "throughput": 2653.17, "total_tokens": 582128} {"current_steps": 2190, "total_steps": 38150, "loss": 0.4981, "lr": 2.8689384010484926e-05, "epoch": 0.5740498034076016, "percentage": 5.74, "elapsed_time": "0:03:39", "remaining_time": "1:00:11", "throughput": 2654.99, "total_tokens": 584000} {"current_steps": 2195, "total_steps": 38150, "loss": 0.7631, "lr": 2.875491480996068e-05, "epoch": 0.5753604193971167, "percentage": 5.75, "elapsed_time": "0:03:40", "remaining_time": "1:00:10", "throughput": 2654.78, "total_tokens": 585104} {"current_steps": 2200, "total_steps": 38150, "loss": 0.4555, "lr": 2.8820445609436437e-05, "epoch": 0.5766710353866317, "percentage": 5.77, "elapsed_time": "0:03:40", "remaining_time": "1:00:08", "throughput": 2655.54, "total_tokens": 586432} {"current_steps": 2205, "total_steps": 38150, "loss": 0.7242, "lr": 2.888597640891219e-05, "epoch": 0.5779816513761468, "percentage": 5.78, "elapsed_time": "0:03:41", "remaining_time": "1:00:07", "throughput": 2655.69, "total_tokens": 587648} {"current_steps": 2210, "total_steps": 38150, "loss": 0.5581, "lr": 2.8951507208387945e-05, "epoch": 0.5792922673656619, "percentage": 5.79, "elapsed_time": "0:03:41", "remaining_time": "1:00:05", "throughput": 2655.29, "total_tokens": 588672} {"current_steps": 2215, "total_steps": 38150, "loss": 0.4202, "lr": 2.9017038007863695e-05, "epoch": 0.580602883355177, "percentage": 5.81, "elapsed_time": "0:03:42", "remaining_time": "1:00:04", "throughput": 2656.51, "total_tokens": 590192} {"current_steps": 2220, "total_steps": 38150, "loss": 0.5273, "lr": 2.908256880733945e-05, "epoch": 0.581913499344692, "percentage": 5.82, "elapsed_time": "0:03:42", "remaining_time": "1:00:02", "throughput": 2655.48, "total_tokens": 591072} {"current_steps": 2225, "total_steps": 38150, "loss": 0.3957, "lr": 2.9148099606815203e-05, "epoch": 0.583224115334207, "percentage": 5.83, "elapsed_time": "0:03:43", "remaining_time": "1:00:00", "throughput": 2655.44, "total_tokens": 592192} {"current_steps": 2230, "total_steps": 38150, "loss": 0.5306, "lr": 2.921363040629096e-05, "epoch": 0.5845347313237221, "percentage": 5.85, "elapsed_time": "0:03:43", "remaining_time": "0:59:59", "throughput": 2656.1, "total_tokens": 593520} {"current_steps": 2235, "total_steps": 38150, "loss": 0.4037, "lr": 2.9279161205766714e-05, "epoch": 0.5858453473132372, "percentage": 5.86, "elapsed_time": "0:03:43", "remaining_time": "0:59:57", "throughput": 2655.57, "total_tokens": 594528} {"current_steps": 2240, "total_steps": 38150, "loss": 0.388, "lr": 2.9344692005242465e-05, "epoch": 0.5871559633027523, "percentage": 5.87, "elapsed_time": "0:03:44", "remaining_time": "0:59:56", "throughput": 2656.02, "total_tokens": 595824} {"current_steps": 2245, "total_steps": 38150, "loss": 0.3229, "lr": 2.941022280471822e-05, "epoch": 0.5884665792922673, "percentage": 5.88, "elapsed_time": "0:03:44", "remaining_time": "0:59:55", "throughput": 2656.38, "total_tokens": 597136} {"current_steps": 2250, "total_steps": 38150, "loss": 0.591, "lr": 2.9475753604193973e-05, "epoch": 0.5897771952817824, "percentage": 5.9, "elapsed_time": "0:03:45", "remaining_time": "0:59:53", "throughput": 2656.5, "total_tokens": 598320} {"current_steps": 2255, "total_steps": 38150, "loss": 0.4191, "lr": 2.9541284403669727e-05, "epoch": 0.5910878112712975, "percentage": 5.91, "elapsed_time": "0:03:45", "remaining_time": "0:59:52", "throughput": 2657.47, "total_tokens": 599792} {"current_steps": 2260, "total_steps": 38150, "loss": 0.3517, "lr": 2.9606815203145477e-05, "epoch": 0.5923984272608126, "percentage": 5.92, "elapsed_time": "0:03:46", "remaining_time": "0:59:51", "throughput": 2657.72, "total_tokens": 601120} {"current_steps": 2265, "total_steps": 38150, "loss": 0.4616, "lr": 2.967234600262123e-05, "epoch": 0.5937090432503277, "percentage": 5.94, "elapsed_time": "0:03:46", "remaining_time": "0:59:50", "throughput": 2657.89, "total_tokens": 602368} {"current_steps": 2270, "total_steps": 38150, "loss": 0.358, "lr": 2.9737876802096985e-05, "epoch": 0.5950196592398427, "percentage": 5.95, "elapsed_time": "0:03:47", "remaining_time": "0:59:49", "throughput": 2658.8, "total_tokens": 603824} {"current_steps": 2275, "total_steps": 38150, "loss": 0.5391, "lr": 2.9803407601572742e-05, "epoch": 0.5963302752293578, "percentage": 5.96, "elapsed_time": "0:03:47", "remaining_time": "0:59:48", "throughput": 2660.29, "total_tokens": 605376} {"current_steps": 2280, "total_steps": 38150, "loss": 0.5157, "lr": 2.9868938401048496e-05, "epoch": 0.5976408912188729, "percentage": 5.98, "elapsed_time": "0:03:48", "remaining_time": "0:59:47", "throughput": 2660.69, "total_tokens": 606672} {"current_steps": 2285, "total_steps": 38150, "loss": 0.3326, "lr": 2.9934469200524247e-05, "epoch": 0.598951507208388, "percentage": 5.99, "elapsed_time": "0:03:48", "remaining_time": "0:59:46", "throughput": 2661.55, "total_tokens": 608096} {"current_steps": 2290, "total_steps": 38150, "loss": 0.3878, "lr": 3e-05, "epoch": 0.6002621231979031, "percentage": 6.0, "elapsed_time": "0:03:48", "remaining_time": "0:59:44", "throughput": 2662.2, "total_tokens": 609408} {"current_steps": 2295, "total_steps": 38150, "loss": 0.4968, "lr": 3.0065530799475755e-05, "epoch": 0.601572739187418, "percentage": 6.02, "elapsed_time": "0:03:49", "remaining_time": "0:59:43", "throughput": 2662.81, "total_tokens": 610720} {"current_steps": 2300, "total_steps": 38150, "loss": 0.6538, "lr": 3.013106159895151e-05, "epoch": 0.6028833551769331, "percentage": 6.03, "elapsed_time": "0:03:49", "remaining_time": "0:59:41", "throughput": 2662.88, "total_tokens": 611888} {"current_steps": 2305, "total_steps": 38150, "loss": 0.6401, "lr": 3.0196592398427266e-05, "epoch": 0.6041939711664482, "percentage": 6.04, "elapsed_time": "0:03:50", "remaining_time": "0:59:40", "throughput": 2662.74, "total_tokens": 613008} {"current_steps": 2310, "total_steps": 38150, "loss": 0.4298, "lr": 3.0262123197903013e-05, "epoch": 0.6055045871559633, "percentage": 6.06, "elapsed_time": "0:03:50", "remaining_time": "0:59:38", "throughput": 2662.66, "total_tokens": 614096} {"current_steps": 2315, "total_steps": 38150, "loss": 0.5405, "lr": 3.032765399737877e-05, "epoch": 0.6068152031454783, "percentage": 6.07, "elapsed_time": "0:03:51", "remaining_time": "0:59:36", "throughput": 2662.06, "total_tokens": 615088} {"current_steps": 2320, "total_steps": 38150, "loss": 0.5642, "lr": 3.0393184796854524e-05, "epoch": 0.6081258191349934, "percentage": 6.08, "elapsed_time": "0:03:51", "remaining_time": "0:59:35", "throughput": 2662.5, "total_tokens": 616400} {"current_steps": 2325, "total_steps": 38150, "loss": 0.6367, "lr": 3.0458715596330278e-05, "epoch": 0.6094364351245085, "percentage": 6.09, "elapsed_time": "0:03:51", "remaining_time": "0:59:34", "throughput": 2664.02, "total_tokens": 618032} {"current_steps": 2330, "total_steps": 38150, "loss": 0.6793, "lr": 3.052424639580603e-05, "epoch": 0.6107470511140236, "percentage": 6.11, "elapsed_time": "0:03:52", "remaining_time": "0:59:33", "throughput": 2664.44, "total_tokens": 619296} {"current_steps": 2335, "total_steps": 38150, "loss": 0.4537, "lr": 3.058977719528178e-05, "epoch": 0.6120576671035387, "percentage": 6.12, "elapsed_time": "0:03:52", "remaining_time": "0:59:32", "throughput": 2665.44, "total_tokens": 620736} {"current_steps": 2340, "total_steps": 38150, "loss": 0.7121, "lr": 3.0655307994757537e-05, "epoch": 0.6133682830930537, "percentage": 6.13, "elapsed_time": "0:03:53", "remaining_time": "0:59:30", "throughput": 2665.43, "total_tokens": 621888} {"current_steps": 2345, "total_steps": 38150, "loss": 0.4692, "lr": 3.0720838794233294e-05, "epoch": 0.6146788990825688, "percentage": 6.15, "elapsed_time": "0:03:53", "remaining_time": "0:59:28", "throughput": 2665.33, "total_tokens": 622992} {"current_steps": 2350, "total_steps": 38150, "loss": 0.6501, "lr": 3.0786369593709044e-05, "epoch": 0.6159895150720839, "percentage": 6.16, "elapsed_time": "0:03:54", "remaining_time": "0:59:27", "throughput": 2665.64, "total_tokens": 624304} {"current_steps": 2355, "total_steps": 38150, "loss": 0.5157, "lr": 3.0851900393184795e-05, "epoch": 0.617300131061599, "percentage": 6.17, "elapsed_time": "0:03:54", "remaining_time": "0:59:27", "throughput": 2666.21, "total_tokens": 625744} {"current_steps": 2360, "total_steps": 38150, "loss": 0.5637, "lr": 3.091743119266055e-05, "epoch": 0.6186107470511141, "percentage": 6.19, "elapsed_time": "0:03:55", "remaining_time": "0:59:26", "throughput": 2666.76, "total_tokens": 627120} {"current_steps": 2365, "total_steps": 38150, "loss": 0.6202, "lr": 3.09829619921363e-05, "epoch": 0.6199213630406291, "percentage": 6.2, "elapsed_time": "0:03:55", "remaining_time": "0:59:24", "throughput": 2666.33, "total_tokens": 628144} {"current_steps": 2370, "total_steps": 38150, "loss": 0.3705, "lr": 3.104849279161206e-05, "epoch": 0.6212319790301442, "percentage": 6.21, "elapsed_time": "0:03:56", "remaining_time": "0:59:23", "throughput": 2666.59, "total_tokens": 629344} {"current_steps": 2375, "total_steps": 38150, "loss": 0.7921, "lr": 3.111402359108782e-05, "epoch": 0.6225425950196593, "percentage": 6.23, "elapsed_time": "0:03:56", "remaining_time": "0:59:22", "throughput": 2667.63, "total_tokens": 630928} {"current_steps": 2380, "total_steps": 38150, "loss": 0.5241, "lr": 3.117955439056357e-05, "epoch": 0.6238532110091743, "percentage": 6.24, "elapsed_time": "0:03:56", "remaining_time": "0:59:21", "throughput": 2668.09, "total_tokens": 632272} {"current_steps": 2385, "total_steps": 38150, "loss": 0.5289, "lr": 3.124508519003932e-05, "epoch": 0.6251638269986893, "percentage": 6.25, "elapsed_time": "0:03:57", "remaining_time": "0:59:20", "throughput": 2668.16, "total_tokens": 633440} {"current_steps": 2390, "total_steps": 38150, "loss": 0.4768, "lr": 3.1310615989515076e-05, "epoch": 0.6264744429882044, "percentage": 6.26, "elapsed_time": "0:03:57", "remaining_time": "0:59:18", "throughput": 2668.34, "total_tokens": 634624} {"current_steps": 2395, "total_steps": 38150, "loss": 0.8147, "lr": 3.1376146788990826e-05, "epoch": 0.6277850589777195, "percentage": 6.28, "elapsed_time": "0:03:58", "remaining_time": "0:59:16", "throughput": 2668.02, "total_tokens": 635664} {"current_steps": 2400, "total_steps": 38150, "loss": 0.4665, "lr": 3.144167758846658e-05, "epoch": 0.6290956749672346, "percentage": 6.29, "elapsed_time": "0:03:58", "remaining_time": "0:59:15", "throughput": 2668.86, "total_tokens": 637104} {"current_steps": 2405, "total_steps": 38150, "loss": 0.3475, "lr": 3.1507208387942334e-05, "epoch": 0.6304062909567497, "percentage": 6.3, "elapsed_time": "0:03:59", "remaining_time": "0:59:14", "throughput": 2669.62, "total_tokens": 638448} {"current_steps": 2410, "total_steps": 38150, "loss": 0.3581, "lr": 3.1572739187418085e-05, "epoch": 0.6317169069462647, "percentage": 6.32, "elapsed_time": "0:03:59", "remaining_time": "0:59:18", "throughput": 2673.62, "total_tokens": 641536} {"current_steps": 2415, "total_steps": 38150, "loss": 0.4593, "lr": 3.163826998689384e-05, "epoch": 0.6330275229357798, "percentage": 6.33, "elapsed_time": "0:04:00", "remaining_time": "0:59:17", "throughput": 2674.21, "total_tokens": 642960} {"current_steps": 2420, "total_steps": 38150, "loss": 0.5151, "lr": 3.17038007863696e-05, "epoch": 0.6343381389252949, "percentage": 6.34, "elapsed_time": "0:04:00", "remaining_time": "0:59:15", "throughput": 2673.7, "total_tokens": 643952} {"current_steps": 2425, "total_steps": 38150, "loss": 0.5031, "lr": 3.176933158584535e-05, "epoch": 0.63564875491481, "percentage": 6.36, "elapsed_time": "0:04:01", "remaining_time": "0:59:14", "throughput": 2674.04, "total_tokens": 645184} {"current_steps": 2430, "total_steps": 38150, "loss": 0.6049, "lr": 3.18348623853211e-05, "epoch": 0.6369593709043251, "percentage": 6.37, "elapsed_time": "0:04:01", "remaining_time": "0:59:13", "throughput": 2675.59, "total_tokens": 646880} {"current_steps": 2435, "total_steps": 38150, "loss": 0.4255, "lr": 3.190039318479686e-05, "epoch": 0.6382699868938401, "percentage": 6.38, "elapsed_time": "0:04:02", "remaining_time": "0:59:12", "throughput": 2675.5, "total_tokens": 648064} {"current_steps": 2440, "total_steps": 38150, "loss": 0.72, "lr": 3.196592398427261e-05, "epoch": 0.6395806028833552, "percentage": 6.4, "elapsed_time": "0:04:02", "remaining_time": "0:59:11", "throughput": 2676.4, "total_tokens": 649552} {"current_steps": 2445, "total_steps": 38150, "loss": 0.5957, "lr": 3.2031454783748365e-05, "epoch": 0.6408912188728703, "percentage": 6.41, "elapsed_time": "0:04:03", "remaining_time": "0:59:10", "throughput": 2676.83, "total_tokens": 650848} {"current_steps": 2450, "total_steps": 38150, "loss": 0.7229, "lr": 3.2096985583224116e-05, "epoch": 0.6422018348623854, "percentage": 6.42, "elapsed_time": "0:04:03", "remaining_time": "0:59:09", "throughput": 2677.59, "total_tokens": 652240} {"current_steps": 2455, "total_steps": 38150, "loss": 0.4842, "lr": 3.216251638269987e-05, "epoch": 0.6435124508519003, "percentage": 6.44, "elapsed_time": "0:04:04", "remaining_time": "0:59:08", "throughput": 2678.37, "total_tokens": 653616} {"current_steps": 2460, "total_steps": 38150, "loss": 0.7283, "lr": 3.2228047182175624e-05, "epoch": 0.6448230668414154, "percentage": 6.45, "elapsed_time": "0:04:04", "remaining_time": "0:59:06", "throughput": 2678.71, "total_tokens": 654864} {"current_steps": 2465, "total_steps": 38150, "loss": 0.3973, "lr": 3.229357798165138e-05, "epoch": 0.6461336828309305, "percentage": 6.46, "elapsed_time": "0:04:04", "remaining_time": "0:59:05", "throughput": 2679.45, "total_tokens": 656288} {"current_steps": 2470, "total_steps": 38150, "loss": 0.7185, "lr": 3.235910878112713e-05, "epoch": 0.6474442988204456, "percentage": 6.47, "elapsed_time": "0:04:05", "remaining_time": "0:59:04", "throughput": 2679.25, "total_tokens": 657360} {"current_steps": 2475, "total_steps": 38150, "loss": 0.6217, "lr": 3.242463958060288e-05, "epoch": 0.6487549148099607, "percentage": 6.49, "elapsed_time": "0:04:05", "remaining_time": "0:59:03", "throughput": 2679.62, "total_tokens": 658704} {"current_steps": 2480, "total_steps": 38150, "loss": 0.5055, "lr": 3.249017038007864e-05, "epoch": 0.6500655307994757, "percentage": 6.5, "elapsed_time": "0:04:06", "remaining_time": "0:59:01", "throughput": 2679.43, "total_tokens": 659792} {"current_steps": 2485, "total_steps": 38150, "loss": 0.4254, "lr": 3.255570117955439e-05, "epoch": 0.6513761467889908, "percentage": 6.51, "elapsed_time": "0:04:06", "remaining_time": "0:59:00", "throughput": 2680.17, "total_tokens": 661152} {"current_steps": 2490, "total_steps": 38150, "loss": 0.3319, "lr": 3.262123197903015e-05, "epoch": 0.6526867627785059, "percentage": 6.53, "elapsed_time": "0:04:07", "remaining_time": "0:58:58", "throughput": 2680.24, "total_tokens": 662288} {"current_steps": 2495, "total_steps": 38150, "loss": 0.5574, "lr": 3.26867627785059e-05, "epoch": 0.653997378768021, "percentage": 6.54, "elapsed_time": "0:04:07", "remaining_time": "0:58:57", "throughput": 2680.71, "total_tokens": 663568} {"current_steps": 2500, "total_steps": 38150, "loss": 0.5624, "lr": 3.2752293577981655e-05, "epoch": 0.6553079947575361, "percentage": 6.55, "elapsed_time": "0:04:08", "remaining_time": "0:58:56", "throughput": 2681.19, "total_tokens": 664960} {"current_steps": 2505, "total_steps": 38150, "loss": 0.4615, "lr": 3.2817824377457405e-05, "epoch": 0.6566186107470511, "percentage": 6.57, "elapsed_time": "0:04:08", "remaining_time": "0:58:55", "throughput": 2681.96, "total_tokens": 666416} {"current_steps": 2510, "total_steps": 38150, "loss": 0.6696, "lr": 3.288335517693316e-05, "epoch": 0.6579292267365662, "percentage": 6.58, "elapsed_time": "0:04:08", "remaining_time": "0:58:54", "throughput": 2681.6, "total_tokens": 667488} {"current_steps": 2515, "total_steps": 38150, "loss": 0.2681, "lr": 3.294888597640891e-05, "epoch": 0.6592398427260813, "percentage": 6.59, "elapsed_time": "0:04:09", "remaining_time": "0:58:53", "throughput": 2682.8, "total_tokens": 669072} {"current_steps": 2520, "total_steps": 38150, "loss": 0.6086, "lr": 3.3014416775884664e-05, "epoch": 0.6605504587155964, "percentage": 6.61, "elapsed_time": "0:04:09", "remaining_time": "0:58:52", "throughput": 2682.91, "total_tokens": 670256} {"current_steps": 2525, "total_steps": 38150, "loss": 0.4122, "lr": 3.307994757536042e-05, "epoch": 0.6618610747051114, "percentage": 6.62, "elapsed_time": "0:04:10", "remaining_time": "0:58:51", "throughput": 2683.08, "total_tokens": 671520} {"current_steps": 2530, "total_steps": 38150, "loss": 0.605, "lr": 3.314547837483618e-05, "epoch": 0.6631716906946264, "percentage": 6.63, "elapsed_time": "0:04:10", "remaining_time": "0:58:50", "throughput": 2684.11, "total_tokens": 673056} {"current_steps": 2535, "total_steps": 38150, "loss": 0.4572, "lr": 3.321100917431193e-05, "epoch": 0.6644823066841415, "percentage": 6.64, "elapsed_time": "0:04:11", "remaining_time": "0:58:48", "throughput": 2683.79, "total_tokens": 674096} {"current_steps": 2540, "total_steps": 38150, "loss": 0.3817, "lr": 3.327653997378768e-05, "epoch": 0.6657929226736566, "percentage": 6.66, "elapsed_time": "0:04:11", "remaining_time": "0:58:47", "throughput": 2683.55, "total_tokens": 675264} {"current_steps": 2545, "total_steps": 38150, "loss": 0.4447, "lr": 3.334207077326344e-05, "epoch": 0.6671035386631717, "percentage": 6.67, "elapsed_time": "0:04:12", "remaining_time": "0:58:47", "throughput": 2684.26, "total_tokens": 676784} {"current_steps": 2550, "total_steps": 38150, "loss": 0.5841, "lr": 3.340760157273919e-05, "epoch": 0.6684141546526867, "percentage": 6.68, "elapsed_time": "0:04:12", "remaining_time": "0:58:46", "throughput": 2684.47, "total_tokens": 678064} {"current_steps": 2555, "total_steps": 38150, "loss": 0.5001, "lr": 3.3473132372214945e-05, "epoch": 0.6697247706422018, "percentage": 6.7, "elapsed_time": "0:04:13", "remaining_time": "0:58:45", "throughput": 2685.91, "total_tokens": 679728} {"current_steps": 2560, "total_steps": 38150, "loss": 0.4693, "lr": 3.3538663171690695e-05, "epoch": 0.6710353866317169, "percentage": 6.71, "elapsed_time": "0:04:13", "remaining_time": "0:58:44", "throughput": 2686.19, "total_tokens": 680976} {"current_steps": 2565, "total_steps": 38150, "loss": 0.421, "lr": 3.3604193971166446e-05, "epoch": 0.672346002621232, "percentage": 6.72, "elapsed_time": "0:04:14", "remaining_time": "0:58:43", "throughput": 2686.98, "total_tokens": 682512} {"current_steps": 2570, "total_steps": 38150, "loss": 0.5373, "lr": 3.36697247706422e-05, "epoch": 0.6736566186107471, "percentage": 6.74, "elapsed_time": "0:04:14", "remaining_time": "0:58:43", "throughput": 2687.97, "total_tokens": 684080} {"current_steps": 2575, "total_steps": 38150, "loss": 0.4022, "lr": 3.373525557011796e-05, "epoch": 0.6749672346002621, "percentage": 6.75, "elapsed_time": "0:04:14", "remaining_time": "0:58:41", "throughput": 2688.0, "total_tokens": 685248} {"current_steps": 2580, "total_steps": 38150, "loss": 0.5071, "lr": 3.380078636959371e-05, "epoch": 0.6762778505897772, "percentage": 6.76, "elapsed_time": "0:04:15", "remaining_time": "0:58:40", "throughput": 2688.29, "total_tokens": 686480} {"current_steps": 2585, "total_steps": 38150, "loss": 0.5378, "lr": 3.386631716906947e-05, "epoch": 0.6775884665792923, "percentage": 6.78, "elapsed_time": "0:04:15", "remaining_time": "0:58:39", "throughput": 2688.51, "total_tokens": 687760} {"current_steps": 2590, "total_steps": 38150, "loss": 0.5509, "lr": 3.393184796854522e-05, "epoch": 0.6788990825688074, "percentage": 6.79, "elapsed_time": "0:04:16", "remaining_time": "0:58:38", "throughput": 2688.46, "total_tokens": 688896} {"current_steps": 2595, "total_steps": 38150, "loss": 0.5407, "lr": 3.399737876802097e-05, "epoch": 0.6802096985583224, "percentage": 6.8, "elapsed_time": "0:04:16", "remaining_time": "0:58:36", "throughput": 2688.14, "total_tokens": 689968} {"current_steps": 2600, "total_steps": 38150, "loss": 0.5807, "lr": 3.4062909567496726e-05, "epoch": 0.6815203145478375, "percentage": 6.82, "elapsed_time": "0:04:17", "remaining_time": "0:58:35", "throughput": 2688.43, "total_tokens": 691232} {"current_steps": 2605, "total_steps": 38150, "loss": 0.801, "lr": 3.4128440366972484e-05, "epoch": 0.6828309305373526, "percentage": 6.83, "elapsed_time": "0:04:17", "remaining_time": "0:58:34", "throughput": 2687.89, "total_tokens": 692304} {"current_steps": 2610, "total_steps": 38150, "loss": 0.4031, "lr": 3.419397116644823e-05, "epoch": 0.6841415465268676, "percentage": 6.84, "elapsed_time": "0:04:18", "remaining_time": "0:58:33", "throughput": 2688.69, "total_tokens": 693744} {"current_steps": 2615, "total_steps": 38150, "loss": 0.6148, "lr": 3.4259501965923985e-05, "epoch": 0.6854521625163827, "percentage": 6.85, "elapsed_time": "0:04:18", "remaining_time": "0:58:32", "throughput": 2689.36, "total_tokens": 695184} {"current_steps": 2620, "total_steps": 38150, "loss": 0.6659, "lr": 3.432503276539974e-05, "epoch": 0.6867627785058977, "percentage": 6.87, "elapsed_time": "0:04:18", "remaining_time": "0:58:31", "throughput": 2689.61, "total_tokens": 696416} {"current_steps": 2625, "total_steps": 38150, "loss": 0.4785, "lr": 3.439056356487549e-05, "epoch": 0.6880733944954128, "percentage": 6.88, "elapsed_time": "0:04:19", "remaining_time": "0:58:30", "throughput": 2689.94, "total_tokens": 697824} {"current_steps": 2630, "total_steps": 38150, "loss": 0.5656, "lr": 3.445609436435125e-05, "epoch": 0.6893840104849279, "percentage": 6.89, "elapsed_time": "0:04:19", "remaining_time": "0:58:29", "throughput": 2690.87, "total_tokens": 699328} {"current_steps": 2635, "total_steps": 38150, "loss": 0.583, "lr": 3.4521625163827e-05, "epoch": 0.690694626474443, "percentage": 6.91, "elapsed_time": "0:04:20", "remaining_time": "0:58:28", "throughput": 2690.29, "total_tokens": 700320} {"current_steps": 2640, "total_steps": 38150, "loss": 0.5581, "lr": 3.458715596330275e-05, "epoch": 0.6920052424639581, "percentage": 6.92, "elapsed_time": "0:04:20", "remaining_time": "0:58:27", "throughput": 2690.69, "total_tokens": 701712} {"current_steps": 2645, "total_steps": 38150, "loss": 0.5892, "lr": 3.465268676277851e-05, "epoch": 0.6933158584534731, "percentage": 6.93, "elapsed_time": "0:04:21", "remaining_time": "0:58:28", "throughput": 2693.22, "total_tokens": 703952} {"current_steps": 2650, "total_steps": 38150, "loss": 0.4913, "lr": 3.4718217562254266e-05, "epoch": 0.6946264744429882, "percentage": 6.95, "elapsed_time": "0:04:21", "remaining_time": "0:58:27", "throughput": 2693.09, "total_tokens": 705168} {"current_steps": 2655, "total_steps": 38150, "loss": 0.3102, "lr": 3.4783748361730016e-05, "epoch": 0.6959370904325033, "percentage": 6.96, "elapsed_time": "0:04:22", "remaining_time": "0:58:26", "throughput": 2692.86, "total_tokens": 706272} {"current_steps": 2660, "total_steps": 38150, "loss": 0.3813, "lr": 3.484927916120577e-05, "epoch": 0.6972477064220184, "percentage": 6.97, "elapsed_time": "0:04:22", "remaining_time": "0:58:25", "throughput": 2693.36, "total_tokens": 707680} {"current_steps": 2665, "total_steps": 38150, "loss": 0.515, "lr": 3.4914809960681524e-05, "epoch": 0.6985583224115334, "percentage": 6.99, "elapsed_time": "0:04:23", "remaining_time": "0:58:24", "throughput": 2693.75, "total_tokens": 709024} {"current_steps": 2670, "total_steps": 38150, "loss": 0.491, "lr": 3.4980340760157274e-05, "epoch": 0.6998689384010485, "percentage": 7.0, "elapsed_time": "0:04:23", "remaining_time": "0:58:23", "throughput": 2694.88, "total_tokens": 710576} {"current_steps": 2675, "total_steps": 38150, "loss": 0.7212, "lr": 3.504587155963303e-05, "epoch": 0.7011795543905636, "percentage": 7.01, "elapsed_time": "0:04:24", "remaining_time": "0:58:34", "throughput": 2686.83, "total_tokens": 711984} {"current_steps": 2680, "total_steps": 38150, "loss": 0.4074, "lr": 3.511140235910878e-05, "epoch": 0.7024901703800787, "percentage": 7.02, "elapsed_time": "0:04:25", "remaining_time": "0:58:33", "throughput": 2687.22, "total_tokens": 713344} {"current_steps": 2685, "total_steps": 38150, "loss": 0.405, "lr": 3.517693315858453e-05, "epoch": 0.7038007863695938, "percentage": 7.04, "elapsed_time": "0:04:25", "remaining_time": "0:58:32", "throughput": 2687.65, "total_tokens": 714704} {"current_steps": 2690, "total_steps": 38150, "loss": 0.6673, "lr": 3.524246395806029e-05, "epoch": 0.7051114023591087, "percentage": 7.05, "elapsed_time": "0:04:26", "remaining_time": "0:58:31", "throughput": 2688.73, "total_tokens": 716288} {"current_steps": 2695, "total_steps": 38150, "loss": 0.4694, "lr": 3.530799475753605e-05, "epoch": 0.7064220183486238, "percentage": 7.06, "elapsed_time": "0:04:26", "remaining_time": "0:58:30", "throughput": 2688.59, "total_tokens": 717392} {"current_steps": 2700, "total_steps": 38150, "loss": 0.6381, "lr": 3.53735255570118e-05, "epoch": 0.7077326343381389, "percentage": 7.08, "elapsed_time": "0:04:27", "remaining_time": "0:58:29", "throughput": 2689.27, "total_tokens": 718784} {"current_steps": 2705, "total_steps": 38150, "loss": 0.5704, "lr": 3.543905635648755e-05, "epoch": 0.709043250327654, "percentage": 7.09, "elapsed_time": "0:04:27", "remaining_time": "0:58:27", "throughput": 2688.98, "total_tokens": 719824} {"current_steps": 2710, "total_steps": 38150, "loss": 0.4701, "lr": 3.5504587155963306e-05, "epoch": 0.7103538663171691, "percentage": 7.1, "elapsed_time": "0:04:28", "remaining_time": "0:58:26", "throughput": 2690.17, "total_tokens": 721424} {"current_steps": 2715, "total_steps": 38150, "loss": 0.525, "lr": 3.5570117955439056e-05, "epoch": 0.7116644823066841, "percentage": 7.12, "elapsed_time": "0:04:28", "remaining_time": "0:58:26", "throughput": 2690.59, "total_tokens": 722784} {"current_steps": 2720, "total_steps": 38150, "loss": 0.5735, "lr": 3.5635648754914814e-05, "epoch": 0.7129750982961992, "percentage": 7.13, "elapsed_time": "0:04:29", "remaining_time": "0:58:24", "throughput": 2691.27, "total_tokens": 724160} {"current_steps": 2725, "total_steps": 38150, "loss": 0.4989, "lr": 3.570117955439057e-05, "epoch": 0.7142857142857143, "percentage": 7.14, "elapsed_time": "0:04:29", "remaining_time": "0:58:23", "throughput": 2691.45, "total_tokens": 725360} {"current_steps": 2730, "total_steps": 38150, "loss": 0.5118, "lr": 3.5766710353866315e-05, "epoch": 0.7155963302752294, "percentage": 7.16, "elapsed_time": "0:04:29", "remaining_time": "0:58:22", "throughput": 2692.01, "total_tokens": 726704} {"current_steps": 2735, "total_steps": 38150, "loss": 0.5223, "lr": 3.583224115334207e-05, "epoch": 0.7169069462647444, "percentage": 7.17, "elapsed_time": "0:04:30", "remaining_time": "0:58:22", "throughput": 2693.57, "total_tokens": 728528} {"current_steps": 2740, "total_steps": 38150, "loss": 0.4888, "lr": 3.589777195281783e-05, "epoch": 0.7182175622542595, "percentage": 7.18, "elapsed_time": "0:04:30", "remaining_time": "0:58:21", "throughput": 2694.62, "total_tokens": 730096} {"current_steps": 2745, "total_steps": 38150, "loss": 0.5738, "lr": 3.596330275229358e-05, "epoch": 0.7195281782437746, "percentage": 7.2, "elapsed_time": "0:04:31", "remaining_time": "0:58:20", "throughput": 2694.35, "total_tokens": 731168} {"current_steps": 2750, "total_steps": 38150, "loss": 0.4614, "lr": 3.602883355176933e-05, "epoch": 0.7208387942332897, "percentage": 7.21, "elapsed_time": "0:04:31", "remaining_time": "0:58:20", "throughput": 2696.28, "total_tokens": 733136} {"current_steps": 2755, "total_steps": 38150, "loss": 0.6927, "lr": 3.609436435124509e-05, "epoch": 0.7221494102228048, "percentage": 7.22, "elapsed_time": "0:04:32", "remaining_time": "0:58:19", "throughput": 2696.52, "total_tokens": 734448} {"current_steps": 2760, "total_steps": 38150, "loss": 0.3673, "lr": 3.615989515072084e-05, "epoch": 0.7234600262123198, "percentage": 7.23, "elapsed_time": "0:04:32", "remaining_time": "0:58:18", "throughput": 2697.43, "total_tokens": 735952} {"current_steps": 2765, "total_steps": 38150, "loss": 0.7013, "lr": 3.6225425950196595e-05, "epoch": 0.7247706422018348, "percentage": 7.25, "elapsed_time": "0:04:33", "remaining_time": "0:58:17", "throughput": 2698.15, "total_tokens": 737392} {"current_steps": 2770, "total_steps": 38150, "loss": 0.4912, "lr": 3.629095674967235e-05, "epoch": 0.7260812581913499, "percentage": 7.26, "elapsed_time": "0:04:33", "remaining_time": "0:58:16", "throughput": 2698.76, "total_tokens": 738816} {"current_steps": 2775, "total_steps": 38150, "loss": 0.5993, "lr": 3.6356487549148097e-05, "epoch": 0.727391874180865, "percentage": 7.27, "elapsed_time": "0:04:34", "remaining_time": "0:58:15", "throughput": 2699.67, "total_tokens": 740336} {"current_steps": 2780, "total_steps": 38150, "loss": 0.4276, "lr": 3.6422018348623854e-05, "epoch": 0.72870249017038, "percentage": 7.29, "elapsed_time": "0:04:34", "remaining_time": "0:58:14", "throughput": 2699.77, "total_tokens": 741536} {"current_steps": 2785, "total_steps": 38150, "loss": 0.4149, "lr": 3.648754914809961e-05, "epoch": 0.7300131061598951, "percentage": 7.3, "elapsed_time": "0:04:35", "remaining_time": "0:58:14", "throughput": 2701.41, "total_tokens": 743392} {"current_steps": 2790, "total_steps": 38150, "loss": 0.5001, "lr": 3.655307994757536e-05, "epoch": 0.7313237221494102, "percentage": 7.31, "elapsed_time": "0:04:35", "remaining_time": "0:58:13", "throughput": 2701.34, "total_tokens": 744608} {"current_steps": 2795, "total_steps": 38150, "loss": 0.4798, "lr": 3.661861074705111e-05, "epoch": 0.7326343381389253, "percentage": 7.33, "elapsed_time": "0:04:36", "remaining_time": "0:58:12", "throughput": 2701.54, "total_tokens": 745840} {"current_steps": 2800, "total_steps": 38150, "loss": 0.6114, "lr": 3.668414154652687e-05, "epoch": 0.7339449541284404, "percentage": 7.34, "elapsed_time": "0:04:36", "remaining_time": "0:58:10", "throughput": 2701.2, "total_tokens": 746896} {"current_steps": 2805, "total_steps": 38150, "loss": 0.6293, "lr": 3.674967234600262e-05, "epoch": 0.7352555701179554, "percentage": 7.35, "elapsed_time": "0:04:36", "remaining_time": "0:58:09", "throughput": 2701.36, "total_tokens": 748176} {"current_steps": 2810, "total_steps": 38150, "loss": 0.6483, "lr": 3.681520314547838e-05, "epoch": 0.7365661861074705, "percentage": 7.37, "elapsed_time": "0:04:37", "remaining_time": "0:58:08", "throughput": 2701.01, "total_tokens": 749312} {"current_steps": 2815, "total_steps": 38150, "loss": 0.5406, "lr": 3.6880733944954135e-05, "epoch": 0.7378768020969856, "percentage": 7.38, "elapsed_time": "0:04:37", "remaining_time": "0:58:08", "throughput": 2701.94, "total_tokens": 750864} {"current_steps": 2820, "total_steps": 38150, "loss": 0.574, "lr": 3.694626474442988e-05, "epoch": 0.7391874180865007, "percentage": 7.39, "elapsed_time": "0:04:38", "remaining_time": "0:58:06", "throughput": 2701.72, "total_tokens": 751952} {"current_steps": 2825, "total_steps": 38150, "loss": 0.5432, "lr": 3.7011795543905636e-05, "epoch": 0.7404980340760158, "percentage": 7.4, "elapsed_time": "0:04:38", "remaining_time": "0:58:05", "throughput": 2701.11, "total_tokens": 752928} {"current_steps": 2830, "total_steps": 38150, "loss": 0.747, "lr": 3.707732634338139e-05, "epoch": 0.7418086500655308, "percentage": 7.42, "elapsed_time": "0:04:39", "remaining_time": "0:58:04", "throughput": 2701.68, "total_tokens": 754400} {"current_steps": 2835, "total_steps": 38150, "loss": 0.422, "lr": 3.7142857142857143e-05, "epoch": 0.7431192660550459, "percentage": 7.43, "elapsed_time": "0:04:39", "remaining_time": "0:58:03", "throughput": 2702.15, "total_tokens": 755712} {"current_steps": 2840, "total_steps": 38150, "loss": 0.6009, "lr": 3.72083879423329e-05, "epoch": 0.744429882044561, "percentage": 7.44, "elapsed_time": "0:04:40", "remaining_time": "0:58:06", "throughput": 2704.7, "total_tokens": 758464} {"current_steps": 2845, "total_steps": 38150, "loss": 0.5096, "lr": 3.727391874180865e-05, "epoch": 0.745740498034076, "percentage": 7.46, "elapsed_time": "0:04:40", "remaining_time": "0:58:05", "throughput": 2705.53, "total_tokens": 759904} {"current_steps": 2850, "total_steps": 38150, "loss": 0.4095, "lr": 3.73394495412844e-05, "epoch": 0.747051114023591, "percentage": 7.47, "elapsed_time": "0:04:41", "remaining_time": "0:58:04", "throughput": 2706.11, "total_tokens": 761328} {"current_steps": 2855, "total_steps": 38150, "loss": 0.6293, "lr": 3.740498034076016e-05, "epoch": 0.7483617300131061, "percentage": 7.48, "elapsed_time": "0:04:41", "remaining_time": "0:58:03", "throughput": 2706.56, "total_tokens": 762688} {"current_steps": 2860, "total_steps": 38150, "loss": 0.391, "lr": 3.7470511140235916e-05, "epoch": 0.7496723460026212, "percentage": 7.5, "elapsed_time": "0:04:42", "remaining_time": "0:58:02", "throughput": 2706.42, "total_tokens": 763888} {"current_steps": 2865, "total_steps": 38150, "loss": 0.4864, "lr": 3.753604193971167e-05, "epoch": 0.7509829619921363, "percentage": 7.51, "elapsed_time": "0:04:42", "remaining_time": "0:58:01", "throughput": 2706.89, "total_tokens": 765296} {"current_steps": 2870, "total_steps": 38150, "loss": 0.5354, "lr": 3.760157273918742e-05, "epoch": 0.7522935779816514, "percentage": 7.52, "elapsed_time": "0:04:43", "remaining_time": "0:58:01", "throughput": 2708.04, "total_tokens": 766928} {"current_steps": 2875, "total_steps": 38150, "loss": 0.6004, "lr": 3.7667103538663175e-05, "epoch": 0.7536041939711664, "percentage": 7.54, "elapsed_time": "0:04:43", "remaining_time": "0:58:00", "throughput": 2708.74, "total_tokens": 768480} {"current_steps": 2880, "total_steps": 38150, "loss": 0.5114, "lr": 3.7732634338138925e-05, "epoch": 0.7549148099606815, "percentage": 7.55, "elapsed_time": "0:04:44", "remaining_time": "0:57:59", "throughput": 2708.56, "total_tokens": 769584} {"current_steps": 2885, "total_steps": 38150, "loss": 0.5689, "lr": 3.779816513761468e-05, "epoch": 0.7562254259501966, "percentage": 7.56, "elapsed_time": "0:04:44", "remaining_time": "0:57:58", "throughput": 2709.18, "total_tokens": 770960} {"current_steps": 2890, "total_steps": 38150, "loss": 0.6082, "lr": 3.786369593709043e-05, "epoch": 0.7575360419397117, "percentage": 7.58, "elapsed_time": "0:04:45", "remaining_time": "0:57:57", "throughput": 2709.54, "total_tokens": 772272} {"current_steps": 2895, "total_steps": 38150, "loss": 0.3947, "lr": 3.7929226736566184e-05, "epoch": 0.7588466579292268, "percentage": 7.59, "elapsed_time": "0:04:45", "remaining_time": "0:58:01", "throughput": 2712.78, "total_tokens": 775536} {"current_steps": 2900, "total_steps": 38150, "loss": 0.6079, "lr": 3.799475753604194e-05, "epoch": 0.7601572739187418, "percentage": 7.6, "elapsed_time": "0:04:46", "remaining_time": "0:58:01", "throughput": 2713.89, "total_tokens": 777216} {"current_steps": 2905, "total_steps": 38150, "loss": 0.4302, "lr": 3.80602883355177e-05, "epoch": 0.7614678899082569, "percentage": 7.61, "elapsed_time": "0:04:46", "remaining_time": "0:57:59", "throughput": 2713.72, "total_tokens": 778320} {"current_steps": 2910, "total_steps": 38150, "loss": 0.5422, "lr": 3.812581913499345e-05, "epoch": 0.762778505897772, "percentage": 7.63, "elapsed_time": "0:04:47", "remaining_time": "0:57:58", "throughput": 2714.19, "total_tokens": 779712} {"current_steps": 2915, "total_steps": 38150, "loss": 0.4855, "lr": 3.81913499344692e-05, "epoch": 0.7640891218872871, "percentage": 7.64, "elapsed_time": "0:04:47", "remaining_time": "0:57:57", "throughput": 2714.15, "total_tokens": 780928} {"current_steps": 2920, "total_steps": 38150, "loss": 0.3741, "lr": 3.825688073394496e-05, "epoch": 0.765399737876802, "percentage": 7.65, "elapsed_time": "0:04:48", "remaining_time": "0:57:56", "throughput": 2714.01, "total_tokens": 782064} {"current_steps": 2925, "total_steps": 38150, "loss": 0.5534, "lr": 3.832241153342071e-05, "epoch": 0.7667103538663171, "percentage": 7.67, "elapsed_time": "0:04:48", "remaining_time": "0:57:56", "throughput": 2714.89, "total_tokens": 783680} {"current_steps": 2930, "total_steps": 38150, "loss": 0.5015, "lr": 3.8387942332896464e-05, "epoch": 0.7680209698558322, "percentage": 7.68, "elapsed_time": "0:04:49", "remaining_time": "0:57:55", "throughput": 2715.07, "total_tokens": 784912} {"current_steps": 2935, "total_steps": 38150, "loss": 0.538, "lr": 3.8453473132372215e-05, "epoch": 0.7693315858453473, "percentage": 7.69, "elapsed_time": "0:04:49", "remaining_time": "0:57:54", "throughput": 2715.74, "total_tokens": 786368} {"current_steps": 2940, "total_steps": 38150, "loss": 0.6837, "lr": 3.851900393184797e-05, "epoch": 0.7706422018348624, "percentage": 7.71, "elapsed_time": "0:04:49", "remaining_time": "0:57:53", "throughput": 2715.94, "total_tokens": 787600} {"current_steps": 2945, "total_steps": 38150, "loss": 0.6916, "lr": 3.858453473132372e-05, "epoch": 0.7719528178243774, "percentage": 7.72, "elapsed_time": "0:04:50", "remaining_time": "0:57:51", "throughput": 2715.97, "total_tokens": 788800} {"current_steps": 2950, "total_steps": 38150, "loss": 0.6628, "lr": 3.865006553079948e-05, "epoch": 0.7732634338138925, "percentage": 7.73, "elapsed_time": "0:04:50", "remaining_time": "0:57:51", "throughput": 2717.09, "total_tokens": 790464} {"current_steps": 2955, "total_steps": 38150, "loss": 1.0472, "lr": 3.871559633027523e-05, "epoch": 0.7745740498034076, "percentage": 7.75, "elapsed_time": "0:04:51", "remaining_time": "0:57:49", "throughput": 2716.39, "total_tokens": 791392} {"current_steps": 2960, "total_steps": 38150, "loss": 0.5231, "lr": 3.878112712975098e-05, "epoch": 0.7758846657929227, "percentage": 7.76, "elapsed_time": "0:04:51", "remaining_time": "0:57:48", "throughput": 2715.98, "total_tokens": 792432} {"current_steps": 2965, "total_steps": 38150, "loss": 0.556, "lr": 3.884665792922674e-05, "epoch": 0.7771952817824378, "percentage": 7.77, "elapsed_time": "0:04:52", "remaining_time": "0:57:48", "throughput": 2717.11, "total_tokens": 794096} {"current_steps": 2970, "total_steps": 38150, "loss": 0.4182, "lr": 3.891218872870249e-05, "epoch": 0.7785058977719528, "percentage": 7.79, "elapsed_time": "0:04:52", "remaining_time": "0:57:47", "throughput": 2718.03, "total_tokens": 795664} {"current_steps": 2975, "total_steps": 38150, "loss": 0.5619, "lr": 3.8977719528178246e-05, "epoch": 0.7798165137614679, "percentage": 7.8, "elapsed_time": "0:04:53", "remaining_time": "0:57:46", "throughput": 2718.52, "total_tokens": 796992} {"current_steps": 2980, "total_steps": 38150, "loss": 0.3889, "lr": 3.9043250327654004e-05, "epoch": 0.781127129750983, "percentage": 7.81, "elapsed_time": "0:04:53", "remaining_time": "0:57:45", "throughput": 2718.37, "total_tokens": 798144} {"current_steps": 2985, "total_steps": 38150, "loss": 0.485, "lr": 3.9108781127129754e-05, "epoch": 0.7824377457404981, "percentage": 7.82, "elapsed_time": "0:04:54", "remaining_time": "0:57:45", "throughput": 2719.91, "total_tokens": 800224} {"current_steps": 2990, "total_steps": 38150, "loss": 0.3899, "lr": 3.9174311926605505e-05, "epoch": 0.783748361730013, "percentage": 7.84, "elapsed_time": "0:04:54", "remaining_time": "0:57:45", "throughput": 2720.39, "total_tokens": 801632} {"current_steps": 2995, "total_steps": 38150, "loss": 0.7386, "lr": 3.923984272608126e-05, "epoch": 0.7850589777195282, "percentage": 7.85, "elapsed_time": "0:04:55", "remaining_time": "0:57:44", "throughput": 2720.69, "total_tokens": 803088} {"current_steps": 3000, "total_steps": 38150, "loss": 0.645, "lr": 3.930537352555701e-05, "epoch": 0.7863695937090432, "percentage": 7.86, "elapsed_time": "0:04:55", "remaining_time": "0:57:43", "throughput": 2720.68, "total_tokens": 804240} {"current_steps": 3005, "total_steps": 38150, "loss": 0.7149, "lr": 3.937090432503276e-05, "epoch": 0.7876802096985583, "percentage": 7.88, "elapsed_time": "0:04:56", "remaining_time": "0:57:42", "throughput": 2720.14, "total_tokens": 805312} {"current_steps": 3010, "total_steps": 38150, "loss": 0.2985, "lr": 3.943643512450852e-05, "epoch": 0.7889908256880734, "percentage": 7.89, "elapsed_time": "0:04:56", "remaining_time": "0:57:42", "throughput": 2721.22, "total_tokens": 807184} {"current_steps": 3015, "total_steps": 38150, "loss": 0.622, "lr": 3.950196592398428e-05, "epoch": 0.7903014416775884, "percentage": 7.9, "elapsed_time": "0:04:57", "remaining_time": "0:57:41", "throughput": 2721.26, "total_tokens": 808400} {"current_steps": 3020, "total_steps": 38150, "loss": 0.5211, "lr": 3.956749672346003e-05, "epoch": 0.7916120576671035, "percentage": 7.92, "elapsed_time": "0:04:57", "remaining_time": "0:57:41", "throughput": 2722.05, "total_tokens": 809936} {"current_steps": 3025, "total_steps": 38150, "loss": 0.5383, "lr": 3.9633027522935785e-05, "epoch": 0.7929226736566186, "percentage": 7.93, "elapsed_time": "0:04:58", "remaining_time": "0:57:40", "throughput": 2722.08, "total_tokens": 811216} {"current_steps": 3030, "total_steps": 38150, "loss": 0.4741, "lr": 3.9698558322411536e-05, "epoch": 0.7942332896461337, "percentage": 7.94, "elapsed_time": "0:04:58", "remaining_time": "0:57:39", "throughput": 2721.82, "total_tokens": 812288} {"current_steps": 3035, "total_steps": 38150, "loss": 0.5008, "lr": 3.9764089121887286e-05, "epoch": 0.7955439056356488, "percentage": 7.96, "elapsed_time": "0:04:58", "remaining_time": "0:57:38", "throughput": 2721.88, "total_tokens": 813536} {"current_steps": 3040, "total_steps": 38150, "loss": 0.5714, "lr": 3.9829619921363044e-05, "epoch": 0.7968545216251638, "percentage": 7.97, "elapsed_time": "0:04:59", "remaining_time": "0:57:36", "throughput": 2722.12, "total_tokens": 814768} {"current_steps": 3045, "total_steps": 38150, "loss": 0.3647, "lr": 3.9895150720838794e-05, "epoch": 0.7981651376146789, "percentage": 7.98, "elapsed_time": "0:04:59", "remaining_time": "0:57:35", "throughput": 2722.04, "total_tokens": 815984} {"current_steps": 3050, "total_steps": 38150, "loss": 0.4115, "lr": 3.996068152031455e-05, "epoch": 0.799475753604194, "percentage": 7.99, "elapsed_time": "0:05:00", "remaining_time": "0:57:36", "throughput": 2722.9, "total_tokens": 817744} {"current_steps": 3055, "total_steps": 38150, "loss": 0.5042, "lr": 4.00262123197903e-05, "epoch": 0.8007863695937091, "percentage": 8.01, "elapsed_time": "0:05:00", "remaining_time": "0:57:34", "throughput": 2722.96, "total_tokens": 818944} {"current_steps": 3060, "total_steps": 38150, "loss": 0.4527, "lr": 4.009174311926606e-05, "epoch": 0.8020969855832241, "percentage": 8.02, "elapsed_time": "0:05:01", "remaining_time": "0:57:33", "throughput": 2723.31, "total_tokens": 820240} {"current_steps": 3065, "total_steps": 38150, "loss": 0.4555, "lr": 4.015727391874181e-05, "epoch": 0.8034076015727392, "percentage": 8.03, "elapsed_time": "0:05:01", "remaining_time": "0:57:33", "throughput": 2724.44, "total_tokens": 822032} {"current_steps": 3070, "total_steps": 38150, "loss": 0.4286, "lr": 4.022280471821757e-05, "epoch": 0.8047182175622543, "percentage": 8.05, "elapsed_time": "0:05:02", "remaining_time": "0:57:33", "throughput": 2725.17, "total_tokens": 823536} {"current_steps": 3075, "total_steps": 38150, "loss": 0.5715, "lr": 4.028833551769332e-05, "epoch": 0.8060288335517694, "percentage": 8.06, "elapsed_time": "0:05:02", "remaining_time": "0:57:32", "throughput": 2725.55, "total_tokens": 824864} {"current_steps": 3080, "total_steps": 38150, "loss": 0.575, "lr": 4.035386631716907e-05, "epoch": 0.8073394495412844, "percentage": 8.07, "elapsed_time": "0:05:03", "remaining_time": "0:57:30", "throughput": 2725.18, "total_tokens": 825936} {"current_steps": 3085, "total_steps": 38150, "loss": 0.5968, "lr": 4.0419397116644826e-05, "epoch": 0.8086500655307994, "percentage": 8.09, "elapsed_time": "0:05:03", "remaining_time": "0:57:29", "throughput": 2724.74, "total_tokens": 826960} {"current_steps": 3090, "total_steps": 38150, "loss": 0.2536, "lr": 4.048492791612058e-05, "epoch": 0.8099606815203145, "percentage": 8.1, "elapsed_time": "0:05:03", "remaining_time": "0:57:28", "throughput": 2723.91, "total_tokens": 827840} {"current_steps": 3095, "total_steps": 38150, "loss": 0.573, "lr": 4.0550458715596333e-05, "epoch": 0.8112712975098296, "percentage": 8.11, "elapsed_time": "0:05:04", "remaining_time": "0:57:27", "throughput": 2724.05, "total_tokens": 829056} {"current_steps": 3100, "total_steps": 38150, "loss": 0.339, "lr": 4.0615989515072084e-05, "epoch": 0.8125819134993447, "percentage": 8.13, "elapsed_time": "0:05:04", "remaining_time": "0:57:26", "throughput": 2724.66, "total_tokens": 830528} {"current_steps": 3105, "total_steps": 38150, "loss": 0.5273, "lr": 4.068152031454784e-05, "epoch": 0.8138925294888598, "percentage": 8.14, "elapsed_time": "0:05:05", "remaining_time": "0:57:25", "throughput": 2725.21, "total_tokens": 831920} {"current_steps": 3110, "total_steps": 38150, "loss": 0.537, "lr": 4.074705111402359e-05, "epoch": 0.8152031454783748, "percentage": 8.15, "elapsed_time": "0:05:06", "remaining_time": "0:57:30", "throughput": 2727.02, "total_tokens": 835104} {"current_steps": 3115, "total_steps": 38150, "loss": 0.3954, "lr": 4.081258191349935e-05, "epoch": 0.8165137614678899, "percentage": 8.17, "elapsed_time": "0:05:06", "remaining_time": "0:57:31", "throughput": 2729.17, "total_tokens": 837472} {"current_steps": 3120, "total_steps": 38150, "loss": 0.4218, "lr": 4.08781127129751e-05, "epoch": 0.817824377457405, "percentage": 8.18, "elapsed_time": "0:05:07", "remaining_time": "0:57:30", "throughput": 2729.27, "total_tokens": 838688} {"current_steps": 3125, "total_steps": 38150, "loss": 0.5962, "lr": 4.094364351245085e-05, "epoch": 0.8191349934469201, "percentage": 8.19, "elapsed_time": "0:05:07", "remaining_time": "0:57:29", "throughput": 2730.46, "total_tokens": 840448} {"current_steps": 3130, "total_steps": 38150, "loss": 0.3767, "lr": 4.100917431192661e-05, "epoch": 0.8204456094364351, "percentage": 8.2, "elapsed_time": "0:05:08", "remaining_time": "0:57:28", "throughput": 2730.74, "total_tokens": 841712} {"current_steps": 3135, "total_steps": 38150, "loss": 0.8721, "lr": 4.1074705111402365e-05, "epoch": 0.8217562254259502, "percentage": 8.22, "elapsed_time": "0:05:08", "remaining_time": "0:57:27", "throughput": 2730.88, "total_tokens": 843024} {"current_steps": 3140, "total_steps": 38150, "loss": 0.7216, "lr": 4.1140235910878115e-05, "epoch": 0.8230668414154653, "percentage": 8.23, "elapsed_time": "0:05:09", "remaining_time": "0:57:27", "throughput": 2732.02, "total_tokens": 844736} {"current_steps": 3145, "total_steps": 38150, "loss": 0.4774, "lr": 4.1205766710353866e-05, "epoch": 0.8243774574049804, "percentage": 8.24, "elapsed_time": "0:05:09", "remaining_time": "0:57:27", "throughput": 2733.04, "total_tokens": 846432} {"current_steps": 3150, "total_steps": 38150, "loss": 0.5695, "lr": 4.127129750982962e-05, "epoch": 0.8256880733944955, "percentage": 8.26, "elapsed_time": "0:05:10", "remaining_time": "0:57:26", "throughput": 2733.66, "total_tokens": 847984} {"current_steps": 3155, "total_steps": 38150, "loss": 0.5457, "lr": 4.1336828309305374e-05, "epoch": 0.8269986893840104, "percentage": 8.27, "elapsed_time": "0:05:10", "remaining_time": "0:57:25", "throughput": 2733.44, "total_tokens": 849072} {"current_steps": 3160, "total_steps": 38150, "loss": 0.5563, "lr": 4.140235910878113e-05, "epoch": 0.8283093053735255, "percentage": 8.28, "elapsed_time": "0:05:11", "remaining_time": "0:57:24", "throughput": 2734.06, "total_tokens": 850496} {"current_steps": 3165, "total_steps": 38150, "loss": 0.3604, "lr": 4.146788990825689e-05, "epoch": 0.8296199213630406, "percentage": 8.3, "elapsed_time": "0:05:11", "remaining_time": "0:57:23", "throughput": 2734.42, "total_tokens": 851904} {"current_steps": 3170, "total_steps": 38150, "loss": 0.4989, "lr": 4.153342070773263e-05, "epoch": 0.8309305373525557, "percentage": 8.31, "elapsed_time": "0:05:11", "remaining_time": "0:57:22", "throughput": 2733.85, "total_tokens": 852864} {"current_steps": 3175, "total_steps": 38150, "loss": 0.5712, "lr": 4.159895150720839e-05, "epoch": 0.8322411533420708, "percentage": 8.32, "elapsed_time": "0:05:12", "remaining_time": "0:57:21", "throughput": 2733.86, "total_tokens": 854032} {"current_steps": 3180, "total_steps": 38150, "loss": 0.483, "lr": 4.1664482306684147e-05, "epoch": 0.8335517693315858, "percentage": 8.34, "elapsed_time": "0:05:12", "remaining_time": "0:57:19", "throughput": 2733.63, "total_tokens": 855120} {"current_steps": 3185, "total_steps": 38150, "loss": 0.4685, "lr": 4.17300131061599e-05, "epoch": 0.8348623853211009, "percentage": 8.35, "elapsed_time": "0:05:13", "remaining_time": "0:57:18", "throughput": 2733.71, "total_tokens": 856320} {"current_steps": 3190, "total_steps": 38150, "loss": 0.3534, "lr": 4.1795543905635654e-05, "epoch": 0.836173001310616, "percentage": 8.36, "elapsed_time": "0:05:13", "remaining_time": "0:57:17", "throughput": 2733.71, "total_tokens": 857520} {"current_steps": 3195, "total_steps": 38150, "loss": 0.3624, "lr": 4.1861074705111405e-05, "epoch": 0.8374836173001311, "percentage": 8.37, "elapsed_time": "0:05:14", "remaining_time": "0:57:16", "throughput": 2733.94, "total_tokens": 858864} {"current_steps": 3200, "total_steps": 38150, "loss": 0.5725, "lr": 4.1926605504587155e-05, "epoch": 0.8387942332896461, "percentage": 8.39, "elapsed_time": "0:05:14", "remaining_time": "0:57:18", "throughput": 2736.34, "total_tokens": 861424} {"current_steps": 3205, "total_steps": 38150, "loss": 0.8135, "lr": 4.199213630406291e-05, "epoch": 0.8401048492791612, "percentage": 8.4, "elapsed_time": "0:05:15", "remaining_time": "0:57:17", "throughput": 2735.92, "total_tokens": 862448} {"current_steps": 3210, "total_steps": 38150, "loss": 0.4708, "lr": 4.205766710353867e-05, "epoch": 0.8414154652686763, "percentage": 8.41, "elapsed_time": "0:05:15", "remaining_time": "0:57:15", "throughput": 2735.34, "total_tokens": 863408} {"current_steps": 3215, "total_steps": 38150, "loss": 0.4995, "lr": 4.2123197903014414e-05, "epoch": 0.8427260812581914, "percentage": 8.43, "elapsed_time": "0:05:16", "remaining_time": "0:57:14", "throughput": 2734.84, "total_tokens": 864432} {"current_steps": 3220, "total_steps": 38150, "loss": 0.403, "lr": 4.218872870249017e-05, "epoch": 0.8440366972477065, "percentage": 8.44, "elapsed_time": "0:05:16", "remaining_time": "0:57:13", "throughput": 2734.97, "total_tokens": 865648} {"current_steps": 3225, "total_steps": 38150, "loss": 0.4282, "lr": 4.225425950196593e-05, "epoch": 0.8453473132372215, "percentage": 8.45, "elapsed_time": "0:05:17", "remaining_time": "0:57:13", "throughput": 2736.38, "total_tokens": 867536} {"current_steps": 3230, "total_steps": 38150, "loss": 0.5901, "lr": 4.231979030144168e-05, "epoch": 0.8466579292267365, "percentage": 8.47, "elapsed_time": "0:05:17", "remaining_time": "0:57:12", "throughput": 2736.71, "total_tokens": 868864} {"current_steps": 3235, "total_steps": 38150, "loss": 0.6637, "lr": 4.2385321100917436e-05, "epoch": 0.8479685452162516, "percentage": 8.48, "elapsed_time": "0:05:17", "remaining_time": "0:57:11", "throughput": 2737.17, "total_tokens": 870272} {"current_steps": 3240, "total_steps": 38150, "loss": 0.6849, "lr": 4.245085190039319e-05, "epoch": 0.8492791612057667, "percentage": 8.49, "elapsed_time": "0:05:18", "remaining_time": "0:57:10", "throughput": 2736.88, "total_tokens": 871344} {"current_steps": 3245, "total_steps": 38150, "loss": 0.5599, "lr": 4.251638269986894e-05, "epoch": 0.8505897771952818, "percentage": 8.51, "elapsed_time": "0:05:18", "remaining_time": "0:57:09", "throughput": 2737.5, "total_tokens": 872848} {"current_steps": 3250, "total_steps": 38150, "loss": 0.6501, "lr": 4.2581913499344695e-05, "epoch": 0.8519003931847968, "percentage": 8.52, "elapsed_time": "0:05:19", "remaining_time": "0:57:08", "throughput": 2737.61, "total_tokens": 874160} {"current_steps": 3255, "total_steps": 38150, "loss": 0.3642, "lr": 4.264744429882045e-05, "epoch": 0.8532110091743119, "percentage": 8.53, "elapsed_time": "0:05:19", "remaining_time": "0:57:07", "throughput": 2737.86, "total_tokens": 875424} {"current_steps": 3260, "total_steps": 38150, "loss": 0.63, "lr": 4.27129750982962e-05, "epoch": 0.854521625163827, "percentage": 8.55, "elapsed_time": "0:05:20", "remaining_time": "0:57:06", "throughput": 2737.58, "total_tokens": 876544} {"current_steps": 3265, "total_steps": 38150, "loss": 0.4559, "lr": 4.277850589777195e-05, "epoch": 0.8558322411533421, "percentage": 8.56, "elapsed_time": "0:05:20", "remaining_time": "0:57:06", "throughput": 2738.09, "total_tokens": 878032} {"current_steps": 3270, "total_steps": 38150, "loss": 0.6221, "lr": 4.284403669724771e-05, "epoch": 0.8571428571428571, "percentage": 8.57, "elapsed_time": "0:05:21", "remaining_time": "0:57:06", "throughput": 2739.67, "total_tokens": 880112} {"current_steps": 3275, "total_steps": 38150, "loss": 0.4155, "lr": 4.290956749672346e-05, "epoch": 0.8584534731323722, "percentage": 8.58, "elapsed_time": "0:05:21", "remaining_time": "0:57:06", "throughput": 2739.9, "total_tokens": 881520} {"current_steps": 3280, "total_steps": 38150, "loss": 0.4087, "lr": 4.297509829619922e-05, "epoch": 0.8597640891218873, "percentage": 8.6, "elapsed_time": "0:05:22", "remaining_time": "0:57:04", "throughput": 2739.61, "total_tokens": 882592} {"current_steps": 3285, "total_steps": 38150, "loss": 0.442, "lr": 4.304062909567497e-05, "epoch": 0.8610747051114024, "percentage": 8.61, "elapsed_time": "0:05:22", "remaining_time": "0:57:04", "throughput": 2739.49, "total_tokens": 883792} {"current_steps": 3290, "total_steps": 38150, "loss": 0.5626, "lr": 4.310615989515072e-05, "epoch": 0.8623853211009175, "percentage": 8.62, "elapsed_time": "0:05:23", "remaining_time": "0:57:03", "throughput": 2740.05, "total_tokens": 885200} {"current_steps": 3295, "total_steps": 38150, "loss": 0.4815, "lr": 4.3171690694626476e-05, "epoch": 0.8636959370904325, "percentage": 8.64, "elapsed_time": "0:05:23", "remaining_time": "0:57:02", "throughput": 2740.83, "total_tokens": 886752} {"current_steps": 3300, "total_steps": 38150, "loss": 0.576, "lr": 4.3237221494102234e-05, "epoch": 0.8650065530799476, "percentage": 8.65, "elapsed_time": "0:05:23", "remaining_time": "0:57:01", "throughput": 2741.16, "total_tokens": 888080} {"current_steps": 3305, "total_steps": 38150, "loss": 0.673, "lr": 4.3302752293577984e-05, "epoch": 0.8663171690694627, "percentage": 8.66, "elapsed_time": "0:05:24", "remaining_time": "0:57:00", "throughput": 2740.95, "total_tokens": 889248} {"current_steps": 3310, "total_steps": 38150, "loss": 0.5583, "lr": 4.3368283093053735e-05, "epoch": 0.8676277850589778, "percentage": 8.68, "elapsed_time": "0:05:24", "remaining_time": "0:56:59", "throughput": 2740.73, "total_tokens": 890368} {"current_steps": 3315, "total_steps": 38150, "loss": 0.6351, "lr": 4.343381389252949e-05, "epoch": 0.8689384010484927, "percentage": 8.69, "elapsed_time": "0:05:25", "remaining_time": "0:56:58", "throughput": 2740.56, "total_tokens": 891472} {"current_steps": 3320, "total_steps": 38150, "loss": 0.5092, "lr": 4.349934469200524e-05, "epoch": 0.8702490170380078, "percentage": 8.7, "elapsed_time": "0:05:25", "remaining_time": "0:56:57", "throughput": 2740.6, "total_tokens": 892688} {"current_steps": 3325, "total_steps": 38150, "loss": 0.568, "lr": 4.3564875491481e-05, "epoch": 0.8715596330275229, "percentage": 8.72, "elapsed_time": "0:05:26", "remaining_time": "0:56:56", "throughput": 2740.7, "total_tokens": 893920} {"current_steps": 3330, "total_steps": 38150, "loss": 0.4485, "lr": 4.363040629095675e-05, "epoch": 0.872870249017038, "percentage": 8.73, "elapsed_time": "0:05:26", "remaining_time": "0:56:54", "throughput": 2740.66, "total_tokens": 895072} {"current_steps": 3335, "total_steps": 38150, "loss": 0.5706, "lr": 4.36959370904325e-05, "epoch": 0.8741808650065531, "percentage": 8.74, "elapsed_time": "0:05:27", "remaining_time": "0:56:54", "throughput": 2740.46, "total_tokens": 896272} {"current_steps": 3340, "total_steps": 38150, "loss": 0.6412, "lr": 4.376146788990826e-05, "epoch": 0.8754914809960681, "percentage": 8.75, "elapsed_time": "0:05:27", "remaining_time": "0:56:53", "throughput": 2740.93, "total_tokens": 897648} {"current_steps": 3345, "total_steps": 38150, "loss": 0.7167, "lr": 4.3826998689384016e-05, "epoch": 0.8768020969855832, "percentage": 8.77, "elapsed_time": "0:05:27", "remaining_time": "0:56:52", "throughput": 2740.73, "total_tokens": 898768} {"current_steps": 3350, "total_steps": 38150, "loss": 0.5439, "lr": 4.3892529488859766e-05, "epoch": 0.8781127129750983, "percentage": 8.78, "elapsed_time": "0:05:28", "remaining_time": "0:56:51", "throughput": 2741.24, "total_tokens": 900240} {"current_steps": 3355, "total_steps": 38150, "loss": 0.5357, "lr": 4.395806028833552e-05, "epoch": 0.8794233289646134, "percentage": 8.79, "elapsed_time": "0:05:28", "remaining_time": "0:56:51", "throughput": 2742.45, "total_tokens": 902000} {"current_steps": 3360, "total_steps": 38150, "loss": 0.5592, "lr": 4.4023591087811274e-05, "epoch": 0.8807339449541285, "percentage": 8.81, "elapsed_time": "0:05:29", "remaining_time": "0:56:50", "throughput": 2742.94, "total_tokens": 903488} {"current_steps": 3365, "total_steps": 38150, "loss": 0.4966, "lr": 4.4089121887287024e-05, "epoch": 0.8820445609436435, "percentage": 8.82, "elapsed_time": "0:05:29", "remaining_time": "0:56:49", "throughput": 2743.09, "total_tokens": 904736} {"current_steps": 3370, "total_steps": 38150, "loss": 0.4486, "lr": 4.415465268676278e-05, "epoch": 0.8833551769331586, "percentage": 8.83, "elapsed_time": "0:05:30", "remaining_time": "0:56:50", "throughput": 2744.96, "total_tokens": 907040} {"current_steps": 3375, "total_steps": 38150, "loss": 0.6384, "lr": 4.422018348623854e-05, "epoch": 0.8846657929226737, "percentage": 8.85, "elapsed_time": "0:05:30", "remaining_time": "0:56:49", "throughput": 2744.49, "total_tokens": 908128} {"current_steps": 3380, "total_steps": 38150, "loss": 0.6205, "lr": 4.428571428571428e-05, "epoch": 0.8859764089121888, "percentage": 8.86, "elapsed_time": "0:05:31", "remaining_time": "0:56:48", "throughput": 2745.35, "total_tokens": 909712} {"current_steps": 3385, "total_steps": 38150, "loss": 0.6551, "lr": 4.435124508519004e-05, "epoch": 0.8872870249017037, "percentage": 8.87, "elapsed_time": "0:05:31", "remaining_time": "0:56:47", "throughput": 2745.47, "total_tokens": 910944} {"current_steps": 3390, "total_steps": 38150, "loss": 0.5018, "lr": 4.44167758846658e-05, "epoch": 0.8885976408912188, "percentage": 8.89, "elapsed_time": "0:05:32", "remaining_time": "0:56:46", "throughput": 2745.23, "total_tokens": 912096} {"current_steps": 3395, "total_steps": 38150, "loss": 0.6398, "lr": 4.448230668414155e-05, "epoch": 0.8899082568807339, "percentage": 8.9, "elapsed_time": "0:05:32", "remaining_time": "0:56:45", "throughput": 2744.94, "total_tokens": 913248} {"current_steps": 3400, "total_steps": 38150, "loss": 0.4601, "lr": 4.45478374836173e-05, "epoch": 0.891218872870249, "percentage": 8.91, "elapsed_time": "0:05:33", "remaining_time": "0:56:44", "throughput": 2744.63, "total_tokens": 914288} {"current_steps": 3405, "total_steps": 38150, "loss": 0.5067, "lr": 4.4613368283093056e-05, "epoch": 0.8925294888597641, "percentage": 8.93, "elapsed_time": "0:05:33", "remaining_time": "0:56:43", "throughput": 2744.22, "total_tokens": 915312} {"current_steps": 3410, "total_steps": 38150, "loss": 0.3875, "lr": 4.4678899082568806e-05, "epoch": 0.8938401048492791, "percentage": 8.94, "elapsed_time": "0:05:34", "remaining_time": "0:56:42", "throughput": 2744.32, "total_tokens": 916624} {"current_steps": 3415, "total_steps": 38150, "loss": 0.478, "lr": 4.4744429882044564e-05, "epoch": 0.8951507208387942, "percentage": 8.95, "elapsed_time": "0:05:34", "remaining_time": "0:56:41", "throughput": 2744.91, "total_tokens": 918048} {"current_steps": 3420, "total_steps": 38150, "loss": 0.7344, "lr": 4.480996068152032e-05, "epoch": 0.8964613368283093, "percentage": 8.96, "elapsed_time": "0:05:34", "remaining_time": "0:56:40", "throughput": 2745.53, "total_tokens": 919472} {"current_steps": 3425, "total_steps": 38150, "loss": 0.5555, "lr": 4.487549148099607e-05, "epoch": 0.8977719528178244, "percentage": 8.98, "elapsed_time": "0:05:35", "remaining_time": "0:56:39", "throughput": 2745.55, "total_tokens": 920688} {"current_steps": 3430, "total_steps": 38150, "loss": 0.6508, "lr": 4.494102228047182e-05, "epoch": 0.8990825688073395, "percentage": 8.99, "elapsed_time": "0:05:35", "remaining_time": "0:56:38", "throughput": 2744.42, "total_tokens": 921456} {"current_steps": 3435, "total_steps": 38150, "loss": 0.4621, "lr": 4.500655307994758e-05, "epoch": 0.9003931847968545, "percentage": 9.0, "elapsed_time": "0:05:36", "remaining_time": "0:56:37", "throughput": 2744.76, "total_tokens": 922816} {"current_steps": 3440, "total_steps": 38150, "loss": 0.8513, "lr": 4.507208387942333e-05, "epoch": 0.9017038007863696, "percentage": 9.02, "elapsed_time": "0:05:36", "remaining_time": "0:56:36", "throughput": 2745.48, "total_tokens": 924304} {"current_steps": 3445, "total_steps": 38150, "loss": 0.461, "lr": 4.513761467889909e-05, "epoch": 0.9030144167758847, "percentage": 9.03, "elapsed_time": "0:05:37", "remaining_time": "0:56:36", "throughput": 2746.01, "total_tokens": 925696} {"current_steps": 3450, "total_steps": 38150, "loss": 0.7884, "lr": 4.520314547837484e-05, "epoch": 0.9043250327653998, "percentage": 9.04, "elapsed_time": "0:05:37", "remaining_time": "0:56:34", "throughput": 2745.57, "total_tokens": 926688} {"current_steps": 3455, "total_steps": 38150, "loss": 0.7816, "lr": 4.526867627785059e-05, "epoch": 0.9056356487549148, "percentage": 9.06, "elapsed_time": "0:05:38", "remaining_time": "0:56:34", "throughput": 2746.11, "total_tokens": 928336} {"current_steps": 3460, "total_steps": 38150, "loss": 0.3352, "lr": 4.5334207077326345e-05, "epoch": 0.9069462647444299, "percentage": 9.07, "elapsed_time": "0:05:38", "remaining_time": "0:56:33", "throughput": 2746.29, "total_tokens": 929664} {"current_steps": 3465, "total_steps": 38150, "loss": 0.6602, "lr": 4.53997378768021e-05, "epoch": 0.908256880733945, "percentage": 9.08, "elapsed_time": "0:05:39", "remaining_time": "0:56:33", "throughput": 2746.79, "total_tokens": 931216} {"current_steps": 3470, "total_steps": 38150, "loss": 1.1129, "lr": 4.546526867627785e-05, "epoch": 0.90956749672346, "percentage": 9.1, "elapsed_time": "0:05:39", "remaining_time": "0:56:32", "throughput": 2746.88, "total_tokens": 932512} {"current_steps": 3475, "total_steps": 38150, "loss": 1.5403, "lr": 4.5530799475753604e-05, "epoch": 0.9108781127129751, "percentage": 9.11, "elapsed_time": "0:05:39", "remaining_time": "0:56:31", "throughput": 2746.18, "total_tokens": 933440} {"current_steps": 3480, "total_steps": 38150, "loss": 0.5091, "lr": 4.559633027522936e-05, "epoch": 0.9121887287024901, "percentage": 9.12, "elapsed_time": "0:05:40", "remaining_time": "0:56:30", "throughput": 2746.27, "total_tokens": 934736} {"current_steps": 3485, "total_steps": 38150, "loss": 0.3343, "lr": 4.566186107470511e-05, "epoch": 0.9134993446920052, "percentage": 9.13, "elapsed_time": "0:05:40", "remaining_time": "0:56:29", "throughput": 2746.24, "total_tokens": 935920} {"current_steps": 3490, "total_steps": 38150, "loss": 0.593, "lr": 4.572739187418087e-05, "epoch": 0.9148099606815203, "percentage": 9.15, "elapsed_time": "0:05:41", "remaining_time": "0:56:29", "throughput": 2746.73, "total_tokens": 937392} {"current_steps": 3495, "total_steps": 38150, "loss": 0.4771, "lr": 4.579292267365662e-05, "epoch": 0.9161205766710354, "percentage": 9.16, "elapsed_time": "0:05:41", "remaining_time": "0:56:28", "throughput": 2746.64, "total_tokens": 938560} {"current_steps": 3500, "total_steps": 38150, "loss": 0.6115, "lr": 4.585845347313238e-05, "epoch": 0.9174311926605505, "percentage": 9.17, "elapsed_time": "0:05:42", "remaining_time": "0:56:27", "throughput": 2746.76, "total_tokens": 939776} {"current_steps": 3505, "total_steps": 38150, "loss": 0.7145, "lr": 4.592398427260813e-05, "epoch": 0.9187418086500655, "percentage": 9.19, "elapsed_time": "0:05:42", "remaining_time": "0:56:26", "throughput": 2746.74, "total_tokens": 940960} {"current_steps": 3510, "total_steps": 38150, "loss": 0.4551, "lr": 4.5989515072083885e-05, "epoch": 0.9200524246395806, "percentage": 9.2, "elapsed_time": "0:05:43", "remaining_time": "0:56:25", "throughput": 2747.31, "total_tokens": 942384} {"current_steps": 3515, "total_steps": 38150, "loss": 0.5551, "lr": 4.6055045871559635e-05, "epoch": 0.9213630406290957, "percentage": 9.21, "elapsed_time": "0:05:43", "remaining_time": "0:56:24", "throughput": 2747.89, "total_tokens": 943872} {"current_steps": 3520, "total_steps": 38150, "loss": 0.6122, "lr": 4.6120576671035386e-05, "epoch": 0.9226736566186108, "percentage": 9.23, "elapsed_time": "0:05:43", "remaining_time": "0:56:24", "throughput": 2748.27, "total_tokens": 945360} {"current_steps": 3525, "total_steps": 38150, "loss": 0.4408, "lr": 4.618610747051114e-05, "epoch": 0.9239842726081258, "percentage": 9.24, "elapsed_time": "0:05:44", "remaining_time": "0:56:23", "throughput": 2748.04, "total_tokens": 946480} {"current_steps": 3530, "total_steps": 38150, "loss": 0.5234, "lr": 4.6251638269986893e-05, "epoch": 0.9252948885976409, "percentage": 9.25, "elapsed_time": "0:05:44", "remaining_time": "0:56:22", "throughput": 2748.24, "total_tokens": 947744} {"current_steps": 3535, "total_steps": 38150, "loss": 0.65, "lr": 4.631716906946265e-05, "epoch": 0.926605504587156, "percentage": 9.27, "elapsed_time": "0:05:45", "remaining_time": "0:56:21", "throughput": 2748.34, "total_tokens": 948976} {"current_steps": 3540, "total_steps": 38150, "loss": 0.5835, "lr": 4.63826998689384e-05, "epoch": 0.927916120576671, "percentage": 9.28, "elapsed_time": "0:05:45", "remaining_time": "0:56:20", "throughput": 2748.67, "total_tokens": 950384} {"current_steps": 3545, "total_steps": 38150, "loss": 0.5243, "lr": 4.644823066841416e-05, "epoch": 0.9292267365661862, "percentage": 9.29, "elapsed_time": "0:05:46", "remaining_time": "0:56:19", "throughput": 2748.68, "total_tokens": 951584} {"current_steps": 3550, "total_steps": 38150, "loss": 0.6499, "lr": 4.651376146788991e-05, "epoch": 0.9305373525557011, "percentage": 9.31, "elapsed_time": "0:05:46", "remaining_time": "0:56:18", "throughput": 2748.74, "total_tokens": 952912} {"current_steps": 3555, "total_steps": 38150, "loss": 0.7328, "lr": 4.6579292267365666e-05, "epoch": 0.9318479685452162, "percentage": 9.32, "elapsed_time": "0:05:47", "remaining_time": "0:56:17", "throughput": 2749.41, "total_tokens": 954368} {"current_steps": 3560, "total_steps": 38150, "loss": 0.4747, "lr": 4.664482306684142e-05, "epoch": 0.9331585845347313, "percentage": 9.33, "elapsed_time": "0:05:47", "remaining_time": "0:56:17", "throughput": 2750.28, "total_tokens": 956000} {"current_steps": 3565, "total_steps": 38150, "loss": 0.5145, "lr": 4.671035386631717e-05, "epoch": 0.9344692005242464, "percentage": 9.34, "elapsed_time": "0:05:48", "remaining_time": "0:56:16", "throughput": 2750.37, "total_tokens": 957328} {"current_steps": 3570, "total_steps": 38150, "loss": 0.5319, "lr": 4.6775884665792925e-05, "epoch": 0.9357798165137615, "percentage": 9.36, "elapsed_time": "0:05:48", "remaining_time": "0:56:15", "throughput": 2750.23, "total_tokens": 958528} {"current_steps": 3575, "total_steps": 38150, "loss": 0.9308, "lr": 4.684141546526868e-05, "epoch": 0.9370904325032765, "percentage": 9.37, "elapsed_time": "0:05:48", "remaining_time": "0:56:14", "throughput": 2750.49, "total_tokens": 959824} {"current_steps": 3580, "total_steps": 38150, "loss": 0.4791, "lr": 4.690694626474443e-05, "epoch": 0.9384010484927916, "percentage": 9.38, "elapsed_time": "0:05:49", "remaining_time": "0:56:14", "throughput": 2750.89, "total_tokens": 961232} {"current_steps": 3585, "total_steps": 38150, "loss": 0.6643, "lr": 4.697247706422019e-05, "epoch": 0.9397116644823067, "percentage": 9.4, "elapsed_time": "0:05:49", "remaining_time": "0:56:13", "throughput": 2751.03, "total_tokens": 962480} {"current_steps": 3590, "total_steps": 38150, "loss": 0.2748, "lr": 4.703800786369594e-05, "epoch": 0.9410222804718218, "percentage": 9.41, "elapsed_time": "0:05:50", "remaining_time": "0:56:12", "throughput": 2751.97, "total_tokens": 964128} {"current_steps": 3595, "total_steps": 38150, "loss": 0.6014, "lr": 4.710353866317169e-05, "epoch": 0.9423328964613368, "percentage": 9.42, "elapsed_time": "0:05:50", "remaining_time": "0:56:11", "throughput": 2752.52, "total_tokens": 965584} {"current_steps": 3600, "total_steps": 38150, "loss": 0.5212, "lr": 4.716906946264745e-05, "epoch": 0.9436435124508519, "percentage": 9.44, "elapsed_time": "0:05:51", "remaining_time": "0:56:11", "throughput": 2753.19, "total_tokens": 967136} {"current_steps": 3605, "total_steps": 38150, "loss": 0.6029, "lr": 4.72346002621232e-05, "epoch": 0.944954128440367, "percentage": 9.45, "elapsed_time": "0:05:51", "remaining_time": "0:56:10", "throughput": 2753.4, "total_tokens": 968512} {"current_steps": 3610, "total_steps": 38150, "loss": 0.7484, "lr": 4.730013106159895e-05, "epoch": 0.9462647444298821, "percentage": 9.46, "elapsed_time": "0:05:52", "remaining_time": "0:56:09", "throughput": 2753.51, "total_tokens": 969744} {"current_steps": 3615, "total_steps": 38150, "loss": 0.3888, "lr": 4.7365661861074707e-05, "epoch": 0.9475753604193972, "percentage": 9.48, "elapsed_time": "0:05:52", "remaining_time": "0:56:08", "throughput": 2753.6, "total_tokens": 970976} {"current_steps": 3620, "total_steps": 38150, "loss": 0.4555, "lr": 4.7431192660550464e-05, "epoch": 0.9488859764089121, "percentage": 9.49, "elapsed_time": "0:05:53", "remaining_time": "0:56:07", "throughput": 2753.79, "total_tokens": 972240} {"current_steps": 3625, "total_steps": 38150, "loss": 0.5738, "lr": 4.7496723460026214e-05, "epoch": 0.9501965923984272, "percentage": 9.5, "elapsed_time": "0:05:53", "remaining_time": "0:56:07", "throughput": 2754.75, "total_tokens": 973904} {"current_steps": 3630, "total_steps": 38150, "loss": 0.4021, "lr": 4.756225425950197e-05, "epoch": 0.9515072083879423, "percentage": 9.52, "elapsed_time": "0:05:53", "remaining_time": "0:56:06", "throughput": 2755.43, "total_tokens": 975392} {"current_steps": 3635, "total_steps": 38150, "loss": 0.4658, "lr": 4.762778505897772e-05, "epoch": 0.9528178243774574, "percentage": 9.53, "elapsed_time": "0:05:54", "remaining_time": "0:56:05", "throughput": 2755.47, "total_tokens": 976560} {"current_steps": 3640, "total_steps": 38150, "loss": 0.7576, "lr": 4.769331585845347e-05, "epoch": 0.9541284403669725, "percentage": 9.54, "elapsed_time": "0:05:54", "remaining_time": "0:56:04", "throughput": 2754.89, "total_tokens": 977600} {"current_steps": 3645, "total_steps": 38150, "loss": 0.6324, "lr": 4.775884665792923e-05, "epoch": 0.9554390563564875, "percentage": 9.55, "elapsed_time": "0:05:55", "remaining_time": "0:56:03", "throughput": 2755.02, "total_tokens": 978896} {"current_steps": 3650, "total_steps": 38150, "loss": 0.4969, "lr": 4.782437745740499e-05, "epoch": 0.9567496723460026, "percentage": 9.57, "elapsed_time": "0:05:55", "remaining_time": "0:56:02", "throughput": 2755.45, "total_tokens": 980320} {"current_steps": 3655, "total_steps": 38150, "loss": 0.7315, "lr": 4.788990825688074e-05, "epoch": 0.9580602883355177, "percentage": 9.58, "elapsed_time": "0:05:56", "remaining_time": "0:56:02", "throughput": 2755.88, "total_tokens": 981744} {"current_steps": 3660, "total_steps": 38150, "loss": 0.4462, "lr": 4.795543905635649e-05, "epoch": 0.9593709043250328, "percentage": 9.59, "elapsed_time": "0:05:56", "remaining_time": "0:56:01", "throughput": 2756.05, "total_tokens": 983088} {"current_steps": 3665, "total_steps": 38150, "loss": 0.4159, "lr": 4.8020969855832246e-05, "epoch": 0.9606815203145478, "percentage": 9.61, "elapsed_time": "0:05:57", "remaining_time": "0:56:00", "throughput": 2756.1, "total_tokens": 984320} {"current_steps": 3670, "total_steps": 38150, "loss": 0.3933, "lr": 4.8086500655307996e-05, "epoch": 0.9619921363040629, "percentage": 9.62, "elapsed_time": "0:05:57", "remaining_time": "0:55:59", "throughput": 2756.11, "total_tokens": 985520} {"current_steps": 3675, "total_steps": 38150, "loss": 0.4487, "lr": 4.8152031454783754e-05, "epoch": 0.963302752293578, "percentage": 9.63, "elapsed_time": "0:05:57", "remaining_time": "0:55:58", "throughput": 2755.54, "total_tokens": 986464} {"current_steps": 3680, "total_steps": 38150, "loss": 0.3602, "lr": 4.8217562254259504e-05, "epoch": 0.9646133682830931, "percentage": 9.65, "elapsed_time": "0:05:58", "remaining_time": "0:55:57", "throughput": 2755.59, "total_tokens": 987680} {"current_steps": 3685, "total_steps": 38150, "loss": 0.4343, "lr": 4.8283093053735255e-05, "epoch": 0.9659239842726082, "percentage": 9.66, "elapsed_time": "0:05:58", "remaining_time": "0:55:57", "throughput": 2756.41, "total_tokens": 989408} {"current_steps": 3690, "total_steps": 38150, "loss": 0.3545, "lr": 4.834862385321101e-05, "epoch": 0.9672346002621232, "percentage": 9.67, "elapsed_time": "0:05:59", "remaining_time": "0:55:56", "throughput": 2755.82, "total_tokens": 990368} {"current_steps": 3695, "total_steps": 38150, "loss": 0.4737, "lr": 4.841415465268677e-05, "epoch": 0.9685452162516383, "percentage": 9.69, "elapsed_time": "0:05:59", "remaining_time": "0:55:55", "throughput": 2756.77, "total_tokens": 992112} {"current_steps": 3700, "total_steps": 38150, "loss": 0.5261, "lr": 4.847968545216252e-05, "epoch": 0.9698558322411533, "percentage": 9.7, "elapsed_time": "0:06:00", "remaining_time": "0:55:55", "throughput": 2757.01, "total_tokens": 993488} {"current_steps": 3705, "total_steps": 38150, "loss": 0.5846, "lr": 4.854521625163827e-05, "epoch": 0.9711664482306684, "percentage": 9.71, "elapsed_time": "0:06:00", "remaining_time": "0:55:54", "throughput": 2757.14, "total_tokens": 994800} {"current_steps": 3710, "total_steps": 38150, "loss": 0.4845, "lr": 4.861074705111403e-05, "epoch": 0.9724770642201835, "percentage": 9.72, "elapsed_time": "0:06:01", "remaining_time": "0:55:53", "throughput": 2757.41, "total_tokens": 996192} {"current_steps": 3715, "total_steps": 38150, "loss": 0.426, "lr": 4.867627785058978e-05, "epoch": 0.9737876802096985, "percentage": 9.74, "elapsed_time": "0:06:01", "remaining_time": "0:55:53", "throughput": 2758.17, "total_tokens": 997872} {"current_steps": 3720, "total_steps": 38150, "loss": 0.6116, "lr": 4.8741808650065535e-05, "epoch": 0.9750982961992136, "percentage": 9.75, "elapsed_time": "0:06:02", "remaining_time": "0:55:52", "throughput": 2759.02, "total_tokens": 999520} {"current_steps": 3725, "total_steps": 38150, "loss": 0.5332, "lr": 4.880733944954129e-05, "epoch": 0.9764089121887287, "percentage": 9.76, "elapsed_time": "0:06:02", "remaining_time": "0:55:51", "throughput": 2758.54, "total_tokens": 1000496} {"current_steps": 3730, "total_steps": 38150, "loss": 0.4836, "lr": 4.8872870249017036e-05, "epoch": 0.9777195281782438, "percentage": 9.78, "elapsed_time": "0:06:03", "remaining_time": "0:55:50", "throughput": 2758.07, "total_tokens": 1001472} {"current_steps": 3735, "total_steps": 38150, "loss": 0.5067, "lr": 4.8938401048492794e-05, "epoch": 0.9790301441677588, "percentage": 9.79, "elapsed_time": "0:06:03", "remaining_time": "0:55:49", "throughput": 2757.99, "total_tokens": 1002688} {"current_steps": 3740, "total_steps": 38150, "loss": 0.5911, "lr": 4.900393184796855e-05, "epoch": 0.9803407601572739, "percentage": 9.8, "elapsed_time": "0:06:04", "remaining_time": "0:55:49", "throughput": 2758.23, "total_tokens": 1004000} {"current_steps": 3745, "total_steps": 38150, "loss": 0.5997, "lr": 4.90694626474443e-05, "epoch": 0.981651376146789, "percentage": 9.82, "elapsed_time": "0:06:04", "remaining_time": "0:55:48", "throughput": 2759.05, "total_tokens": 1005744} {"current_steps": 3750, "total_steps": 38150, "loss": 0.5351, "lr": 4.913499344692005e-05, "epoch": 0.9829619921363041, "percentage": 9.83, "elapsed_time": "0:06:05", "remaining_time": "0:55:48", "throughput": 2759.82, "total_tokens": 1007344} {"current_steps": 3755, "total_steps": 38150, "loss": 0.3958, "lr": 4.920052424639581e-05, "epoch": 0.9842726081258192, "percentage": 9.84, "elapsed_time": "0:06:05", "remaining_time": "0:55:47", "throughput": 2760.11, "total_tokens": 1008736} {"current_steps": 3760, "total_steps": 38150, "loss": 0.3917, "lr": 4.926605504587156e-05, "epoch": 0.9855832241153342, "percentage": 9.86, "elapsed_time": "0:06:05", "remaining_time": "0:55:46", "throughput": 2759.83, "total_tokens": 1009808} {"current_steps": 3765, "total_steps": 38150, "loss": 0.4175, "lr": 4.933158584534732e-05, "epoch": 0.9868938401048493, "percentage": 9.87, "elapsed_time": "0:06:06", "remaining_time": "0:55:45", "throughput": 2759.09, "total_tokens": 1010688} {"current_steps": 3770, "total_steps": 38150, "loss": 0.5057, "lr": 4.9397116644823075e-05, "epoch": 0.9882044560943644, "percentage": 9.88, "elapsed_time": "0:06:06", "remaining_time": "0:55:45", "throughput": 2759.74, "total_tokens": 1012320} {"current_steps": 3775, "total_steps": 38150, "loss": 0.3895, "lr": 4.946264744429882e-05, "epoch": 0.9895150720838795, "percentage": 9.9, "elapsed_time": "0:06:07", "remaining_time": "0:55:44", "throughput": 2759.35, "total_tokens": 1013328} {"current_steps": 3780, "total_steps": 38150, "loss": 0.4538, "lr": 4.9528178243774576e-05, "epoch": 0.9908256880733946, "percentage": 9.91, "elapsed_time": "0:06:07", "remaining_time": "0:55:43", "throughput": 2759.91, "total_tokens": 1014912} {"current_steps": 3785, "total_steps": 38150, "loss": 0.4071, "lr": 4.959370904325033e-05, "epoch": 0.9921363040629095, "percentage": 9.92, "elapsed_time": "0:06:08", "remaining_time": "0:55:42", "throughput": 2760.3, "total_tokens": 1016336} {"current_steps": 3790, "total_steps": 38150, "loss": 0.6299, "lr": 4.9659239842726083e-05, "epoch": 0.9934469200524246, "percentage": 9.93, "elapsed_time": "0:06:08", "remaining_time": "0:55:42", "throughput": 2760.37, "total_tokens": 1017568} {"current_steps": 3795, "total_steps": 38150, "loss": 0.3962, "lr": 4.972477064220184e-05, "epoch": 0.9947575360419397, "percentage": 9.95, "elapsed_time": "0:06:09", "remaining_time": "0:55:40", "throughput": 2760.35, "total_tokens": 1018736} {"current_steps": 3800, "total_steps": 38150, "loss": 0.3867, "lr": 4.979030144167759e-05, "epoch": 0.9960681520314548, "percentage": 9.96, "elapsed_time": "0:06:09", "remaining_time": "0:55:39", "throughput": 2759.9, "total_tokens": 1019744} {"current_steps": 3805, "total_steps": 38150, "loss": 0.6028, "lr": 4.985583224115334e-05, "epoch": 0.9973787680209698, "percentage": 9.97, "elapsed_time": "0:06:09", "remaining_time": "0:55:38", "throughput": 2759.73, "total_tokens": 1020880} {"current_steps": 3810, "total_steps": 38150, "loss": 0.6953, "lr": 4.99213630406291e-05, "epoch": 0.9986893840104849, "percentage": 9.99, "elapsed_time": "0:06:10", "remaining_time": "0:55:38", "throughput": 2760.37, "total_tokens": 1022400} {"current_steps": 3815, "total_steps": 38150, "loss": 0.5661, "lr": 4.9986893840104856e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:06:10", "remaining_time": "0:55:38", "throughput": 2759.72, "total_tokens": 1023568} {"current_steps": 3816, "total_steps": 38150, "eval_loss": 0.6061103343963623, "epoch": 1.000262123197903, "percentage": 10.0, "elapsed_time": "0:06:28", "remaining_time": "0:58:11", "throughput": 2638.5, "total_tokens": 1023840} {"current_steps": 3820, "total_steps": 38150, "loss": 0.4425, "lr": 4.9999998325613814e-05, "epoch": 1.001310615989515, "percentage": 10.01, "elapsed_time": "0:06:30", "remaining_time": "0:58:25", "throughput": 2626.94, "total_tokens": 1024656} {"current_steps": 3825, "total_steps": 38150, "loss": 0.5058, "lr": 4.999999152342031e-05, "epoch": 1.0026212319790302, "percentage": 10.03, "elapsed_time": "0:06:30", "remaining_time": "0:58:24", "throughput": 2627.0, "total_tokens": 1025904} {"current_steps": 3830, "total_steps": 38150, "loss": 0.4553, "lr": 4.999997948877178e-05, "epoch": 1.0039318479685453, "percentage": 10.04, "elapsed_time": "0:06:30", "remaining_time": "0:58:23", "throughput": 2626.46, "total_tokens": 1026816} {"current_steps": 3835, "total_steps": 38150, "loss": 0.5867, "lr": 4.9999962221670737e-05, "epoch": 1.0052424639580604, "percentage": 10.05, "elapsed_time": "0:06:31", "remaining_time": "0:58:22", "throughput": 2626.71, "total_tokens": 1028176} {"current_steps": 3840, "total_steps": 38150, "loss": 0.4607, "lr": 4.9999939722120804e-05, "epoch": 1.0065530799475753, "percentage": 10.07, "elapsed_time": "0:06:31", "remaining_time": "0:58:21", "throughput": 2626.33, "total_tokens": 1029232} {"current_steps": 3845, "total_steps": 38150, "loss": 0.4068, "lr": 4.9999911990126674e-05, "epoch": 1.0078636959370904, "percentage": 10.08, "elapsed_time": "0:06:32", "remaining_time": "0:58:20", "throughput": 2626.51, "total_tokens": 1030512} {"current_steps": 3850, "total_steps": 38150, "loss": 0.3592, "lr": 4.999987902569416e-05, "epoch": 1.0091743119266054, "percentage": 10.09, "elapsed_time": "0:06:32", "remaining_time": "0:58:19", "throughput": 2626.17, "total_tokens": 1031488} {"current_steps": 3855, "total_steps": 38150, "loss": 0.3932, "lr": 4.9999840828830167e-05, "epoch": 1.0104849279161205, "percentage": 10.1, "elapsed_time": "0:06:33", "remaining_time": "0:58:18", "throughput": 2626.98, "total_tokens": 1033152} {"current_steps": 3860, "total_steps": 38150, "loss": 0.4552, "lr": 4.999979739954269e-05, "epoch": 1.0117955439056356, "percentage": 10.12, "elapsed_time": "0:06:33", "remaining_time": "0:58:17", "throughput": 2627.61, "total_tokens": 1034624} {"current_steps": 3865, "total_steps": 38150, "loss": 0.4133, "lr": 4.999974873784081e-05, "epoch": 1.0131061598951507, "percentage": 10.13, "elapsed_time": "0:06:34", "remaining_time": "0:58:16", "throughput": 2627.23, "total_tokens": 1035584} {"current_steps": 3870, "total_steps": 38150, "loss": 0.477, "lr": 4.9999694843734715e-05, "epoch": 1.0144167758846658, "percentage": 10.14, "elapsed_time": "0:06:34", "remaining_time": "0:58:15", "throughput": 2627.71, "total_tokens": 1036960} {"current_steps": 3875, "total_steps": 38150, "loss": 0.5576, "lr": 4.999963571723568e-05, "epoch": 1.015727391874181, "percentage": 10.16, "elapsed_time": "0:06:35", "remaining_time": "0:58:15", "throughput": 2628.65, "total_tokens": 1038720} {"current_steps": 3880, "total_steps": 38150, "loss": 0.4132, "lr": 4.9999571358356095e-05, "epoch": 1.017038007863696, "percentage": 10.17, "elapsed_time": "0:06:35", "remaining_time": "0:58:14", "throughput": 2629.52, "total_tokens": 1040400} {"current_steps": 3885, "total_steps": 38150, "loss": 0.3842, "lr": 4.9999501767109416e-05, "epoch": 1.018348623853211, "percentage": 10.18, "elapsed_time": "0:06:36", "remaining_time": "0:58:14", "throughput": 2630.69, "total_tokens": 1042304} {"current_steps": 3890, "total_steps": 38150, "loss": 0.571, "lr": 4.999942694351021e-05, "epoch": 1.019659239842726, "percentage": 10.2, "elapsed_time": "0:06:36", "remaining_time": "0:58:13", "throughput": 2631.16, "total_tokens": 1043728} {"current_steps": 3895, "total_steps": 38150, "loss": 0.4474, "lr": 4.9999346887574146e-05, "epoch": 1.020969855832241, "percentage": 10.21, "elapsed_time": "0:06:37", "remaining_time": "0:58:12", "throughput": 2630.92, "total_tokens": 1044752} {"current_steps": 3900, "total_steps": 38150, "loss": 0.5764, "lr": 4.999926159931797e-05, "epoch": 1.0222804718217562, "percentage": 10.22, "elapsed_time": "0:06:37", "remaining_time": "0:58:11", "throughput": 2631.15, "total_tokens": 1045968} {"current_steps": 3905, "total_steps": 38150, "loss": 0.5223, "lr": 4.999917107875954e-05, "epoch": 1.0235910878112713, "percentage": 10.24, "elapsed_time": "0:06:37", "remaining_time": "0:58:09", "throughput": 2630.6, "total_tokens": 1046848} {"current_steps": 3910, "total_steps": 38150, "loss": 0.5639, "lr": 4.999907532591779e-05, "epoch": 1.0249017038007864, "percentage": 10.25, "elapsed_time": "0:06:38", "remaining_time": "0:58:09", "throughput": 2630.88, "total_tokens": 1048208} {"current_steps": 3915, "total_steps": 38150, "loss": 0.3614, "lr": 4.9998974340812775e-05, "epoch": 1.0262123197903015, "percentage": 10.26, "elapsed_time": "0:06:38", "remaining_time": "0:58:08", "throughput": 2631.46, "total_tokens": 1049744} {"current_steps": 3920, "total_steps": 38150, "loss": 0.5128, "lr": 4.999886812346563e-05, "epoch": 1.0275229357798166, "percentage": 10.28, "elapsed_time": "0:06:39", "remaining_time": "0:58:07", "throughput": 2631.39, "total_tokens": 1050816} {"current_steps": 3925, "total_steps": 38150, "loss": 0.4542, "lr": 4.999875667389858e-05, "epoch": 1.0288335517693317, "percentage": 10.29, "elapsed_time": "0:06:39", "remaining_time": "0:58:05", "throughput": 2631.26, "total_tokens": 1051888} {"current_steps": 3930, "total_steps": 38150, "loss": 0.2777, "lr": 4.999863999213495e-05, "epoch": 1.0301441677588468, "percentage": 10.3, "elapsed_time": "0:06:40", "remaining_time": "0:58:04", "throughput": 2631.19, "total_tokens": 1052960} {"current_steps": 3935, "total_steps": 38150, "loss": 0.4618, "lr": 4.999851807819916e-05, "epoch": 1.0314547837483616, "percentage": 10.31, "elapsed_time": "0:06:40", "remaining_time": "0:58:04", "throughput": 2631.94, "total_tokens": 1054592} {"current_steps": 3940, "total_steps": 38150, "loss": 0.4172, "lr": 4.9998390932116734e-05, "epoch": 1.0327653997378767, "percentage": 10.33, "elapsed_time": "0:06:41", "remaining_time": "0:58:03", "throughput": 2632.51, "total_tokens": 1056080} {"current_steps": 3945, "total_steps": 38150, "loss": 0.464, "lr": 4.9998258553914286e-05, "epoch": 1.0340760157273918, "percentage": 10.34, "elapsed_time": "0:06:41", "remaining_time": "0:58:02", "throughput": 2633.06, "total_tokens": 1057520} {"current_steps": 3950, "total_steps": 38150, "loss": 0.6422, "lr": 4.999812094361951e-05, "epoch": 1.035386631716907, "percentage": 10.35, "elapsed_time": "0:06:42", "remaining_time": "0:58:01", "throughput": 2633.44, "total_tokens": 1058928} {"current_steps": 3955, "total_steps": 38150, "loss": 0.2569, "lr": 4.9997978101261215e-05, "epoch": 1.036697247706422, "percentage": 10.37, "elapsed_time": "0:06:42", "remaining_time": "0:58:00", "throughput": 2633.93, "total_tokens": 1060400} {"current_steps": 3960, "total_steps": 38150, "loss": 0.5309, "lr": 4.9997830026869294e-05, "epoch": 1.0380078636959371, "percentage": 10.38, "elapsed_time": "0:06:43", "remaining_time": "0:57:59", "throughput": 2634.53, "total_tokens": 1061824} {"current_steps": 3965, "total_steps": 38150, "loss": 0.7101, "lr": 4.999767672047474e-05, "epoch": 1.0393184796854522, "percentage": 10.39, "elapsed_time": "0:06:43", "remaining_time": "0:57:59", "throughput": 2635.6, "total_tokens": 1063584} {"current_steps": 3970, "total_steps": 38150, "loss": 0.5739, "lr": 4.999751818210965e-05, "epoch": 1.0406290956749673, "percentage": 10.41, "elapsed_time": "0:06:44", "remaining_time": "0:57:58", "throughput": 2635.44, "total_tokens": 1064736} {"current_steps": 3975, "total_steps": 38150, "loss": 0.501, "lr": 4.999735441180718e-05, "epoch": 1.0419397116644824, "percentage": 10.42, "elapsed_time": "0:06:44", "remaining_time": "0:57:57", "throughput": 2635.16, "total_tokens": 1065744} {"current_steps": 3980, "total_steps": 38150, "loss": 0.5147, "lr": 4.999718540960164e-05, "epoch": 1.0432503276539973, "percentage": 10.43, "elapsed_time": "0:06:45", "remaining_time": "0:57:58", "throughput": 2636.93, "total_tokens": 1068432} {"current_steps": 3985, "total_steps": 38150, "loss": 0.5059, "lr": 4.999701117552839e-05, "epoch": 1.0445609436435124, "percentage": 10.45, "elapsed_time": "0:06:45", "remaining_time": "0:57:57", "throughput": 2637.03, "total_tokens": 1069712} {"current_steps": 3990, "total_steps": 38150, "loss": 0.3664, "lr": 4.999683170962388e-05, "epoch": 1.0458715596330275, "percentage": 10.46, "elapsed_time": "0:06:46", "remaining_time": "0:57:57", "throughput": 2637.89, "total_tokens": 1071328} {"current_steps": 3995, "total_steps": 38150, "loss": 0.7255, "lr": 4.9996647011925685e-05, "epoch": 1.0471821756225426, "percentage": 10.47, "elapsed_time": "0:06:46", "remaining_time": "0:57:55", "throughput": 2637.55, "total_tokens": 1072288} {"current_steps": 4000, "total_steps": 38150, "loss": 0.8107, "lr": 4.9996457082472465e-05, "epoch": 1.0484927916120577, "percentage": 10.48, "elapsed_time": "0:06:47", "remaining_time": "0:57:54", "throughput": 2638.37, "total_tokens": 1073872} {"current_steps": 4005, "total_steps": 38150, "loss": 0.3473, "lr": 4.999626192130397e-05, "epoch": 1.0498034076015728, "percentage": 10.5, "elapsed_time": "0:06:47", "remaining_time": "0:57:54", "throughput": 2639.24, "total_tokens": 1075728} {"current_steps": 4010, "total_steps": 38150, "loss": 0.3985, "lr": 4.999606152846104e-05, "epoch": 1.0511140235910879, "percentage": 10.51, "elapsed_time": "0:06:48", "remaining_time": "0:57:53", "throughput": 2639.23, "total_tokens": 1076864} {"current_steps": 4015, "total_steps": 38150, "loss": 0.3926, "lr": 4.9995855903985624e-05, "epoch": 1.052424639580603, "percentage": 10.52, "elapsed_time": "0:06:48", "remaining_time": "0:57:52", "throughput": 2639.66, "total_tokens": 1078192} {"current_steps": 4020, "total_steps": 38150, "loss": 0.5633, "lr": 4.9995645047920756e-05, "epoch": 1.053735255570118, "percentage": 10.54, "elapsed_time": "0:06:48", "remaining_time": "0:57:51", "throughput": 2639.56, "total_tokens": 1079280} {"current_steps": 4025, "total_steps": 38150, "loss": 0.4701, "lr": 4.999542896031056e-05, "epoch": 1.0550458715596331, "percentage": 10.55, "elapsed_time": "0:06:49", "remaining_time": "0:57:50", "throughput": 2639.93, "total_tokens": 1080672} {"current_steps": 4030, "total_steps": 38150, "loss": 0.4689, "lr": 4.999520764120029e-05, "epoch": 1.056356487549148, "percentage": 10.56, "elapsed_time": "0:06:49", "remaining_time": "0:57:49", "throughput": 2640.61, "total_tokens": 1082208} {"current_steps": 4035, "total_steps": 38150, "loss": 0.4146, "lr": 4.999498109063624e-05, "epoch": 1.0576671035386631, "percentage": 10.58, "elapsed_time": "0:06:50", "remaining_time": "0:57:48", "throughput": 2641.01, "total_tokens": 1083584} {"current_steps": 4040, "total_steps": 38150, "loss": 0.4572, "lr": 4.999474930866583e-05, "epoch": 1.0589777195281782, "percentage": 10.59, "elapsed_time": "0:06:50", "remaining_time": "0:57:47", "throughput": 2641.27, "total_tokens": 1084864} {"current_steps": 4045, "total_steps": 38150, "loss": 0.5478, "lr": 4.999451229533759e-05, "epoch": 1.0602883355176933, "percentage": 10.6, "elapsed_time": "0:06:51", "remaining_time": "0:57:46", "throughput": 2640.96, "total_tokens": 1085872} {"current_steps": 4050, "total_steps": 38150, "loss": 0.5742, "lr": 4.99942700507011e-05, "epoch": 1.0615989515072084, "percentage": 10.62, "elapsed_time": "0:06:51", "remaining_time": "0:57:45", "throughput": 2641.59, "total_tokens": 1087408} {"current_steps": 4055, "total_steps": 38150, "loss": 0.5452, "lr": 4.9994022574807085e-05, "epoch": 1.0629095674967235, "percentage": 10.63, "elapsed_time": "0:06:52", "remaining_time": "0:57:44", "throughput": 2641.7, "total_tokens": 1088576} {"current_steps": 4060, "total_steps": 38150, "loss": 0.3743, "lr": 4.999376986770733e-05, "epoch": 1.0642201834862386, "percentage": 10.64, "elapsed_time": "0:06:52", "remaining_time": "0:57:43", "throughput": 2642.45, "total_tokens": 1090144} {"current_steps": 4065, "total_steps": 38150, "loss": 0.6008, "lr": 4.999351192945473e-05, "epoch": 1.0655307994757537, "percentage": 10.66, "elapsed_time": "0:06:52", "remaining_time": "0:57:42", "throughput": 2642.47, "total_tokens": 1091296} {"current_steps": 4070, "total_steps": 38150, "loss": 0.3977, "lr": 4.999324876010326e-05, "epoch": 1.0668414154652686, "percentage": 10.67, "elapsed_time": "0:06:53", "remaining_time": "0:57:41", "throughput": 2642.46, "total_tokens": 1092448} {"current_steps": 4075, "total_steps": 38150, "loss": 0.3594, "lr": 4.999298035970801e-05, "epoch": 1.0681520314547837, "percentage": 10.68, "elapsed_time": "0:06:53", "remaining_time": "0:57:40", "throughput": 2642.41, "total_tokens": 1093552} {"current_steps": 4080, "total_steps": 38150, "loss": 0.4645, "lr": 4.999270672832516e-05, "epoch": 1.0694626474442988, "percentage": 10.69, "elapsed_time": "0:06:54", "remaining_time": "0:57:39", "throughput": 2642.34, "total_tokens": 1094640} {"current_steps": 4085, "total_steps": 38150, "loss": 0.556, "lr": 4.9992427866011974e-05, "epoch": 1.0707732634338138, "percentage": 10.71, "elapsed_time": "0:06:54", "remaining_time": "0:57:39", "throughput": 2642.92, "total_tokens": 1096288} {"current_steps": 4090, "total_steps": 38150, "loss": 0.4866, "lr": 4.9992143772826826e-05, "epoch": 1.072083879423329, "percentage": 10.72, "elapsed_time": "0:06:55", "remaining_time": "0:57:38", "throughput": 2643.59, "total_tokens": 1097888} {"current_steps": 4095, "total_steps": 38150, "loss": 0.5002, "lr": 4.9991854448829165e-05, "epoch": 1.073394495412844, "percentage": 10.73, "elapsed_time": "0:06:55", "remaining_time": "0:57:37", "throughput": 2643.93, "total_tokens": 1099248} {"current_steps": 4100, "total_steps": 38150, "loss": 0.7568, "lr": 4.999155989407954e-05, "epoch": 1.0747051114023591, "percentage": 10.75, "elapsed_time": "0:06:56", "remaining_time": "0:57:36", "throughput": 2644.39, "total_tokens": 1100736} {"current_steps": 4105, "total_steps": 38150, "loss": 0.4022, "lr": 4.999126010863963e-05, "epoch": 1.0760157273918742, "percentage": 10.76, "elapsed_time": "0:06:56", "remaining_time": "0:57:35", "throughput": 2645.08, "total_tokens": 1102208} {"current_steps": 4110, "total_steps": 38150, "loss": 0.4156, "lr": 4.999095509257214e-05, "epoch": 1.0773263433813893, "percentage": 10.77, "elapsed_time": "0:06:57", "remaining_time": "0:57:34", "throughput": 2644.85, "total_tokens": 1103216} {"current_steps": 4115, "total_steps": 38150, "loss": 0.3341, "lr": 4.999064484594095e-05, "epoch": 1.0786369593709044, "percentage": 10.79, "elapsed_time": "0:06:57", "remaining_time": "0:57:33", "throughput": 2644.93, "total_tokens": 1104400} {"current_steps": 4120, "total_steps": 38150, "loss": 0.7361, "lr": 4.999032936881096e-05, "epoch": 1.0799475753604193, "percentage": 10.8, "elapsed_time": "0:06:57", "remaining_time": "0:57:32", "throughput": 2644.95, "total_tokens": 1105552} {"current_steps": 4125, "total_steps": 38150, "loss": 0.7484, "lr": 4.999000866124822e-05, "epoch": 1.0812581913499344, "percentage": 10.81, "elapsed_time": "0:06:58", "remaining_time": "0:57:32", "throughput": 2646.16, "total_tokens": 1107616} {"current_steps": 4130, "total_steps": 38150, "loss": 0.5231, "lr": 4.9989682723319846e-05, "epoch": 1.0825688073394495, "percentage": 10.83, "elapsed_time": "0:06:59", "remaining_time": "0:57:31", "throughput": 2646.77, "total_tokens": 1109056} {"current_steps": 4135, "total_steps": 38150, "loss": 0.4521, "lr": 4.9989351555094055e-05, "epoch": 1.0838794233289646, "percentage": 10.84, "elapsed_time": "0:06:59", "remaining_time": "0:57:30", "throughput": 2647.16, "total_tokens": 1110400} {"current_steps": 4140, "total_steps": 38150, "loss": 0.4684, "lr": 4.998901515664017e-05, "epoch": 1.0851900393184797, "percentage": 10.85, "elapsed_time": "0:06:59", "remaining_time": "0:57:29", "throughput": 2647.16, "total_tokens": 1111536} {"current_steps": 4145, "total_steps": 38150, "loss": 0.4447, "lr": 4.998867352802858e-05, "epoch": 1.0865006553079948, "percentage": 10.87, "elapsed_time": "0:07:00", "remaining_time": "0:57:29", "throughput": 2649.02, "total_tokens": 1113936} {"current_steps": 4150, "total_steps": 38150, "loss": 0.4758, "lr": 4.9988326669330797e-05, "epoch": 1.0878112712975099, "percentage": 10.88, "elapsed_time": "0:07:00", "remaining_time": "0:57:28", "throughput": 2649.35, "total_tokens": 1115312} {"current_steps": 4155, "total_steps": 38150, "loss": 0.4573, "lr": 4.998797458061942e-05, "epoch": 1.089121887287025, "percentage": 10.89, "elapsed_time": "0:07:01", "remaining_time": "0:57:27", "throughput": 2649.27, "total_tokens": 1116384} {"current_steps": 4160, "total_steps": 38150, "loss": 0.6298, "lr": 4.998761726196814e-05, "epoch": 1.09043250327654, "percentage": 10.9, "elapsed_time": "0:07:01", "remaining_time": "0:57:26", "throughput": 2648.96, "total_tokens": 1117360} {"current_steps": 4165, "total_steps": 38150, "loss": 0.393, "lr": 4.9987254713451754e-05, "epoch": 1.091743119266055, "percentage": 10.92, "elapsed_time": "0:07:02", "remaining_time": "0:57:25", "throughput": 2649.12, "total_tokens": 1118544} {"current_steps": 4170, "total_steps": 38150, "loss": 0.585, "lr": 4.998688693514612e-05, "epoch": 1.09305373525557, "percentage": 10.93, "elapsed_time": "0:07:02", "remaining_time": "0:57:24", "throughput": 2649.39, "total_tokens": 1119824} {"current_steps": 4175, "total_steps": 38150, "loss": 0.5521, "lr": 4.998651392712823e-05, "epoch": 1.0943643512450851, "percentage": 10.94, "elapsed_time": "0:07:03", "remaining_time": "0:57:23", "throughput": 2649.8, "total_tokens": 1121264} {"current_steps": 4180, "total_steps": 38150, "loss": 0.3416, "lr": 4.998613568947614e-05, "epoch": 1.0956749672346002, "percentage": 10.96, "elapsed_time": "0:07:03", "remaining_time": "0:57:22", "throughput": 2650.16, "total_tokens": 1122560} {"current_steps": 4185, "total_steps": 38150, "loss": 0.477, "lr": 4.998575222226903e-05, "epoch": 1.0969855832241153, "percentage": 10.97, "elapsed_time": "0:07:04", "remaining_time": "0:57:21", "throughput": 2650.54, "total_tokens": 1123920} {"current_steps": 4190, "total_steps": 38150, "loss": 0.3895, "lr": 4.9985363525587145e-05, "epoch": 1.0982961992136304, "percentage": 10.98, "elapsed_time": "0:07:04", "remaining_time": "0:57:20", "throughput": 2650.98, "total_tokens": 1125280} {"current_steps": 4195, "total_steps": 38150, "loss": 0.3661, "lr": 4.998496959951185e-05, "epoch": 1.0996068152031455, "percentage": 11.0, "elapsed_time": "0:07:05", "remaining_time": "0:57:20", "throughput": 2651.78, "total_tokens": 1127056} {"current_steps": 4200, "total_steps": 38150, "loss": 0.6114, "lr": 4.998457044412559e-05, "epoch": 1.1009174311926606, "percentage": 11.01, "elapsed_time": "0:07:05", "remaining_time": "0:57:20", "throughput": 2652.25, "total_tokens": 1128720} {"current_steps": 4205, "total_steps": 38150, "loss": 0.3396, "lr": 4.998416605951191e-05, "epoch": 1.1022280471821757, "percentage": 11.02, "elapsed_time": "0:07:06", "remaining_time": "0:57:19", "throughput": 2652.31, "total_tokens": 1129968} {"current_steps": 4210, "total_steps": 38150, "loss": 0.4634, "lr": 4.998375644575543e-05, "epoch": 1.1035386631716908, "percentage": 11.04, "elapsed_time": "0:07:06", "remaining_time": "0:57:18", "throughput": 2652.64, "total_tokens": 1131408} {"current_steps": 4215, "total_steps": 38150, "loss": 0.4183, "lr": 4.99833416029419e-05, "epoch": 1.1048492791612057, "percentage": 11.05, "elapsed_time": "0:07:06", "remaining_time": "0:57:17", "throughput": 2652.32, "total_tokens": 1132400} {"current_steps": 4220, "total_steps": 38150, "loss": 0.5609, "lr": 4.998292153115814e-05, "epoch": 1.1061598951507208, "percentage": 11.06, "elapsed_time": "0:07:07", "remaining_time": "0:57:16", "throughput": 2652.7, "total_tokens": 1133712} {"current_steps": 4225, "total_steps": 38150, "loss": 0.5013, "lr": 4.9982496230492085e-05, "epoch": 1.1074705111402359, "percentage": 11.07, "elapsed_time": "0:07:07", "remaining_time": "0:57:15", "throughput": 2653.28, "total_tokens": 1135232} {"current_steps": 4230, "total_steps": 38150, "loss": 0.6096, "lr": 4.998206570103271e-05, "epoch": 1.108781127129751, "percentage": 11.09, "elapsed_time": "0:07:08", "remaining_time": "0:57:14", "throughput": 2653.16, "total_tokens": 1136288} {"current_steps": 4235, "total_steps": 38150, "loss": 0.4467, "lr": 4.998162994287017e-05, "epoch": 1.110091743119266, "percentage": 11.1, "elapsed_time": "0:07:08", "remaining_time": "0:57:13", "throughput": 2653.45, "total_tokens": 1137584} {"current_steps": 4240, "total_steps": 38150, "loss": 0.4461, "lr": 4.998118895609564e-05, "epoch": 1.1114023591087812, "percentage": 11.11, "elapsed_time": "0:07:09", "remaining_time": "0:57:12", "throughput": 2654.47, "total_tokens": 1139408} {"current_steps": 4245, "total_steps": 38150, "loss": 0.6515, "lr": 4.9980742740801425e-05, "epoch": 1.1127129750982963, "percentage": 11.13, "elapsed_time": "0:07:09", "remaining_time": "0:57:11", "throughput": 2654.25, "total_tokens": 1140448} {"current_steps": 4250, "total_steps": 38150, "loss": 0.4232, "lr": 4.998029129708092e-05, "epoch": 1.1140235910878113, "percentage": 11.14, "elapsed_time": "0:07:10", "remaining_time": "0:57:11", "throughput": 2654.8, "total_tokens": 1142000} {"current_steps": 4255, "total_steps": 38150, "loss": 0.4713, "lr": 4.997983462502861e-05, "epoch": 1.1153342070773264, "percentage": 11.15, "elapsed_time": "0:07:10", "remaining_time": "0:57:10", "throughput": 2655.42, "total_tokens": 1143568} {"current_steps": 4260, "total_steps": 38150, "loss": 0.3882, "lr": 4.997937272474007e-05, "epoch": 1.1166448230668413, "percentage": 11.17, "elapsed_time": "0:07:11", "remaining_time": "0:57:09", "throughput": 2655.44, "total_tokens": 1144800} {"current_steps": 4265, "total_steps": 38150, "loss": 0.3961, "lr": 4.9978905596311985e-05, "epoch": 1.1179554390563564, "percentage": 11.18, "elapsed_time": "0:07:11", "remaining_time": "0:57:08", "throughput": 2655.49, "total_tokens": 1146080} {"current_steps": 4270, "total_steps": 38150, "loss": 0.4202, "lr": 4.9978433239842115e-05, "epoch": 1.1192660550458715, "percentage": 11.19, "elapsed_time": "0:07:12", "remaining_time": "0:57:07", "throughput": 2656.04, "total_tokens": 1147488} {"current_steps": 4275, "total_steps": 38150, "loss": 0.8581, "lr": 4.997795565542933e-05, "epoch": 1.1205766710353866, "percentage": 11.21, "elapsed_time": "0:07:12", "remaining_time": "0:57:06", "throughput": 2655.46, "total_tokens": 1148368} {"current_steps": 4280, "total_steps": 38150, "loss": 0.5372, "lr": 4.997747284317358e-05, "epoch": 1.1218872870249017, "percentage": 11.22, "elapsed_time": "0:07:12", "remaining_time": "0:57:06", "throughput": 2655.78, "total_tokens": 1149808} {"current_steps": 4285, "total_steps": 38150, "loss": 0.587, "lr": 4.997698480317593e-05, "epoch": 1.1231979030144168, "percentage": 11.23, "elapsed_time": "0:07:13", "remaining_time": "0:57:05", "throughput": 2656.21, "total_tokens": 1151184} {"current_steps": 4290, "total_steps": 38150, "loss": 0.528, "lr": 4.997649153553851e-05, "epoch": 1.124508519003932, "percentage": 11.25, "elapsed_time": "0:07:13", "remaining_time": "0:57:04", "throughput": 2656.0, "total_tokens": 1152288} {"current_steps": 4295, "total_steps": 38150, "loss": 0.5426, "lr": 4.9975993040364574e-05, "epoch": 1.125819134993447, "percentage": 11.26, "elapsed_time": "0:07:14", "remaining_time": "0:57:03", "throughput": 2656.26, "total_tokens": 1153648} {"current_steps": 4300, "total_steps": 38150, "loss": 0.6093, "lr": 4.9975489317758446e-05, "epoch": 1.127129750982962, "percentage": 11.27, "elapsed_time": "0:07:14", "remaining_time": "0:57:02", "throughput": 2656.22, "total_tokens": 1154864} {"current_steps": 4305, "total_steps": 38150, "loss": 0.5505, "lr": 4.9974980367825555e-05, "epoch": 1.1284403669724772, "percentage": 11.28, "elapsed_time": "0:07:15", "remaining_time": "0:57:02", "throughput": 2657.12, "total_tokens": 1156608} {"current_steps": 4310, "total_steps": 38150, "loss": 0.4126, "lr": 4.997446619067243e-05, "epoch": 1.129750982961992, "percentage": 11.3, "elapsed_time": "0:07:15", "remaining_time": "0:57:01", "throughput": 2657.26, "total_tokens": 1157968} {"current_steps": 4315, "total_steps": 38150, "loss": 0.7822, "lr": 4.997394678640669e-05, "epoch": 1.1310615989515072, "percentage": 11.31, "elapsed_time": "0:07:16", "remaining_time": "0:57:00", "throughput": 2657.3, "total_tokens": 1159152} {"current_steps": 4320, "total_steps": 38150, "loss": 0.5023, "lr": 4.997342215513703e-05, "epoch": 1.1323722149410222, "percentage": 11.32, "elapsed_time": "0:07:16", "remaining_time": "0:56:59", "throughput": 2656.98, "total_tokens": 1160144} {"current_steps": 4325, "total_steps": 38150, "loss": 0.4647, "lr": 4.9972892296973263e-05, "epoch": 1.1336828309305373, "percentage": 11.34, "elapsed_time": "0:07:17", "remaining_time": "0:56:58", "throughput": 2656.74, "total_tokens": 1161136} {"current_steps": 4330, "total_steps": 38150, "loss": 0.5846, "lr": 4.997235721202629e-05, "epoch": 1.1349934469200524, "percentage": 11.35, "elapsed_time": "0:07:17", "remaining_time": "0:56:57", "throughput": 2656.96, "total_tokens": 1162384} {"current_steps": 4335, "total_steps": 38150, "loss": 0.4929, "lr": 4.997181690040811e-05, "epoch": 1.1363040629095675, "percentage": 11.36, "elapsed_time": "0:07:17", "remaining_time": "0:56:56", "throughput": 2657.28, "total_tokens": 1163696} {"current_steps": 4340, "total_steps": 38150, "loss": 0.5408, "lr": 4.997127136223179e-05, "epoch": 1.1376146788990826, "percentage": 11.38, "elapsed_time": "0:07:18", "remaining_time": "0:56:54", "throughput": 2657.33, "total_tokens": 1164864} {"current_steps": 4345, "total_steps": 38150, "loss": 0.382, "lr": 4.997072059761153e-05, "epoch": 1.1389252948885977, "percentage": 11.39, "elapsed_time": "0:07:18", "remaining_time": "0:56:53", "throughput": 2657.25, "total_tokens": 1165968} {"current_steps": 4350, "total_steps": 38150, "loss": 0.5557, "lr": 4.997016460666258e-05, "epoch": 1.1402359108781126, "percentage": 11.4, "elapsed_time": "0:07:19", "remaining_time": "0:56:53", "throughput": 2657.88, "total_tokens": 1167488} {"current_steps": 4355, "total_steps": 38150, "loss": 0.7966, "lr": 4.996960338950134e-05, "epoch": 1.1415465268676277, "percentage": 11.42, "elapsed_time": "0:07:19", "remaining_time": "0:56:52", "throughput": 2658.52, "total_tokens": 1169024} {"current_steps": 4360, "total_steps": 38150, "loss": 0.3896, "lr": 4.996903694624525e-05, "epoch": 1.1428571428571428, "percentage": 11.43, "elapsed_time": "0:07:20", "remaining_time": "0:56:51", "throughput": 2658.68, "total_tokens": 1170352} {"current_steps": 4365, "total_steps": 38150, "loss": 0.574, "lr": 4.996846527701287e-05, "epoch": 1.144167758846658, "percentage": 11.44, "elapsed_time": "0:07:20", "remaining_time": "0:56:50", "throughput": 2659.0, "total_tokens": 1171808} {"current_steps": 4370, "total_steps": 38150, "loss": 0.5173, "lr": 4.996788838192384e-05, "epoch": 1.145478374836173, "percentage": 11.45, "elapsed_time": "0:07:21", "remaining_time": "0:56:50", "throughput": 2659.14, "total_tokens": 1173104} {"current_steps": 4375, "total_steps": 38150, "loss": 0.5372, "lr": 4.9967306261098924e-05, "epoch": 1.146788990825688, "percentage": 11.47, "elapsed_time": "0:07:21", "remaining_time": "0:56:49", "throughput": 2659.07, "total_tokens": 1174208} {"current_steps": 4380, "total_steps": 38150, "loss": 0.8105, "lr": 4.996671891465994e-05, "epoch": 1.1480996068152032, "percentage": 11.48, "elapsed_time": "0:07:22", "remaining_time": "0:56:49", "throughput": 2660.52, "total_tokens": 1176528} {"current_steps": 4385, "total_steps": 38150, "loss": 0.885, "lr": 4.996612634272983e-05, "epoch": 1.1494102228047183, "percentage": 11.49, "elapsed_time": "0:07:22", "remaining_time": "0:56:48", "throughput": 2661.01, "total_tokens": 1177936} {"current_steps": 4390, "total_steps": 38150, "loss": 0.4095, "lr": 4.996552854543262e-05, "epoch": 1.1507208387942334, "percentage": 11.51, "elapsed_time": "0:07:23", "remaining_time": "0:56:47", "throughput": 2660.66, "total_tokens": 1178896} {"current_steps": 4395, "total_steps": 38150, "loss": 0.6971, "lr": 4.9964925522893416e-05, "epoch": 1.1520314547837485, "percentage": 11.52, "elapsed_time": "0:07:23", "remaining_time": "0:56:46", "throughput": 2660.9, "total_tokens": 1180160} {"current_steps": 4400, "total_steps": 38150, "loss": 0.3507, "lr": 4.9964317275238435e-05, "epoch": 1.1533420707732633, "percentage": 11.53, "elapsed_time": "0:07:23", "remaining_time": "0:56:45", "throughput": 2661.42, "total_tokens": 1181648} {"current_steps": 4405, "total_steps": 38150, "loss": 0.9921, "lr": 4.996370380259499e-05, "epoch": 1.1546526867627784, "percentage": 11.55, "elapsed_time": "0:07:24", "remaining_time": "0:56:44", "throughput": 2661.43, "total_tokens": 1182896} {"current_steps": 4410, "total_steps": 38150, "loss": 0.6759, "lr": 4.996308510509147e-05, "epoch": 1.1559633027522935, "percentage": 11.56, "elapsed_time": "0:07:24", "remaining_time": "0:56:43", "throughput": 2661.57, "total_tokens": 1184112} {"current_steps": 4415, "total_steps": 38150, "loss": 0.3336, "lr": 4.9962461182857366e-05, "epoch": 1.1572739187418086, "percentage": 11.57, "elapsed_time": "0:07:25", "remaining_time": "0:56:42", "throughput": 2661.71, "total_tokens": 1185312} {"current_steps": 4420, "total_steps": 38150, "loss": 0.4073, "lr": 4.9961832036023275e-05, "epoch": 1.1585845347313237, "percentage": 11.59, "elapsed_time": "0:07:25", "remaining_time": "0:56:41", "throughput": 2661.47, "total_tokens": 1186336} {"current_steps": 4425, "total_steps": 38150, "loss": 0.6473, "lr": 4.996119766472087e-05, "epoch": 1.1598951507208388, "percentage": 11.6, "elapsed_time": "0:07:26", "remaining_time": "0:56:40", "throughput": 2662.02, "total_tokens": 1187776} {"current_steps": 4430, "total_steps": 38150, "loss": 0.4608, "lr": 4.996055806908292e-05, "epoch": 1.161205766710354, "percentage": 11.61, "elapsed_time": "0:07:26", "remaining_time": "0:56:39", "throughput": 2662.14, "total_tokens": 1189040} {"current_steps": 4435, "total_steps": 38150, "loss": 0.4416, "lr": 4.99599132492433e-05, "epoch": 1.162516382699869, "percentage": 11.63, "elapsed_time": "0:07:27", "remaining_time": "0:56:38", "throughput": 2662.18, "total_tokens": 1190272} {"current_steps": 4440, "total_steps": 38150, "loss": 0.5059, "lr": 4.995926320533695e-05, "epoch": 1.163826998689384, "percentage": 11.64, "elapsed_time": "0:07:27", "remaining_time": "0:56:37", "throughput": 2662.32, "total_tokens": 1191472} {"current_steps": 4445, "total_steps": 38150, "loss": 0.4633, "lr": 4.995860793749995e-05, "epoch": 1.165137614678899, "percentage": 11.65, "elapsed_time": "0:07:27", "remaining_time": "0:56:36", "throughput": 2662.75, "total_tokens": 1192832} {"current_steps": 4450, "total_steps": 38150, "loss": 0.5792, "lr": 4.995794744586942e-05, "epoch": 1.166448230668414, "percentage": 11.66, "elapsed_time": "0:07:28", "remaining_time": "0:56:36", "throughput": 2663.16, "total_tokens": 1194288} {"current_steps": 4455, "total_steps": 38150, "loss": 0.52, "lr": 4.9957281730583635e-05, "epoch": 1.1677588466579292, "percentage": 11.68, "elapsed_time": "0:07:28", "remaining_time": "0:56:35", "throughput": 2663.08, "total_tokens": 1195392} {"current_steps": 4460, "total_steps": 38150, "loss": 0.489, "lr": 4.9956610791781885e-05, "epoch": 1.1690694626474443, "percentage": 11.69, "elapsed_time": "0:07:29", "remaining_time": "0:56:34", "throughput": 2663.63, "total_tokens": 1196880} {"current_steps": 4465, "total_steps": 38150, "loss": 0.5309, "lr": 4.995593462960464e-05, "epoch": 1.1703800786369594, "percentage": 11.7, "elapsed_time": "0:07:29", "remaining_time": "0:56:33", "throughput": 2663.66, "total_tokens": 1198064} {"current_steps": 4470, "total_steps": 38150, "loss": 0.5672, "lr": 4.9955253244193375e-05, "epoch": 1.1716906946264745, "percentage": 11.72, "elapsed_time": "0:07:30", "remaining_time": "0:56:32", "throughput": 2663.51, "total_tokens": 1199152} {"current_steps": 4475, "total_steps": 38150, "loss": 0.5102, "lr": 4.9954566635690744e-05, "epoch": 1.1730013106159896, "percentage": 11.73, "elapsed_time": "0:07:30", "remaining_time": "0:56:31", "throughput": 2663.43, "total_tokens": 1200256} {"current_steps": 4480, "total_steps": 38150, "loss": 0.5985, "lr": 4.995387480424043e-05, "epoch": 1.1743119266055047, "percentage": 11.74, "elapsed_time": "0:07:31", "remaining_time": "0:56:30", "throughput": 2664.18, "total_tokens": 1201936} {"current_steps": 4485, "total_steps": 38150, "loss": 0.4225, "lr": 4.995317774998723e-05, "epoch": 1.1756225425950197, "percentage": 11.76, "elapsed_time": "0:07:31", "remaining_time": "0:56:32", "throughput": 2666.21, "total_tokens": 1205088} {"current_steps": 4490, "total_steps": 38150, "loss": 0.4093, "lr": 4.995247547307704e-05, "epoch": 1.1769331585845348, "percentage": 11.77, "elapsed_time": "0:07:32", "remaining_time": "0:56:31", "throughput": 2666.16, "total_tokens": 1206176} {"current_steps": 4495, "total_steps": 38150, "loss": 0.4584, "lr": 4.995176797365686e-05, "epoch": 1.1782437745740497, "percentage": 11.78, "elapsed_time": "0:07:32", "remaining_time": "0:56:30", "throughput": 2666.5, "total_tokens": 1207568} {"current_steps": 4500, "total_steps": 38150, "loss": 0.3384, "lr": 4.995105525187475e-05, "epoch": 1.1795543905635648, "percentage": 11.8, "elapsed_time": "0:07:33", "remaining_time": "0:56:29", "throughput": 2666.51, "total_tokens": 1208816} {"current_steps": 4505, "total_steps": 38150, "loss": 0.6038, "lr": 4.9950337307879884e-05, "epoch": 1.18086500655308, "percentage": 11.81, "elapsed_time": "0:07:33", "remaining_time": "0:56:28", "throughput": 2666.47, "total_tokens": 1209952} {"current_steps": 4510, "total_steps": 38150, "loss": 0.3846, "lr": 4.994961414182254e-05, "epoch": 1.182175622542595, "percentage": 11.82, "elapsed_time": "0:07:34", "remaining_time": "0:56:27", "throughput": 2667.07, "total_tokens": 1211408} {"current_steps": 4515, "total_steps": 38150, "loss": 0.3498, "lr": 4.9948885753854056e-05, "epoch": 1.18348623853211, "percentage": 11.83, "elapsed_time": "0:07:34", "remaining_time": "0:56:26", "throughput": 2667.57, "total_tokens": 1212816} {"current_steps": 4520, "total_steps": 38150, "loss": 0.5078, "lr": 4.99481521441269e-05, "epoch": 1.1847968545216252, "percentage": 11.85, "elapsed_time": "0:07:35", "remaining_time": "0:56:26", "throughput": 2667.58, "total_tokens": 1214048} {"current_steps": 4525, "total_steps": 38150, "loss": 0.5216, "lr": 4.99474133127946e-05, "epoch": 1.1861074705111403, "percentage": 11.86, "elapsed_time": "0:07:35", "remaining_time": "0:56:25", "throughput": 2667.87, "total_tokens": 1215360} {"current_steps": 4530, "total_steps": 38150, "loss": 0.8024, "lr": 4.99466692600118e-05, "epoch": 1.1874180865006554, "percentage": 11.87, "elapsed_time": "0:07:35", "remaining_time": "0:56:24", "throughput": 2667.56, "total_tokens": 1216352} {"current_steps": 4535, "total_steps": 38150, "loss": 0.4992, "lr": 4.994591998593423e-05, "epoch": 1.1887287024901703, "percentage": 11.89, "elapsed_time": "0:07:36", "remaining_time": "0:56:23", "throughput": 2667.76, "total_tokens": 1217680} {"current_steps": 4540, "total_steps": 38150, "loss": 0.4291, "lr": 4.9945165490718714e-05, "epoch": 1.1900393184796854, "percentage": 11.9, "elapsed_time": "0:07:36", "remaining_time": "0:56:23", "throughput": 2668.54, "total_tokens": 1219472} {"current_steps": 4545, "total_steps": 38150, "loss": 0.4501, "lr": 4.994440577452316e-05, "epoch": 1.1913499344692005, "percentage": 11.91, "elapsed_time": "0:07:37", "remaining_time": "0:56:22", "throughput": 2669.13, "total_tokens": 1221008} {"current_steps": 4550, "total_steps": 38150, "loss": 0.6931, "lr": 4.9943640837506574e-05, "epoch": 1.1926605504587156, "percentage": 11.93, "elapsed_time": "0:07:37", "remaining_time": "0:56:21", "throughput": 2668.9, "total_tokens": 1222016} {"current_steps": 4555, "total_steps": 38150, "loss": 0.5521, "lr": 4.994287067982907e-05, "epoch": 1.1939711664482306, "percentage": 11.94, "elapsed_time": "0:07:38", "remaining_time": "0:56:20", "throughput": 2668.84, "total_tokens": 1223136} {"current_steps": 4560, "total_steps": 38150, "loss": 0.9464, "lr": 4.994209530165183e-05, "epoch": 1.1952817824377457, "percentage": 11.95, "elapsed_time": "0:07:38", "remaining_time": "0:56:19", "throughput": 2668.84, "total_tokens": 1224368} {"current_steps": 4565, "total_steps": 38150, "loss": 0.4571, "lr": 4.9941314703137134e-05, "epoch": 1.1965923984272608, "percentage": 11.97, "elapsed_time": "0:07:39", "remaining_time": "0:56:19", "throughput": 2669.84, "total_tokens": 1226448} {"current_steps": 4570, "total_steps": 38150, "loss": 0.4697, "lr": 4.994052888444837e-05, "epoch": 1.197903014416776, "percentage": 11.98, "elapsed_time": "0:07:39", "remaining_time": "0:56:18", "throughput": 2670.19, "total_tokens": 1227792} {"current_steps": 4575, "total_steps": 38150, "loss": 0.4008, "lr": 4.993973784575e-05, "epoch": 1.199213630406291, "percentage": 11.99, "elapsed_time": "0:07:40", "remaining_time": "0:56:17", "throughput": 2670.41, "total_tokens": 1229056} {"current_steps": 4580, "total_steps": 38150, "loss": 0.5003, "lr": 4.9938941587207586e-05, "epoch": 1.2005242463958061, "percentage": 12.01, "elapsed_time": "0:07:40", "remaining_time": "0:56:16", "throughput": 2670.5, "total_tokens": 1230272} {"current_steps": 4585, "total_steps": 38150, "loss": 0.7135, "lr": 4.9938140108987795e-05, "epoch": 1.2018348623853212, "percentage": 12.02, "elapsed_time": "0:07:41", "remaining_time": "0:56:15", "throughput": 2670.89, "total_tokens": 1231648} {"current_steps": 4590, "total_steps": 38150, "loss": 0.4789, "lr": 4.9937333411258366e-05, "epoch": 1.203145478374836, "percentage": 12.03, "elapsed_time": "0:07:41", "remaining_time": "0:56:14", "throughput": 2670.81, "total_tokens": 1232736} {"current_steps": 4595, "total_steps": 38150, "loss": 0.3929, "lr": 4.993652149418815e-05, "epoch": 1.2044560943643512, "percentage": 12.04, "elapsed_time": "0:07:41", "remaining_time": "0:56:13", "throughput": 2670.85, "total_tokens": 1233904} {"current_steps": 4600, "total_steps": 38150, "loss": 0.6018, "lr": 4.9935704357947065e-05, "epoch": 1.2057667103538663, "percentage": 12.06, "elapsed_time": "0:07:42", "remaining_time": "0:56:12", "throughput": 2671.16, "total_tokens": 1235232} {"current_steps": 4605, "total_steps": 38150, "loss": 0.4629, "lr": 4.9934882002706154e-05, "epoch": 1.2070773263433814, "percentage": 12.07, "elapsed_time": "0:07:42", "remaining_time": "0:56:11", "throughput": 2671.52, "total_tokens": 1236608} {"current_steps": 4610, "total_steps": 38150, "loss": 0.6699, "lr": 4.9934054428637514e-05, "epoch": 1.2083879423328965, "percentage": 12.08, "elapsed_time": "0:07:43", "remaining_time": "0:56:10", "throughput": 2671.42, "total_tokens": 1237712} {"current_steps": 4615, "total_steps": 38150, "loss": 0.5151, "lr": 4.9933221635914365e-05, "epoch": 1.2096985583224116, "percentage": 12.1, "elapsed_time": "0:07:43", "remaining_time": "0:56:10", "throughput": 2671.78, "total_tokens": 1239152} {"current_steps": 4620, "total_steps": 38150, "loss": 0.336, "lr": 4.9932383624711014e-05, "epoch": 1.2110091743119267, "percentage": 12.11, "elapsed_time": "0:07:44", "remaining_time": "0:56:09", "throughput": 2672.45, "total_tokens": 1240784} {"current_steps": 4625, "total_steps": 38150, "loss": 0.6048, "lr": 4.993154039520285e-05, "epoch": 1.2123197903014418, "percentage": 12.12, "elapsed_time": "0:07:44", "remaining_time": "0:56:09", "throughput": 2673.53, "total_tokens": 1242752} {"current_steps": 4630, "total_steps": 38150, "loss": 0.392, "lr": 4.9930691947566354e-05, "epoch": 1.2136304062909566, "percentage": 12.14, "elapsed_time": "0:07:45", "remaining_time": "0:56:08", "throughput": 2673.84, "total_tokens": 1244176} {"current_steps": 4635, "total_steps": 38150, "loss": 0.3537, "lr": 4.992983828197911e-05, "epoch": 1.2149410222804717, "percentage": 12.15, "elapsed_time": "0:07:45", "remaining_time": "0:56:07", "throughput": 2673.91, "total_tokens": 1245376} {"current_steps": 4640, "total_steps": 38150, "loss": 0.4621, "lr": 4.99289793986198e-05, "epoch": 1.2162516382699868, "percentage": 12.16, "elapsed_time": "0:07:46", "remaining_time": "0:56:06", "throughput": 2673.96, "total_tokens": 1246544} {"current_steps": 4645, "total_steps": 38150, "loss": 0.4486, "lr": 4.992811529766816e-05, "epoch": 1.217562254259502, "percentage": 12.18, "elapsed_time": "0:07:46", "remaining_time": "0:56:06", "throughput": 2674.25, "total_tokens": 1248016} {"current_steps": 4650, "total_steps": 38150, "loss": 0.5156, "lr": 4.992724597930508e-05, "epoch": 1.218872870249017, "percentage": 12.19, "elapsed_time": "0:07:47", "remaining_time": "0:56:05", "throughput": 2674.65, "total_tokens": 1249392} {"current_steps": 4655, "total_steps": 38150, "loss": 0.462, "lr": 4.9926371443712474e-05, "epoch": 1.2201834862385321, "percentage": 12.2, "elapsed_time": "0:07:47", "remaining_time": "0:56:04", "throughput": 2675.25, "total_tokens": 1250960} {"current_steps": 4660, "total_steps": 38150, "loss": 0.436, "lr": 4.9925491691073396e-05, "epoch": 1.2214941022280472, "percentage": 12.21, "elapsed_time": "0:07:48", "remaining_time": "0:56:03", "throughput": 2675.57, "total_tokens": 1252320} {"current_steps": 4665, "total_steps": 38150, "loss": 0.4713, "lr": 4.9924606721571975e-05, "epoch": 1.2228047182175623, "percentage": 12.23, "elapsed_time": "0:07:48", "remaining_time": "0:56:03", "throughput": 2676.36, "total_tokens": 1254080} {"current_steps": 4670, "total_steps": 38150, "loss": 0.6017, "lr": 4.9923716535393434e-05, "epoch": 1.2241153342070774, "percentage": 12.24, "elapsed_time": "0:07:49", "remaining_time": "0:56:02", "throughput": 2676.26, "total_tokens": 1255168} {"current_steps": 4675, "total_steps": 38150, "loss": 0.5386, "lr": 4.9922821132724086e-05, "epoch": 1.2254259501965925, "percentage": 12.25, "elapsed_time": "0:07:49", "remaining_time": "0:56:01", "throughput": 2676.6, "total_tokens": 1256528} {"current_steps": 4680, "total_steps": 38150, "loss": 0.4831, "lr": 4.992192051375134e-05, "epoch": 1.2267365661861074, "percentage": 12.27, "elapsed_time": "0:07:49", "remaining_time": "0:56:00", "throughput": 2676.79, "total_tokens": 1257808} {"current_steps": 4685, "total_steps": 38150, "loss": 0.5671, "lr": 4.992101467866369e-05, "epoch": 1.2280471821756225, "percentage": 12.28, "elapsed_time": "0:07:50", "remaining_time": "0:55:59", "throughput": 2676.81, "total_tokens": 1259040} {"current_steps": 4690, "total_steps": 38150, "loss": 0.5357, "lr": 4.9920103627650734e-05, "epoch": 1.2293577981651376, "percentage": 12.29, "elapsed_time": "0:07:50", "remaining_time": "0:55:58", "throughput": 2677.44, "total_tokens": 1260592} {"current_steps": 4695, "total_steps": 38150, "loss": 0.6257, "lr": 4.991918736090314e-05, "epoch": 1.2306684141546527, "percentage": 12.31, "elapsed_time": "0:07:51", "remaining_time": "0:55:57", "throughput": 2677.34, "total_tokens": 1261680} {"current_steps": 4700, "total_steps": 38150, "loss": 0.6308, "lr": 4.991826587861269e-05, "epoch": 1.2319790301441678, "percentage": 12.32, "elapsed_time": "0:07:51", "remaining_time": "0:55:56", "throughput": 2677.31, "total_tokens": 1262816} {"current_steps": 4705, "total_steps": 38150, "loss": 0.5734, "lr": 4.991733918097225e-05, "epoch": 1.2332896461336829, "percentage": 12.33, "elapsed_time": "0:07:52", "remaining_time": "0:55:56", "throughput": 2677.9, "total_tokens": 1264464} {"current_steps": 4710, "total_steps": 38150, "loss": 0.4635, "lr": 4.9916407268175775e-05, "epoch": 1.234600262123198, "percentage": 12.35, "elapsed_time": "0:07:52", "remaining_time": "0:55:55", "throughput": 2677.77, "total_tokens": 1265536} {"current_steps": 4715, "total_steps": 38150, "loss": 0.4616, "lr": 4.991547014041831e-05, "epoch": 1.235910878112713, "percentage": 12.36, "elapsed_time": "0:07:53", "remaining_time": "0:55:54", "throughput": 2678.34, "total_tokens": 1267104} {"current_steps": 4720, "total_steps": 38150, "loss": 0.4191, "lr": 4.9914527797895995e-05, "epoch": 1.237221494102228, "percentage": 12.37, "elapsed_time": "0:07:53", "remaining_time": "0:55:53", "throughput": 2678.21, "total_tokens": 1268256} {"current_steps": 4725, "total_steps": 38150, "loss": 0.6099, "lr": 4.9913580240806054e-05, "epoch": 1.238532110091743, "percentage": 12.39, "elapsed_time": "0:07:53", "remaining_time": "0:55:52", "throughput": 2677.81, "total_tokens": 1269184} {"current_steps": 4730, "total_steps": 38150, "loss": 0.4836, "lr": 4.991262746934682e-05, "epoch": 1.2398427260812581, "percentage": 12.4, "elapsed_time": "0:07:54", "remaining_time": "0:55:52", "throughput": 2678.45, "total_tokens": 1270768} {"current_steps": 4735, "total_steps": 38150, "loss": 0.4186, "lr": 4.991166948371771e-05, "epoch": 1.2411533420707732, "percentage": 12.41, "elapsed_time": "0:07:54", "remaining_time": "0:55:51", "throughput": 2678.93, "total_tokens": 1272336} {"current_steps": 4740, "total_steps": 38150, "loss": 0.3702, "lr": 4.991070628411921e-05, "epoch": 1.2424639580602883, "percentage": 12.42, "elapsed_time": "0:07:55", "remaining_time": "0:55:50", "throughput": 2678.82, "total_tokens": 1273520} {"current_steps": 4745, "total_steps": 38150, "loss": 0.3889, "lr": 4.9909737870752935e-05, "epoch": 1.2437745740498034, "percentage": 12.44, "elapsed_time": "0:07:55", "remaining_time": "0:55:50", "throughput": 2679.22, "total_tokens": 1274976} {"current_steps": 4750, "total_steps": 38150, "loss": 0.524, "lr": 4.990876424382156e-05, "epoch": 1.2450851900393185, "percentage": 12.45, "elapsed_time": "0:07:56", "remaining_time": "0:55:49", "throughput": 2679.17, "total_tokens": 1276096} {"current_steps": 4755, "total_steps": 38150, "loss": 0.3179, "lr": 4.9907785403528863e-05, "epoch": 1.2463958060288336, "percentage": 12.46, "elapsed_time": "0:07:56", "remaining_time": "0:55:49", "throughput": 2680.32, "total_tokens": 1278192} {"current_steps": 4760, "total_steps": 38150, "loss": 0.4082, "lr": 4.9906801350079724e-05, "epoch": 1.2477064220183487, "percentage": 12.48, "elapsed_time": "0:07:57", "remaining_time": "0:55:48", "throughput": 2680.69, "total_tokens": 1279520} {"current_steps": 4765, "total_steps": 38150, "loss": 0.5633, "lr": 4.9905812083680105e-05, "epoch": 1.2490170380078638, "percentage": 12.49, "elapsed_time": "0:07:57", "remaining_time": "0:55:47", "throughput": 2680.64, "total_tokens": 1280608} {"current_steps": 4770, "total_steps": 38150, "loss": 0.4318, "lr": 4.990481760453704e-05, "epoch": 1.2503276539973789, "percentage": 12.5, "elapsed_time": "0:07:58", "remaining_time": "0:55:46", "throughput": 2681.33, "total_tokens": 1282416} {"current_steps": 4775, "total_steps": 38150, "loss": 0.6223, "lr": 4.9903817912858684e-05, "epoch": 1.2516382699868938, "percentage": 12.52, "elapsed_time": "0:07:58", "remaining_time": "0:55:45", "throughput": 2681.12, "total_tokens": 1283456} {"current_steps": 4780, "total_steps": 38150, "loss": 0.54, "lr": 4.9902813008854274e-05, "epoch": 1.2529488859764089, "percentage": 12.53, "elapsed_time": "0:07:59", "remaining_time": "0:55:44", "throughput": 2681.15, "total_tokens": 1284624} {"current_steps": 4785, "total_steps": 38150, "loss": 0.5168, "lr": 4.990180289273413e-05, "epoch": 1.254259501965924, "percentage": 12.54, "elapsed_time": "0:07:59", "remaining_time": "0:55:44", "throughput": 2681.26, "total_tokens": 1285888} {"current_steps": 4790, "total_steps": 38150, "loss": 0.3981, "lr": 4.990078756470966e-05, "epoch": 1.255570117955439, "percentage": 12.56, "elapsed_time": "0:08:00", "remaining_time": "0:55:43", "throughput": 2681.34, "total_tokens": 1287184} {"current_steps": 4795, "total_steps": 38150, "loss": 0.498, "lr": 4.989976702499339e-05, "epoch": 1.2568807339449541, "percentage": 12.57, "elapsed_time": "0:08:00", "remaining_time": "0:55:42", "throughput": 2681.7, "total_tokens": 1288592} {"current_steps": 4800, "total_steps": 38150, "loss": 0.7359, "lr": 4.98987412737989e-05, "epoch": 1.2581913499344692, "percentage": 12.58, "elapsed_time": "0:08:00", "remaining_time": "0:55:41", "throughput": 2681.67, "total_tokens": 1289744} {"current_steps": 4805, "total_steps": 38150, "loss": 0.5692, "lr": 4.989771031134088e-05, "epoch": 1.2595019659239843, "percentage": 12.6, "elapsed_time": "0:08:01", "remaining_time": "0:55:40", "throughput": 2681.75, "total_tokens": 1290960} {"current_steps": 4810, "total_steps": 38150, "loss": 0.4865, "lr": 4.989667413783511e-05, "epoch": 1.2608125819134992, "percentage": 12.61, "elapsed_time": "0:08:01", "remaining_time": "0:55:39", "throughput": 2681.91, "total_tokens": 1292208} {"current_steps": 4815, "total_steps": 38150, "loss": 0.5459, "lr": 4.9895632753498465e-05, "epoch": 1.2621231979030143, "percentage": 12.62, "elapsed_time": "0:08:02", "remaining_time": "0:55:38", "throughput": 2682.12, "total_tokens": 1293472} {"current_steps": 4820, "total_steps": 38150, "loss": 0.3869, "lr": 4.98945861585489e-05, "epoch": 1.2634338138925294, "percentage": 12.63, "elapsed_time": "0:08:02", "remaining_time": "0:55:37", "throughput": 2682.17, "total_tokens": 1294640} {"current_steps": 4825, "total_steps": 38150, "loss": 0.5083, "lr": 4.989353435320547e-05, "epoch": 1.2647444298820445, "percentage": 12.65, "elapsed_time": "0:08:03", "remaining_time": "0:55:37", "throughput": 2682.52, "total_tokens": 1296096} {"current_steps": 4830, "total_steps": 38150, "loss": 0.544, "lr": 4.9892477337688306e-05, "epoch": 1.2660550458715596, "percentage": 12.66, "elapsed_time": "0:08:03", "remaining_time": "0:55:36", "throughput": 2682.29, "total_tokens": 1297200} {"current_steps": 4835, "total_steps": 38150, "loss": 0.3522, "lr": 4.9891415112218654e-05, "epoch": 1.2673656618610747, "percentage": 12.67, "elapsed_time": "0:08:04", "remaining_time": "0:55:35", "throughput": 2682.49, "total_tokens": 1298512} {"current_steps": 4840, "total_steps": 38150, "loss": 0.5005, "lr": 4.9890347677018826e-05, "epoch": 1.2686762778505898, "percentage": 12.69, "elapsed_time": "0:08:04", "remaining_time": "0:55:34", "throughput": 2682.41, "total_tokens": 1299616} {"current_steps": 4845, "total_steps": 38150, "loss": 0.4123, "lr": 4.9889275032312235e-05, "epoch": 1.2699868938401049, "percentage": 12.7, "elapsed_time": "0:08:04", "remaining_time": "0:55:33", "throughput": 2682.42, "total_tokens": 1300784} {"current_steps": 4850, "total_steps": 38150, "loss": 0.4747, "lr": 4.988819717832338e-05, "epoch": 1.27129750982962, "percentage": 12.71, "elapsed_time": "0:08:05", "remaining_time": "0:55:32", "throughput": 2682.94, "total_tokens": 1302304} {"current_steps": 4855, "total_steps": 38150, "loss": 0.4463, "lr": 4.988711411527786e-05, "epoch": 1.272608125819135, "percentage": 12.73, "elapsed_time": "0:08:05", "remaining_time": "0:55:32", "throughput": 2683.79, "total_tokens": 1304224} {"current_steps": 4860, "total_steps": 38150, "loss": 0.5948, "lr": 4.988602584340236e-05, "epoch": 1.2739187418086502, "percentage": 12.74, "elapsed_time": "0:08:06", "remaining_time": "0:55:31", "throughput": 2684.12, "total_tokens": 1305584} {"current_steps": 4865, "total_steps": 38150, "loss": 0.4847, "lr": 4.988493236292465e-05, "epoch": 1.2752293577981653, "percentage": 12.75, "elapsed_time": "0:08:06", "remaining_time": "0:55:31", "throughput": 2684.19, "total_tokens": 1306848} {"current_steps": 4870, "total_steps": 38150, "loss": 0.5456, "lr": 4.98838336740736e-05, "epoch": 1.2765399737876801, "percentage": 12.77, "elapsed_time": "0:08:07", "remaining_time": "0:55:30", "throughput": 2684.31, "total_tokens": 1308064} {"current_steps": 4875, "total_steps": 38150, "loss": 0.3834, "lr": 4.9882729777079154e-05, "epoch": 1.2778505897771952, "percentage": 12.78, "elapsed_time": "0:08:07", "remaining_time": "0:55:29", "throughput": 2684.19, "total_tokens": 1309152} {"current_steps": 4880, "total_steps": 38150, "loss": 0.502, "lr": 4.9881620672172355e-05, "epoch": 1.2791612057667103, "percentage": 12.79, "elapsed_time": "0:08:08", "remaining_time": "0:55:28", "throughput": 2684.31, "total_tokens": 1310352} {"current_steps": 4885, "total_steps": 38150, "loss": 0.4293, "lr": 4.988050635958535e-05, "epoch": 1.2804718217562254, "percentage": 12.8, "elapsed_time": "0:08:08", "remaining_time": "0:55:27", "throughput": 2684.13, "total_tokens": 1311408} {"current_steps": 4890, "total_steps": 38150, "loss": 0.4994, "lr": 4.987938683955135e-05, "epoch": 1.2817824377457405, "percentage": 12.82, "elapsed_time": "0:08:09", "remaining_time": "0:55:26", "throughput": 2684.18, "total_tokens": 1312656} {"current_steps": 4895, "total_steps": 38150, "loss": 0.5005, "lr": 4.987826211230467e-05, "epoch": 1.2830930537352556, "percentage": 12.83, "elapsed_time": "0:08:09", "remaining_time": "0:55:25", "throughput": 2684.59, "total_tokens": 1314096} {"current_steps": 4900, "total_steps": 38150, "loss": 0.3143, "lr": 4.987713217808072e-05, "epoch": 1.2844036697247707, "percentage": 12.84, "elapsed_time": "0:08:09", "remaining_time": "0:55:24", "throughput": 2684.49, "total_tokens": 1315168} {"current_steps": 4905, "total_steps": 38150, "loss": 0.6377, "lr": 4.987599703711599e-05, "epoch": 1.2857142857142856, "percentage": 12.86, "elapsed_time": "0:08:10", "remaining_time": "0:55:23", "throughput": 2684.71, "total_tokens": 1316592} {"current_steps": 4910, "total_steps": 38150, "loss": 0.5113, "lr": 4.9874856689648065e-05, "epoch": 1.2870249017038007, "percentage": 12.87, "elapsed_time": "0:08:10", "remaining_time": "0:55:22", "throughput": 2684.25, "total_tokens": 1317488} {"current_steps": 4915, "total_steps": 38150, "loss": 0.324, "lr": 4.9873711135915605e-05, "epoch": 1.2883355176933158, "percentage": 12.88, "elapsed_time": "0:08:11", "remaining_time": "0:55:22", "throughput": 2685.15, "total_tokens": 1319216} {"current_steps": 4920, "total_steps": 38150, "loss": 0.5463, "lr": 4.987256037615839e-05, "epoch": 1.2896461336828309, "percentage": 12.9, "elapsed_time": "0:08:11", "remaining_time": "0:55:21", "throughput": 2685.03, "total_tokens": 1320320} {"current_steps": 4925, "total_steps": 38150, "loss": 0.3903, "lr": 4.987140441061726e-05, "epoch": 1.290956749672346, "percentage": 12.91, "elapsed_time": "0:08:12", "remaining_time": "0:55:20", "throughput": 2685.29, "total_tokens": 1321664} {"current_steps": 4930, "total_steps": 38150, "loss": 0.32, "lr": 4.987024323953417e-05, "epoch": 1.292267365661861, "percentage": 12.92, "elapsed_time": "0:08:12", "remaining_time": "0:55:19", "throughput": 2685.52, "total_tokens": 1323040} {"current_steps": 4935, "total_steps": 38150, "loss": 0.3558, "lr": 4.9869076863152134e-05, "epoch": 1.2935779816513762, "percentage": 12.94, "elapsed_time": "0:08:13", "remaining_time": "0:55:18", "throughput": 2685.56, "total_tokens": 1324224} {"current_steps": 4940, "total_steps": 38150, "loss": 0.3138, "lr": 4.986790528171529e-05, "epoch": 1.2948885976408913, "percentage": 12.95, "elapsed_time": "0:08:13", "remaining_time": "0:55:18", "throughput": 2686.05, "total_tokens": 1325744} {"current_steps": 4945, "total_steps": 38150, "loss": 0.4604, "lr": 4.986672849546883e-05, "epoch": 1.2961992136304064, "percentage": 12.96, "elapsed_time": "0:08:14", "remaining_time": "0:55:17", "throughput": 2686.43, "total_tokens": 1327136} {"current_steps": 4950, "total_steps": 38150, "loss": 0.5517, "lr": 4.9865546504659063e-05, "epoch": 1.2975098296199215, "percentage": 12.98, "elapsed_time": "0:08:14", "remaining_time": "0:55:16", "throughput": 2687.43, "total_tokens": 1329040} {"current_steps": 4955, "total_steps": 38150, "loss": 0.5076, "lr": 4.986435930953338e-05, "epoch": 1.2988204456094365, "percentage": 12.99, "elapsed_time": "0:08:15", "remaining_time": "0:55:16", "throughput": 2687.81, "total_tokens": 1330512} {"current_steps": 4960, "total_steps": 38150, "loss": 0.3415, "lr": 4.986316691034026e-05, "epoch": 1.3001310615989516, "percentage": 13.0, "elapsed_time": "0:08:15", "remaining_time": "0:55:15", "throughput": 2687.32, "total_tokens": 1331408} {"current_steps": 4965, "total_steps": 38150, "loss": 0.6227, "lr": 4.986196930732926e-05, "epoch": 1.3014416775884665, "percentage": 13.01, "elapsed_time": "0:08:15", "remaining_time": "0:55:14", "throughput": 2687.23, "total_tokens": 1332512} {"current_steps": 4970, "total_steps": 38150, "loss": 0.3056, "lr": 4.986076650075104e-05, "epoch": 1.3027522935779816, "percentage": 13.03, "elapsed_time": "0:08:16", "remaining_time": "0:55:13", "throughput": 2687.64, "total_tokens": 1334048} {"current_steps": 4975, "total_steps": 38150, "loss": 0.6656, "lr": 4.985955849085735e-05, "epoch": 1.3040629095674967, "percentage": 13.04, "elapsed_time": "0:08:16", "remaining_time": "0:55:12", "throughput": 2687.58, "total_tokens": 1335168} {"current_steps": 4980, "total_steps": 38150, "loss": 0.3446, "lr": 4.9858345277901034e-05, "epoch": 1.3053735255570118, "percentage": 13.05, "elapsed_time": "0:08:17", "remaining_time": "0:55:12", "throughput": 2687.93, "total_tokens": 1336624} {"current_steps": 4985, "total_steps": 38150, "loss": 0.4584, "lr": 4.9857126862135984e-05, "epoch": 1.306684141546527, "percentage": 13.07, "elapsed_time": "0:08:17", "remaining_time": "0:55:11", "throughput": 2687.85, "total_tokens": 1337728} {"current_steps": 4990, "total_steps": 38150, "loss": 0.4533, "lr": 4.985590324381724e-05, "epoch": 1.307994757536042, "percentage": 13.08, "elapsed_time": "0:08:18", "remaining_time": "0:55:10", "throughput": 2688.3, "total_tokens": 1339136} {"current_steps": 4995, "total_steps": 38150, "loss": 0.6284, "lr": 4.98546744232009e-05, "epoch": 1.309305373525557, "percentage": 13.09, "elapsed_time": "0:08:18", "remaining_time": "0:55:09", "throughput": 2688.86, "total_tokens": 1340784} {"current_steps": 5000, "total_steps": 38150, "loss": 0.3178, "lr": 4.9853440400544136e-05, "epoch": 1.310615989515072, "percentage": 13.11, "elapsed_time": "0:08:19", "remaining_time": "0:55:09", "throughput": 2689.42, "total_tokens": 1342384} {"current_steps": 5005, "total_steps": 38150, "loss": 0.4189, "lr": 4.985220117610525e-05, "epoch": 1.311926605504587, "percentage": 13.12, "elapsed_time": "0:08:19", "remaining_time": "0:55:08", "throughput": 2689.85, "total_tokens": 1343952} {"current_steps": 5010, "total_steps": 38150, "loss": 0.3092, "lr": 4.985095675014359e-05, "epoch": 1.3132372214941022, "percentage": 13.13, "elapsed_time": "0:08:20", "remaining_time": "0:55:08", "throughput": 2690.52, "total_tokens": 1345600} {"current_steps": 5015, "total_steps": 38150, "loss": 0.5543, "lr": 4.984970712291963e-05, "epoch": 1.3145478374836173, "percentage": 13.15, "elapsed_time": "0:08:20", "remaining_time": "0:55:07", "throughput": 2691.03, "total_tokens": 1347216} {"current_steps": 5020, "total_steps": 38150, "loss": 0.4412, "lr": 4.98484522946949e-05, "epoch": 1.3158584534731324, "percentage": 13.16, "elapsed_time": "0:08:21", "remaining_time": "0:55:06", "throughput": 2691.04, "total_tokens": 1348368} {"current_steps": 5025, "total_steps": 38150, "loss": 0.4727, "lr": 4.984719226573205e-05, "epoch": 1.3171690694626474, "percentage": 13.17, "elapsed_time": "0:08:21", "remaining_time": "0:55:05", "throughput": 2691.06, "total_tokens": 1349504} {"current_steps": 5030, "total_steps": 38150, "loss": 0.534, "lr": 4.984592703629478e-05, "epoch": 1.3184796854521625, "percentage": 13.18, "elapsed_time": "0:08:21", "remaining_time": "0:55:04", "throughput": 2691.13, "total_tokens": 1350688} {"current_steps": 5035, "total_steps": 38150, "loss": 0.5981, "lr": 4.9844656606647924e-05, "epoch": 1.3197903014416776, "percentage": 13.2, "elapsed_time": "0:08:22", "remaining_time": "0:55:04", "throughput": 2691.45, "total_tokens": 1352160} {"current_steps": 5040, "total_steps": 38150, "loss": 0.3938, "lr": 4.984338097705736e-05, "epoch": 1.3211009174311927, "percentage": 13.21, "elapsed_time": "0:08:22", "remaining_time": "0:55:03", "throughput": 2691.62, "total_tokens": 1353504} {"current_steps": 5045, "total_steps": 38150, "loss": 0.4694, "lr": 4.984210014779008e-05, "epoch": 1.3224115334207078, "percentage": 13.22, "elapsed_time": "0:08:23", "remaining_time": "0:55:02", "throughput": 2692.05, "total_tokens": 1354992} {"current_steps": 5050, "total_steps": 38150, "loss": 0.5513, "lr": 4.984081411911417e-05, "epoch": 1.323722149410223, "percentage": 13.24, "elapsed_time": "0:08:23", "remaining_time": "0:55:01", "throughput": 2691.76, "total_tokens": 1355984} {"current_steps": 5055, "total_steps": 38150, "loss": 0.4361, "lr": 4.9839522891298784e-05, "epoch": 1.3250327653997378, "percentage": 13.25, "elapsed_time": "0:08:24", "remaining_time": "0:55:01", "throughput": 2692.03, "total_tokens": 1357360} {"current_steps": 5060, "total_steps": 38150, "loss": 0.5139, "lr": 4.983822646461417e-05, "epoch": 1.326343381389253, "percentage": 13.26, "elapsed_time": "0:08:24", "remaining_time": "0:55:00", "throughput": 2691.86, "total_tokens": 1358416} {"current_steps": 5065, "total_steps": 38150, "loss": 0.6348, "lr": 4.9836924839331686e-05, "epoch": 1.327653997378768, "percentage": 13.28, "elapsed_time": "0:08:25", "remaining_time": "0:54:59", "throughput": 2692.3, "total_tokens": 1359824} {"current_steps": 5070, "total_steps": 38150, "loss": 0.5004, "lr": 4.983561801572374e-05, "epoch": 1.328964613368283, "percentage": 13.29, "elapsed_time": "0:08:25", "remaining_time": "0:54:58", "throughput": 2692.43, "total_tokens": 1361056} {"current_steps": 5075, "total_steps": 38150, "loss": 0.5481, "lr": 4.983430599406386e-05, "epoch": 1.3302752293577982, "percentage": 13.3, "elapsed_time": "0:08:25", "remaining_time": "0:54:57", "throughput": 2692.14, "total_tokens": 1362048} {"current_steps": 5080, "total_steps": 38150, "loss": 0.3545, "lr": 4.983298877462664e-05, "epoch": 1.3315858453473133, "percentage": 13.32, "elapsed_time": "0:08:26", "remaining_time": "0:54:56", "throughput": 2691.7, "total_tokens": 1362960} {"current_steps": 5085, "total_steps": 38150, "loss": 0.3399, "lr": 4.983166635768778e-05, "epoch": 1.3328964613368284, "percentage": 13.33, "elapsed_time": "0:08:26", "remaining_time": "0:54:55", "throughput": 2691.76, "total_tokens": 1364192} {"current_steps": 5090, "total_steps": 38150, "loss": 0.459, "lr": 4.9830338743524064e-05, "epoch": 1.3342070773263432, "percentage": 13.34, "elapsed_time": "0:08:27", "remaining_time": "0:54:55", "throughput": 2692.73, "total_tokens": 1366240} {"current_steps": 5095, "total_steps": 38150, "loss": 0.4576, "lr": 4.982900593241334e-05, "epoch": 1.3355176933158583, "percentage": 13.36, "elapsed_time": "0:08:27", "remaining_time": "0:54:54", "throughput": 2692.98, "total_tokens": 1367584} {"current_steps": 5100, "total_steps": 38150, "loss": 0.4402, "lr": 4.982766792463458e-05, "epoch": 1.3368283093053734, "percentage": 13.37, "elapsed_time": "0:08:28", "remaining_time": "0:54:54", "throughput": 2693.49, "total_tokens": 1369152} {"current_steps": 5105, "total_steps": 38150, "loss": 0.4047, "lr": 4.9826324720467834e-05, "epoch": 1.3381389252948885, "percentage": 13.38, "elapsed_time": "0:08:28", "remaining_time": "0:54:53", "throughput": 2693.41, "total_tokens": 1370256} {"current_steps": 5110, "total_steps": 38150, "loss": 0.9961, "lr": 4.982497632019421e-05, "epoch": 1.3394495412844036, "percentage": 13.39, "elapsed_time": "0:08:29", "remaining_time": "0:54:54", "throughput": 2694.66, "total_tokens": 1373184} {"current_steps": 5115, "total_steps": 38150, "loss": 0.6547, "lr": 4.9823622724095936e-05, "epoch": 1.3407601572739187, "percentage": 13.41, "elapsed_time": "0:08:30", "remaining_time": "0:54:54", "throughput": 2694.9, "total_tokens": 1374544} {"current_steps": 5120, "total_steps": 38150, "loss": 0.5706, "lr": 4.982226393245632e-05, "epoch": 1.3420707732634338, "percentage": 13.42, "elapsed_time": "0:08:30", "remaining_time": "0:54:53", "throughput": 2695.05, "total_tokens": 1375808} {"current_steps": 5125, "total_steps": 38150, "loss": 0.5374, "lr": 4.982089994555975e-05, "epoch": 1.343381389252949, "percentage": 13.43, "elapsed_time": "0:08:30", "remaining_time": "0:54:52", "throughput": 2695.33, "total_tokens": 1377216} {"current_steps": 5130, "total_steps": 38150, "loss": 0.537, "lr": 4.981953076369171e-05, "epoch": 1.344692005242464, "percentage": 13.45, "elapsed_time": "0:08:31", "remaining_time": "0:54:51", "throughput": 2695.42, "total_tokens": 1378448} {"current_steps": 5135, "total_steps": 38150, "loss": 0.6506, "lr": 4.981815638713877e-05, "epoch": 1.3460026212319791, "percentage": 13.46, "elapsed_time": "0:08:31", "remaining_time": "0:54:50", "throughput": 2695.62, "total_tokens": 1379728} {"current_steps": 5140, "total_steps": 38150, "loss": 0.6218, "lr": 4.981677681618858e-05, "epoch": 1.3473132372214942, "percentage": 13.47, "elapsed_time": "0:08:32", "remaining_time": "0:54:49", "throughput": 2695.57, "total_tokens": 1380880} {"current_steps": 5145, "total_steps": 38150, "loss": 0.7655, "lr": 4.981539205112988e-05, "epoch": 1.3486238532110093, "percentage": 13.49, "elapsed_time": "0:08:32", "remaining_time": "0:54:49", "throughput": 2696.09, "total_tokens": 1382672} {"current_steps": 5150, "total_steps": 38150, "loss": 0.5043, "lr": 4.98140020922525e-05, "epoch": 1.3499344692005242, "percentage": 13.5, "elapsed_time": "0:08:33", "remaining_time": "0:54:49", "throughput": 2696.53, "total_tokens": 1384176} {"current_steps": 5155, "total_steps": 38150, "loss": 0.5239, "lr": 4.9812606939847356e-05, "epoch": 1.3512450851900393, "percentage": 13.51, "elapsed_time": "0:08:33", "remaining_time": "0:54:48", "throughput": 2696.7, "total_tokens": 1385440} {"current_steps": 5160, "total_steps": 38150, "loss": 0.5464, "lr": 4.981120659420646e-05, "epoch": 1.3525557011795544, "percentage": 13.53, "elapsed_time": "0:08:34", "remaining_time": "0:54:47", "throughput": 2697.25, "total_tokens": 1387040} {"current_steps": 5165, "total_steps": 38150, "loss": 0.5119, "lr": 4.9809801055622887e-05, "epoch": 1.3538663171690695, "percentage": 13.54, "elapsed_time": "0:08:34", "remaining_time": "0:54:46", "throughput": 2697.01, "total_tokens": 1388048} {"current_steps": 5170, "total_steps": 38150, "loss": 0.6121, "lr": 4.980839032439082e-05, "epoch": 1.3551769331585846, "percentage": 13.55, "elapsed_time": "0:08:35", "remaining_time": "0:54:45", "throughput": 2696.82, "total_tokens": 1389072} {"current_steps": 5175, "total_steps": 38150, "loss": 0.4084, "lr": 4.980697440080553e-05, "epoch": 1.3564875491480997, "percentage": 13.56, "elapsed_time": "0:08:35", "remaining_time": "0:54:45", "throughput": 2697.4, "total_tokens": 1390720} {"current_steps": 5180, "total_steps": 38150, "loss": 0.2487, "lr": 4.980555328516335e-05, "epoch": 1.3577981651376148, "percentage": 13.58, "elapsed_time": "0:08:36", "remaining_time": "0:54:44", "throughput": 2697.65, "total_tokens": 1392096} {"current_steps": 5185, "total_steps": 38150, "loss": 0.3952, "lr": 4.9804126977761747e-05, "epoch": 1.3591087811271296, "percentage": 13.59, "elapsed_time": "0:08:36", "remaining_time": "0:54:43", "throughput": 2697.86, "total_tokens": 1393376} {"current_steps": 5190, "total_steps": 38150, "loss": 0.5265, "lr": 4.980269547889921e-05, "epoch": 1.3604193971166447, "percentage": 13.6, "elapsed_time": "0:08:36", "remaining_time": "0:54:42", "throughput": 2698.15, "total_tokens": 1394704} {"current_steps": 5195, "total_steps": 38150, "loss": 0.6168, "lr": 4.980125878887537e-05, "epoch": 1.3617300131061598, "percentage": 13.62, "elapsed_time": "0:08:37", "remaining_time": "0:54:41", "throughput": 2698.21, "total_tokens": 1395888} {"current_steps": 5200, "total_steps": 38150, "loss": 0.6688, "lr": 4.979981690799092e-05, "epoch": 1.363040629095675, "percentage": 13.63, "elapsed_time": "0:08:37", "remaining_time": "0:54:41", "throughput": 2698.47, "total_tokens": 1397280} {"current_steps": 5205, "total_steps": 38150, "loss": 0.4383, "lr": 4.9798369836547644e-05, "epoch": 1.36435124508519, "percentage": 13.64, "elapsed_time": "0:08:38", "remaining_time": "0:54:40", "throughput": 2698.27, "total_tokens": 1398320} {"current_steps": 5210, "total_steps": 38150, "loss": 0.4469, "lr": 4.97969175748484e-05, "epoch": 1.365661861074705, "percentage": 13.66, "elapsed_time": "0:08:38", "remaining_time": "0:54:39", "throughput": 2698.53, "total_tokens": 1399632} {"current_steps": 5215, "total_steps": 38150, "loss": 0.5019, "lr": 4.9795460123197166e-05, "epoch": 1.3669724770642202, "percentage": 13.67, "elapsed_time": "0:08:39", "remaining_time": "0:54:38", "throughput": 2698.46, "total_tokens": 1400768} {"current_steps": 5220, "total_steps": 38150, "loss": 0.4145, "lr": 4.979399748189896e-05, "epoch": 1.3682830930537353, "percentage": 13.68, "elapsed_time": "0:08:39", "remaining_time": "0:54:37", "throughput": 2699.01, "total_tokens": 1402352} {"current_steps": 5225, "total_steps": 38150, "loss": 0.3216, "lr": 4.979252965125993e-05, "epoch": 1.3695937090432504, "percentage": 13.7, "elapsed_time": "0:08:40", "remaining_time": "0:54:36", "throughput": 2698.69, "total_tokens": 1403328} {"current_steps": 5230, "total_steps": 38150, "loss": 0.5544, "lr": 4.9791056631587276e-05, "epoch": 1.3709043250327655, "percentage": 13.71, "elapsed_time": "0:08:40", "remaining_time": "0:54:35", "throughput": 2698.85, "total_tokens": 1404592} {"current_steps": 5235, "total_steps": 38150, "loss": 0.474, "lr": 4.978957842318931e-05, "epoch": 1.3722149410222806, "percentage": 13.72, "elapsed_time": "0:08:40", "remaining_time": "0:54:35", "throughput": 2698.99, "total_tokens": 1405840} {"current_steps": 5240, "total_steps": 38150, "loss": 0.5589, "lr": 4.978809502637541e-05, "epoch": 1.3735255570117955, "percentage": 13.74, "elapsed_time": "0:08:41", "remaining_time": "0:54:34", "throughput": 2699.42, "total_tokens": 1407248} {"current_steps": 5245, "total_steps": 38150, "loss": 0.4699, "lr": 4.9786606441456054e-05, "epoch": 1.3748361730013106, "percentage": 13.75, "elapsed_time": "0:08:41", "remaining_time": "0:54:33", "throughput": 2699.62, "total_tokens": 1408528} {"current_steps": 5250, "total_steps": 38150, "loss": 0.3609, "lr": 4.9785112668742796e-05, "epoch": 1.3761467889908257, "percentage": 13.76, "elapsed_time": "0:08:42", "remaining_time": "0:54:32", "throughput": 2699.83, "total_tokens": 1409792} {"current_steps": 5255, "total_steps": 38150, "loss": 0.4464, "lr": 4.978361370854828e-05, "epoch": 1.3774574049803407, "percentage": 13.77, "elapsed_time": "0:08:42", "remaining_time": "0:54:31", "throughput": 2700.19, "total_tokens": 1411168} {"current_steps": 5260, "total_steps": 38150, "loss": 0.4815, "lr": 4.978210956118624e-05, "epoch": 1.3787680209698558, "percentage": 13.79, "elapsed_time": "0:08:43", "remaining_time": "0:54:30", "throughput": 2700.38, "total_tokens": 1412512} {"current_steps": 5265, "total_steps": 38150, "loss": 0.5601, "lr": 4.9780600226971486e-05, "epoch": 1.380078636959371, "percentage": 13.8, "elapsed_time": "0:08:43", "remaining_time": "0:54:29", "throughput": 2700.23, "total_tokens": 1413584} {"current_steps": 5270, "total_steps": 38150, "loss": 0.6072, "lr": 4.977908570621993e-05, "epoch": 1.381389252948886, "percentage": 13.81, "elapsed_time": "0:08:44", "remaining_time": "0:54:29", "throughput": 2701.2, "total_tokens": 1415520} {"current_steps": 5275, "total_steps": 38150, "loss": 0.5795, "lr": 4.977756599924854e-05, "epoch": 1.382699868938401, "percentage": 13.83, "elapsed_time": "0:08:44", "remaining_time": "0:54:28", "throughput": 2701.07, "total_tokens": 1416576} {"current_steps": 5280, "total_steps": 38150, "loss": 0.3491, "lr": 4.97760411063754e-05, "epoch": 1.384010484927916, "percentage": 13.84, "elapsed_time": "0:08:44", "remaining_time": "0:54:27", "throughput": 2701.57, "total_tokens": 1418032} {"current_steps": 5285, "total_steps": 38150, "loss": 0.5349, "lr": 4.977451102791968e-05, "epoch": 1.385321100917431, "percentage": 13.85, "elapsed_time": "0:08:45", "remaining_time": "0:54:26", "throughput": 2701.7, "total_tokens": 1419264} {"current_steps": 5290, "total_steps": 38150, "loss": 0.5829, "lr": 4.977297576420159e-05, "epoch": 1.3866317169069462, "percentage": 13.87, "elapsed_time": "0:08:45", "remaining_time": "0:54:25", "throughput": 2701.34, "total_tokens": 1420224} {"current_steps": 5295, "total_steps": 38150, "loss": 0.5434, "lr": 4.977143531554249e-05, "epoch": 1.3879423328964613, "percentage": 13.88, "elapsed_time": "0:08:46", "remaining_time": "0:54:25", "throughput": 2701.48, "total_tokens": 1421552} {"current_steps": 5300, "total_steps": 38150, "loss": 0.5536, "lr": 4.9769889682264774e-05, "epoch": 1.3892529488859764, "percentage": 13.89, "elapsed_time": "0:08:46", "remaining_time": "0:54:24", "throughput": 2701.65, "total_tokens": 1422832} {"current_steps": 5305, "total_steps": 38150, "loss": 0.4924, "lr": 4.976833886469196e-05, "epoch": 1.3905635648754915, "percentage": 13.91, "elapsed_time": "0:08:47", "remaining_time": "0:54:23", "throughput": 2701.56, "total_tokens": 1423952} {"current_steps": 5310, "total_steps": 38150, "loss": 0.3191, "lr": 4.97667828631486e-05, "epoch": 1.3918741808650066, "percentage": 13.92, "elapsed_time": "0:08:47", "remaining_time": "0:54:22", "throughput": 2701.65, "total_tokens": 1425168} {"current_steps": 5315, "total_steps": 38150, "loss": 0.5516, "lr": 4.976522167796038e-05, "epoch": 1.3931847968545217, "percentage": 13.93, "elapsed_time": "0:08:47", "remaining_time": "0:54:21", "throughput": 2701.36, "total_tokens": 1426160} {"current_steps": 5320, "total_steps": 38150, "loss": 0.5665, "lr": 4.9763655309454064e-05, "epoch": 1.3944954128440368, "percentage": 13.94, "elapsed_time": "0:08:48", "remaining_time": "0:54:20", "throughput": 2701.54, "total_tokens": 1427440} {"current_steps": 5325, "total_steps": 38150, "loss": 0.4709, "lr": 4.976208375795748e-05, "epoch": 1.3958060288335519, "percentage": 13.96, "elapsed_time": "0:08:48", "remaining_time": "0:54:19", "throughput": 2701.35, "total_tokens": 1428496} {"current_steps": 5330, "total_steps": 38150, "loss": 0.4407, "lr": 4.9760507023799544e-05, "epoch": 1.397116644823067, "percentage": 13.97, "elapsed_time": "0:08:49", "remaining_time": "0:54:18", "throughput": 2701.17, "total_tokens": 1429568} {"current_steps": 5335, "total_steps": 38150, "loss": 0.5139, "lr": 4.9758925107310276e-05, "epoch": 1.3984272608125818, "percentage": 13.98, "elapsed_time": "0:08:49", "remaining_time": "0:54:18", "throughput": 2701.19, "total_tokens": 1430800} {"current_steps": 5340, "total_steps": 38150, "loss": 0.5121, "lr": 4.975733800882077e-05, "epoch": 1.399737876802097, "percentage": 14.0, "elapsed_time": "0:08:50", "remaining_time": "0:54:17", "throughput": 2701.15, "total_tokens": 1431968} {"current_steps": 5345, "total_steps": 38150, "loss": 0.6382, "lr": 4.975574572866318e-05, "epoch": 1.401048492791612, "percentage": 14.01, "elapsed_time": "0:08:50", "remaining_time": "0:54:16", "throughput": 2701.5, "total_tokens": 1433440} {"current_steps": 5350, "total_steps": 38150, "loss": 0.3873, "lr": 4.97541482671708e-05, "epoch": 1.4023591087811271, "percentage": 14.02, "elapsed_time": "0:08:51", "remaining_time": "0:54:15", "throughput": 2701.46, "total_tokens": 1434640} {"current_steps": 5355, "total_steps": 38150, "loss": 0.4993, "lr": 4.975254562467794e-05, "epoch": 1.4036697247706422, "percentage": 14.04, "elapsed_time": "0:08:51", "remaining_time": "0:54:15", "throughput": 2702.02, "total_tokens": 1436224} {"current_steps": 5360, "total_steps": 38150, "loss": 0.4075, "lr": 4.9750937801520064e-05, "epoch": 1.4049803407601573, "percentage": 14.05, "elapsed_time": "0:08:51", "remaining_time": "0:54:14", "throughput": 2701.63, "total_tokens": 1437136} {"current_steps": 5365, "total_steps": 38150, "loss": 0.5732, "lr": 4.974932479803367e-05, "epoch": 1.4062909567496724, "percentage": 14.06, "elapsed_time": "0:08:52", "remaining_time": "0:54:13", "throughput": 2701.81, "total_tokens": 1438384} {"current_steps": 5370, "total_steps": 38150, "loss": 0.6208, "lr": 4.974770661455636e-05, "epoch": 1.4076015727391873, "percentage": 14.08, "elapsed_time": "0:08:52", "remaining_time": "0:54:12", "throughput": 2701.91, "total_tokens": 1439600} {"current_steps": 5375, "total_steps": 38150, "loss": 0.5294, "lr": 4.974608325142681e-05, "epoch": 1.4089121887287024, "percentage": 14.09, "elapsed_time": "0:08:53", "remaining_time": "0:54:11", "throughput": 2701.91, "total_tokens": 1440768} {"current_steps": 5380, "total_steps": 38150, "loss": 0.4458, "lr": 4.97444547089848e-05, "epoch": 1.4102228047182175, "percentage": 14.1, "elapsed_time": "0:08:53", "remaining_time": "0:54:10", "throughput": 2702.39, "total_tokens": 1442320} {"current_steps": 5385, "total_steps": 38150, "loss": 0.4834, "lr": 4.974282098757118e-05, "epoch": 1.4115334207077326, "percentage": 14.12, "elapsed_time": "0:08:54", "remaining_time": "0:54:09", "throughput": 2702.37, "total_tokens": 1443456} {"current_steps": 5390, "total_steps": 38150, "loss": 0.4132, "lr": 4.974118208752787e-05, "epoch": 1.4128440366972477, "percentage": 14.13, "elapsed_time": "0:08:54", "remaining_time": "0:54:09", "throughput": 2702.68, "total_tokens": 1444864} {"current_steps": 5395, "total_steps": 38150, "loss": 0.4338, "lr": 4.97395380091979e-05, "epoch": 1.4141546526867628, "percentage": 14.14, "elapsed_time": "0:08:55", "remaining_time": "0:54:08", "throughput": 2702.78, "total_tokens": 1446176} {"current_steps": 5400, "total_steps": 38150, "loss": 0.4606, "lr": 4.9737888752925375e-05, "epoch": 1.4154652686762779, "percentage": 14.15, "elapsed_time": "0:08:55", "remaining_time": "0:54:07", "throughput": 2702.83, "total_tokens": 1447376} {"current_steps": 5405, "total_steps": 38150, "loss": 0.5389, "lr": 4.973623431905548e-05, "epoch": 1.416775884665793, "percentage": 14.17, "elapsed_time": "0:08:55", "remaining_time": "0:54:06", "throughput": 2702.53, "total_tokens": 1448368} {"current_steps": 5410, "total_steps": 38150, "loss": 0.5465, "lr": 4.973457470793447e-05, "epoch": 1.418086500655308, "percentage": 14.18, "elapsed_time": "0:08:56", "remaining_time": "0:54:05", "throughput": 2702.46, "total_tokens": 1449456} {"current_steps": 5415, "total_steps": 38150, "loss": 0.4601, "lr": 4.973290991990972e-05, "epoch": 1.4193971166448232, "percentage": 14.19, "elapsed_time": "0:08:56", "remaining_time": "0:54:05", "throughput": 2702.95, "total_tokens": 1451088} {"current_steps": 5420, "total_steps": 38150, "loss": 0.5225, "lr": 4.973123995532966e-05, "epoch": 1.4207077326343382, "percentage": 14.21, "elapsed_time": "0:08:57", "remaining_time": "0:54:04", "throughput": 2702.93, "total_tokens": 1452240} {"current_steps": 5425, "total_steps": 38150, "loss": 0.4726, "lr": 4.972956481454381e-05, "epoch": 1.4220183486238533, "percentage": 14.22, "elapsed_time": "0:08:57", "remaining_time": "0:54:03", "throughput": 2703.33, "total_tokens": 1453648} {"current_steps": 5430, "total_steps": 38150, "loss": 0.5678, "lr": 4.972788449790277e-05, "epoch": 1.4233289646133682, "percentage": 14.23, "elapsed_time": "0:08:58", "remaining_time": "0:54:03", "throughput": 2704.12, "total_tokens": 1455584} {"current_steps": 5435, "total_steps": 38150, "loss": 0.3849, "lr": 4.9726199005758234e-05, "epoch": 1.4246395806028833, "percentage": 14.25, "elapsed_time": "0:08:58", "remaining_time": "0:54:03", "throughput": 2704.89, "total_tokens": 1457408} {"current_steps": 5440, "total_steps": 38150, "loss": 0.4865, "lr": 4.972450833846297e-05, "epoch": 1.4259501965923984, "percentage": 14.26, "elapsed_time": "0:08:59", "remaining_time": "0:54:02", "throughput": 2705.11, "total_tokens": 1458704} {"current_steps": 5445, "total_steps": 38150, "loss": 0.3492, "lr": 4.972281249637083e-05, "epoch": 1.4272608125819135, "percentage": 14.27, "elapsed_time": "0:08:59", "remaining_time": "0:54:03", "throughput": 2706.11, "total_tokens": 1461232} {"current_steps": 5450, "total_steps": 38150, "loss": 0.5126, "lr": 4.9721111479836756e-05, "epoch": 1.4285714285714286, "percentage": 14.29, "elapsed_time": "0:09:00", "remaining_time": "0:54:02", "throughput": 2706.45, "total_tokens": 1462768} {"current_steps": 5455, "total_steps": 38150, "loss": 0.4543, "lr": 4.971940528921676e-05, "epoch": 1.4298820445609437, "percentage": 14.3, "elapsed_time": "0:09:00", "remaining_time": "0:54:02", "throughput": 2706.79, "total_tokens": 1464160} {"current_steps": 5460, "total_steps": 38150, "loss": 0.4163, "lr": 4.9717693924867944e-05, "epoch": 1.4311926605504588, "percentage": 14.31, "elapsed_time": "0:09:01", "remaining_time": "0:54:01", "throughput": 2706.71, "total_tokens": 1465264} {"current_steps": 5465, "total_steps": 38150, "loss": 0.4108, "lr": 4.9715977387148504e-05, "epoch": 1.4325032765399737, "percentage": 14.33, "elapsed_time": "0:09:01", "remaining_time": "0:54:00", "throughput": 2706.95, "total_tokens": 1466592} {"current_steps": 5470, "total_steps": 38150, "loss": 0.5781, "lr": 4.971425567641771e-05, "epoch": 1.4338138925294888, "percentage": 14.34, "elapsed_time": "0:09:02", "remaining_time": "0:53:59", "throughput": 2706.94, "total_tokens": 1467744} {"current_steps": 5475, "total_steps": 38150, "loss": 0.4171, "lr": 4.97125287930359e-05, "epoch": 1.4351245085190039, "percentage": 14.35, "elapsed_time": "0:09:02", "remaining_time": "0:53:58", "throughput": 2706.76, "total_tokens": 1468768} {"current_steps": 5480, "total_steps": 38150, "loss": 0.4955, "lr": 4.971079673736451e-05, "epoch": 1.436435124508519, "percentage": 14.36, "elapsed_time": "0:09:03", "remaining_time": "0:53:57", "throughput": 2707.08, "total_tokens": 1470144} {"current_steps": 5485, "total_steps": 38150, "loss": 0.6547, "lr": 4.970905950976606e-05, "epoch": 1.437745740498034, "percentage": 14.38, "elapsed_time": "0:09:03", "remaining_time": "0:53:56", "throughput": 2707.25, "total_tokens": 1471488} {"current_steps": 5490, "total_steps": 38150, "loss": 0.7066, "lr": 4.970731711060415e-05, "epoch": 1.4390563564875491, "percentage": 14.39, "elapsed_time": "0:09:03", "remaining_time": "0:53:56", "throughput": 2707.43, "total_tokens": 1472784} {"current_steps": 5495, "total_steps": 38150, "loss": 0.4282, "lr": 4.970556954024346e-05, "epoch": 1.4403669724770642, "percentage": 14.4, "elapsed_time": "0:09:04", "remaining_time": "0:53:55", "throughput": 2707.6, "total_tokens": 1474112} {"current_steps": 5500, "total_steps": 38150, "loss": 0.3785, "lr": 4.970381679904975e-05, "epoch": 1.4416775884665793, "percentage": 14.42, "elapsed_time": "0:09:04", "remaining_time": "0:53:54", "throughput": 2707.34, "total_tokens": 1475120} {"current_steps": 5505, "total_steps": 38150, "loss": 0.6274, "lr": 4.970205888738988e-05, "epoch": 1.4429882044560944, "percentage": 14.43, "elapsed_time": "0:09:05", "remaining_time": "0:53:53", "throughput": 2707.39, "total_tokens": 1476368} {"current_steps": 5510, "total_steps": 38150, "loss": 0.4744, "lr": 4.970029580563176e-05, "epoch": 1.4442988204456095, "percentage": 14.44, "elapsed_time": "0:09:05", "remaining_time": "0:53:53", "throughput": 2707.63, "total_tokens": 1477760} {"current_steps": 5515, "total_steps": 38150, "loss": 0.382, "lr": 4.96985275541444e-05, "epoch": 1.4456094364351246, "percentage": 14.46, "elapsed_time": "0:09:06", "remaining_time": "0:53:52", "throughput": 2707.87, "total_tokens": 1479136} {"current_steps": 5520, "total_steps": 38150, "loss": 0.3317, "lr": 4.969675413329791e-05, "epoch": 1.4469200524246395, "percentage": 14.47, "elapsed_time": "0:09:06", "remaining_time": "0:53:51", "throughput": 2707.48, "total_tokens": 1480048} {"current_steps": 5525, "total_steps": 38150, "loss": 0.4033, "lr": 4.969497554346344e-05, "epoch": 1.4482306684141546, "percentage": 14.48, "elapsed_time": "0:09:07", "remaining_time": "0:53:50", "throughput": 2707.55, "total_tokens": 1481360} {"current_steps": 5530, "total_steps": 38150, "loss": 0.5941, "lr": 4.969319178501327e-05, "epoch": 1.4495412844036697, "percentage": 14.5, "elapsed_time": "0:09:07", "remaining_time": "0:53:49", "throughput": 2708.06, "total_tokens": 1482864} {"current_steps": 5535, "total_steps": 38150, "loss": 0.3464, "lr": 4.969140285832072e-05, "epoch": 1.4508519003931848, "percentage": 14.51, "elapsed_time": "0:09:08", "remaining_time": "0:53:49", "throughput": 2708.42, "total_tokens": 1484336} {"current_steps": 5540, "total_steps": 38150, "loss": 0.4356, "lr": 4.968960876376022e-05, "epoch": 1.4521625163826999, "percentage": 14.52, "elapsed_time": "0:09:08", "remaining_time": "0:53:48", "throughput": 2708.38, "total_tokens": 1485472} {"current_steps": 5545, "total_steps": 38150, "loss": 0.4283, "lr": 4.9687809501707264e-05, "epoch": 1.453473132372215, "percentage": 14.53, "elapsed_time": "0:09:08", "remaining_time": "0:53:48", "throughput": 2709.04, "total_tokens": 1487264} {"current_steps": 5550, "total_steps": 38150, "loss": 0.4804, "lr": 4.968600507253843e-05, "epoch": 1.45478374836173, "percentage": 14.55, "elapsed_time": "0:09:09", "remaining_time": "0:53:47", "throughput": 2708.97, "total_tokens": 1488400} {"current_steps": 5555, "total_steps": 38150, "loss": 0.3878, "lr": 4.968419547663139e-05, "epoch": 1.456094364351245, "percentage": 14.56, "elapsed_time": "0:09:09", "remaining_time": "0:53:46", "throughput": 2708.79, "total_tokens": 1489424} {"current_steps": 5560, "total_steps": 38150, "loss": 0.5697, "lr": 4.9682380714364897e-05, "epoch": 1.45740498034076, "percentage": 14.57, "elapsed_time": "0:09:10", "remaining_time": "0:53:45", "throughput": 2708.36, "total_tokens": 1490320} {"current_steps": 5565, "total_steps": 38150, "loss": 0.5917, "lr": 4.968056078611876e-05, "epoch": 1.4587155963302751, "percentage": 14.59, "elapsed_time": "0:09:10", "remaining_time": "0:53:45", "throughput": 2709.42, "total_tokens": 1492640} {"current_steps": 5570, "total_steps": 38150, "loss": 0.5868, "lr": 4.96787356922739e-05, "epoch": 1.4600262123197902, "percentage": 14.6, "elapsed_time": "0:09:11", "remaining_time": "0:53:44", "throughput": 2709.56, "total_tokens": 1493872} {"current_steps": 5575, "total_steps": 38150, "loss": 0.5079, "lr": 4.9676905433212296e-05, "epoch": 1.4613368283093053, "percentage": 14.61, "elapsed_time": "0:09:11", "remaining_time": "0:53:44", "throughput": 2709.81, "total_tokens": 1495216} {"current_steps": 5580, "total_steps": 38150, "loss": 0.4804, "lr": 4.967507000931702e-05, "epoch": 1.4626474442988204, "percentage": 14.63, "elapsed_time": "0:09:12", "remaining_time": "0:53:43", "throughput": 2709.79, "total_tokens": 1496480} {"current_steps": 5585, "total_steps": 38150, "loss": 0.4418, "lr": 4.967322942097225e-05, "epoch": 1.4639580602883355, "percentage": 14.64, "elapsed_time": "0:09:12", "remaining_time": "0:53:42", "throughput": 2710.15, "total_tokens": 1497936} {"current_steps": 5590, "total_steps": 38150, "loss": 0.454, "lr": 4.9671383668563167e-05, "epoch": 1.4652686762778506, "percentage": 14.65, "elapsed_time": "0:09:13", "remaining_time": "0:53:42", "throughput": 2710.3, "total_tokens": 1499280} {"current_steps": 5595, "total_steps": 38150, "loss": 0.5505, "lr": 4.966953275247612e-05, "epoch": 1.4665792922673657, "percentage": 14.67, "elapsed_time": "0:09:13", "remaining_time": "0:53:41", "throughput": 2710.4, "total_tokens": 1500464} {"current_steps": 5600, "total_steps": 38150, "loss": 0.3442, "lr": 4.966767667309849e-05, "epoch": 1.4678899082568808, "percentage": 14.68, "elapsed_time": "0:09:14", "remaining_time": "0:53:40", "throughput": 2710.7, "total_tokens": 1501824} {"current_steps": 5605, "total_steps": 38150, "loss": 0.4907, "lr": 4.966581543081876e-05, "epoch": 1.469200524246396, "percentage": 14.69, "elapsed_time": "0:09:14", "remaining_time": "0:53:39", "throughput": 2710.64, "total_tokens": 1503024} {"current_steps": 5610, "total_steps": 38150, "loss": 0.631, "lr": 4.966394902602649e-05, "epoch": 1.470511140235911, "percentage": 14.71, "elapsed_time": "0:09:14", "remaining_time": "0:53:39", "throughput": 2711.38, "total_tokens": 1504800} {"current_steps": 5615, "total_steps": 38150, "loss": 0.4033, "lr": 4.966207745911229e-05, "epoch": 1.4718217562254259, "percentage": 14.72, "elapsed_time": "0:09:15", "remaining_time": "0:53:38", "throughput": 2711.44, "total_tokens": 1506016} {"current_steps": 5620, "total_steps": 38150, "loss": 0.6106, "lr": 4.9660200730467894e-05, "epoch": 1.473132372214941, "percentage": 14.73, "elapsed_time": "0:09:15", "remaining_time": "0:53:37", "throughput": 2711.67, "total_tokens": 1507360} {"current_steps": 5625, "total_steps": 38150, "loss": 0.5802, "lr": 4.9658318840486095e-05, "epoch": 1.474442988204456, "percentage": 14.74, "elapsed_time": "0:09:16", "remaining_time": "0:53:36", "throughput": 2711.54, "total_tokens": 1508528} {"current_steps": 5630, "total_steps": 38150, "loss": 0.5152, "lr": 4.9656431789560765e-05, "epoch": 1.4757536041939712, "percentage": 14.76, "elapsed_time": "0:09:16", "remaining_time": "0:53:35", "throughput": 2711.37, "total_tokens": 1509584} {"current_steps": 5635, "total_steps": 38150, "loss": 0.8406, "lr": 4.9654539578086865e-05, "epoch": 1.4770642201834863, "percentage": 14.77, "elapsed_time": "0:09:17", "remaining_time": "0:53:35", "throughput": 2711.68, "total_tokens": 1511008} {"current_steps": 5640, "total_steps": 38150, "loss": 0.532, "lr": 4.965264220646044e-05, "epoch": 1.4783748361730014, "percentage": 14.78, "elapsed_time": "0:09:17", "remaining_time": "0:53:34", "throughput": 2711.97, "total_tokens": 1512448} {"current_steps": 5645, "total_steps": 38150, "loss": 0.526, "lr": 4.965073967507859e-05, "epoch": 1.4796854521625165, "percentage": 14.8, "elapsed_time": "0:09:18", "remaining_time": "0:53:33", "throughput": 2712.13, "total_tokens": 1513712} {"current_steps": 5650, "total_steps": 38150, "loss": 0.6023, "lr": 4.9648831984339525e-05, "epoch": 1.4809960681520313, "percentage": 14.81, "elapsed_time": "0:09:18", "remaining_time": "0:53:33", "throughput": 2712.87, "total_tokens": 1515632} {"current_steps": 5655, "total_steps": 38150, "loss": 0.3562, "lr": 4.9646919134642513e-05, "epoch": 1.4823066841415464, "percentage": 14.82, "elapsed_time": "0:09:19", "remaining_time": "0:53:32", "throughput": 2712.58, "total_tokens": 1516592} {"current_steps": 5660, "total_steps": 38150, "loss": 0.4619, "lr": 4.964500112638791e-05, "epoch": 1.4836173001310615, "percentage": 14.84, "elapsed_time": "0:09:19", "remaining_time": "0:53:32", "throughput": 2712.95, "total_tokens": 1518080} {"current_steps": 5665, "total_steps": 38150, "loss": 0.3543, "lr": 4.964307795997716e-05, "epoch": 1.4849279161205766, "percentage": 14.85, "elapsed_time": "0:09:20", "remaining_time": "0:53:31", "throughput": 2713.11, "total_tokens": 1519344} {"current_steps": 5670, "total_steps": 38150, "loss": 0.4681, "lr": 4.964114963581277e-05, "epoch": 1.4862385321100917, "percentage": 14.86, "elapsed_time": "0:09:20", "remaining_time": "0:53:30", "throughput": 2712.9, "total_tokens": 1520384} {"current_steps": 5675, "total_steps": 38150, "loss": 0.5288, "lr": 4.963921615429833e-05, "epoch": 1.4875491480996068, "percentage": 14.88, "elapsed_time": "0:09:20", "remaining_time": "0:53:29", "throughput": 2713.33, "total_tokens": 1521840} {"current_steps": 5680, "total_steps": 38150, "loss": 0.5571, "lr": 4.963727751583853e-05, "epoch": 1.488859764089122, "percentage": 14.89, "elapsed_time": "0:09:21", "remaining_time": "0:53:28", "throughput": 2713.25, "total_tokens": 1522960} {"current_steps": 5685, "total_steps": 38150, "loss": 0.4615, "lr": 4.963533372083912e-05, "epoch": 1.490170380078637, "percentage": 14.9, "elapsed_time": "0:09:21", "remaining_time": "0:53:28", "throughput": 2713.57, "total_tokens": 1524416} {"current_steps": 5690, "total_steps": 38150, "loss": 0.5468, "lr": 4.963338476970692e-05, "epoch": 1.491480996068152, "percentage": 14.91, "elapsed_time": "0:09:22", "remaining_time": "0:53:27", "throughput": 2713.82, "total_tokens": 1525808} {"current_steps": 5695, "total_steps": 38150, "loss": 0.3973, "lr": 4.963143066284986e-05, "epoch": 1.4927916120576672, "percentage": 14.93, "elapsed_time": "0:09:22", "remaining_time": "0:53:26", "throughput": 2713.87, "total_tokens": 1527088} {"current_steps": 5700, "total_steps": 38150, "loss": 0.5338, "lr": 4.962947140067691e-05, "epoch": 1.4941022280471823, "percentage": 14.94, "elapsed_time": "0:09:23", "remaining_time": "0:53:25", "throughput": 2714.12, "total_tokens": 1528432} {"current_steps": 5705, "total_steps": 38150, "loss": 0.6326, "lr": 4.962750698359816e-05, "epoch": 1.4954128440366974, "percentage": 14.95, "elapsed_time": "0:09:23", "remaining_time": "0:53:25", "throughput": 2714.04, "total_tokens": 1529520} {"current_steps": 5710, "total_steps": 38150, "loss": 0.4788, "lr": 4.962553741202475e-05, "epoch": 1.4967234600262123, "percentage": 14.97, "elapsed_time": "0:09:23", "remaining_time": "0:53:24", "throughput": 2714.05, "total_tokens": 1530720} {"current_steps": 5715, "total_steps": 38150, "loss": 0.5605, "lr": 4.962356268636891e-05, "epoch": 1.4980340760157274, "percentage": 14.98, "elapsed_time": "0:09:24", "remaining_time": "0:53:23", "throughput": 2714.06, "total_tokens": 1531952} {"current_steps": 5720, "total_steps": 38150, "loss": 0.4662, "lr": 4.962158280704395e-05, "epoch": 1.4993446920052425, "percentage": 14.99, "elapsed_time": "0:09:24", "remaining_time": "0:53:23", "throughput": 2714.35, "total_tokens": 1533456} {"current_steps": 5724, "total_steps": 38150, "eval_loss": 0.5115170478820801, "epoch": 1.5003931847968546, "percentage": 15.0, "elapsed_time": "0:09:42", "remaining_time": "0:54:57", "throughput": 2635.75, "total_tokens": 1534400} {"current_steps": 5725, "total_steps": 38150, "loss": 0.5307, "lr": 4.961959777446425e-05, "epoch": 1.5006553079947575, "percentage": 15.01, "elapsed_time": "0:09:43", "remaining_time": "0:55:05", "throughput": 2629.55, "total_tokens": 1534720} {"current_steps": 5730, "total_steps": 38150, "loss": 0.3311, "lr": 4.961760758904527e-05, "epoch": 1.5019659239842726, "percentage": 15.02, "elapsed_time": "0:09:44", "remaining_time": "0:55:05", "throughput": 2630.49, "total_tokens": 1536992} {"current_steps": 5735, "total_steps": 38150, "loss": 0.6005, "lr": 4.961561225120356e-05, "epoch": 1.5032765399737875, "percentage": 15.03, "elapsed_time": "0:09:44", "remaining_time": "0:55:05", "throughput": 2630.72, "total_tokens": 1538288} {"current_steps": 5740, "total_steps": 38150, "loss": 0.4807, "lr": 4.9613611761356736e-05, "epoch": 1.5045871559633026, "percentage": 15.05, "elapsed_time": "0:09:45", "remaining_time": "0:55:04", "throughput": 2630.53, "total_tokens": 1539296} {"current_steps": 5745, "total_steps": 38150, "loss": 0.4038, "lr": 4.96116061199235e-05, "epoch": 1.5058977719528177, "percentage": 15.06, "elapsed_time": "0:09:45", "remaining_time": "0:55:03", "throughput": 2631.07, "total_tokens": 1540896} {"current_steps": 5750, "total_steps": 38150, "loss": 0.433, "lr": 4.960959532732363e-05, "epoch": 1.5072083879423328, "percentage": 15.07, "elapsed_time": "0:09:46", "remaining_time": "0:55:02", "throughput": 2631.03, "total_tokens": 1542000} {"current_steps": 5755, "total_steps": 38150, "loss": 0.4251, "lr": 4.9607579383977984e-05, "epoch": 1.508519003931848, "percentage": 15.09, "elapsed_time": "0:09:46", "remaining_time": "0:55:01", "throughput": 2631.48, "total_tokens": 1543536} {"current_steps": 5760, "total_steps": 38150, "loss": 0.5783, "lr": 4.9605558290308484e-05, "epoch": 1.509829619921363, "percentage": 15.1, "elapsed_time": "0:09:47", "remaining_time": "0:55:01", "throughput": 2631.94, "total_tokens": 1545056} {"current_steps": 5765, "total_steps": 38150, "loss": 0.4075, "lr": 4.9603532046738154e-05, "epoch": 1.511140235910878, "percentage": 15.11, "elapsed_time": "0:09:47", "remaining_time": "0:55:00", "throughput": 2631.82, "total_tokens": 1546128} {"current_steps": 5770, "total_steps": 38150, "loss": 0.3033, "lr": 4.960150065369108e-05, "epoch": 1.5124508519003932, "percentage": 15.12, "elapsed_time": "0:09:47", "remaining_time": "0:54:59", "throughput": 2632.13, "total_tokens": 1547536} {"current_steps": 5775, "total_steps": 38150, "loss": 0.4794, "lr": 4.9599464111592417e-05, "epoch": 1.5137614678899083, "percentage": 15.14, "elapsed_time": "0:09:48", "remaining_time": "0:54:58", "throughput": 2632.73, "total_tokens": 1549152} {"current_steps": 5780, "total_steps": 38150, "loss": 0.4688, "lr": 4.959742242086843e-05, "epoch": 1.5150720838794234, "percentage": 15.15, "elapsed_time": "0:09:48", "remaining_time": "0:54:57", "throughput": 2633.0, "total_tokens": 1550464} {"current_steps": 5785, "total_steps": 38150, "loss": 0.4473, "lr": 4.959537558194643e-05, "epoch": 1.5163826998689385, "percentage": 15.16, "elapsed_time": "0:09:49", "remaining_time": "0:54:56", "throughput": 2633.31, "total_tokens": 1551808} {"current_steps": 5790, "total_steps": 38150, "loss": 0.4709, "lr": 4.959332359525482e-05, "epoch": 1.5176933158584536, "percentage": 15.18, "elapsed_time": "0:09:49", "remaining_time": "0:54:55", "throughput": 2633.5, "total_tokens": 1553056} {"current_steps": 5795, "total_steps": 38150, "loss": 0.4694, "lr": 4.9591266461223075e-05, "epoch": 1.5190039318479687, "percentage": 15.19, "elapsed_time": "0:09:50", "remaining_time": "0:54:54", "throughput": 2633.29, "total_tokens": 1554032} {"current_steps": 5800, "total_steps": 38150, "loss": 0.3603, "lr": 4.958920418028175e-05, "epoch": 1.5203145478374838, "percentage": 15.2, "elapsed_time": "0:09:50", "remaining_time": "0:54:54", "throughput": 2633.54, "total_tokens": 1555360} {"current_steps": 5805, "total_steps": 38150, "loss": 0.513, "lr": 4.958713675286247e-05, "epoch": 1.5216251638269986, "percentage": 15.22, "elapsed_time": "0:09:51", "remaining_time": "0:54:53", "throughput": 2633.41, "total_tokens": 1556384} {"current_steps": 5810, "total_steps": 38150, "loss": 0.4739, "lr": 4.9585064179397955e-05, "epoch": 1.5229357798165137, "percentage": 15.23, "elapsed_time": "0:09:51", "remaining_time": "0:54:52", "throughput": 2633.98, "total_tokens": 1557968} {"current_steps": 5815, "total_steps": 38150, "loss": 0.571, "lr": 4.958298646032199e-05, "epoch": 1.5242463958060288, "percentage": 15.24, "elapsed_time": "0:09:51", "remaining_time": "0:54:51", "throughput": 2633.92, "total_tokens": 1559056} {"current_steps": 5820, "total_steps": 38150, "loss": 0.4626, "lr": 4.958090359606943e-05, "epoch": 1.525557011795544, "percentage": 15.26, "elapsed_time": "0:09:52", "remaining_time": "0:54:50", "throughput": 2634.15, "total_tokens": 1560336} {"current_steps": 5825, "total_steps": 38150, "loss": 0.3891, "lr": 4.957881558707622e-05, "epoch": 1.526867627785059, "percentage": 15.27, "elapsed_time": "0:09:52", "remaining_time": "0:54:49", "throughput": 2633.99, "total_tokens": 1561344} {"current_steps": 5830, "total_steps": 38150, "loss": 0.542, "lr": 4.957672243377938e-05, "epoch": 1.528178243774574, "percentage": 15.28, "elapsed_time": "0:09:53", "remaining_time": "0:54:48", "throughput": 2634.45, "total_tokens": 1562960} {"current_steps": 5835, "total_steps": 38150, "loss": 0.4602, "lr": 4.9574624136617e-05, "epoch": 1.529488859764089, "percentage": 15.29, "elapsed_time": "0:09:53", "remaining_time": "0:54:48", "throughput": 2635.2, "total_tokens": 1564736} {"current_steps": 5840, "total_steps": 38150, "loss": 0.4171, "lr": 4.9572520696028245e-05, "epoch": 1.530799475753604, "percentage": 15.31, "elapsed_time": "0:09:54", "remaining_time": "0:54:48", "throughput": 2635.94, "total_tokens": 1566624} {"current_steps": 5845, "total_steps": 38150, "loss": 0.4428, "lr": 4.9570412112453377e-05, "epoch": 1.5321100917431192, "percentage": 15.32, "elapsed_time": "0:09:54", "remaining_time": "0:54:47", "throughput": 2636.55, "total_tokens": 1568336} {"current_steps": 5850, "total_steps": 38150, "loss": 0.5026, "lr": 4.95682983863337e-05, "epoch": 1.5334207077326343, "percentage": 15.33, "elapsed_time": "0:09:55", "remaining_time": "0:54:47", "throughput": 2637.34, "total_tokens": 1570208} {"current_steps": 5855, "total_steps": 38150, "loss": 0.4748, "lr": 4.9566179518111625e-05, "epoch": 1.5347313237221494, "percentage": 15.35, "elapsed_time": "0:09:55", "remaining_time": "0:54:46", "throughput": 2637.58, "total_tokens": 1571504} {"current_steps": 5860, "total_steps": 38150, "loss": 0.4932, "lr": 4.9564055508230616e-05, "epoch": 1.5360419397116645, "percentage": 15.36, "elapsed_time": "0:09:56", "remaining_time": "0:54:45", "throughput": 2637.24, "total_tokens": 1572400} {"current_steps": 5865, "total_steps": 38150, "loss": 0.5005, "lr": 4.9561926357135235e-05, "epoch": 1.5373525557011796, "percentage": 15.37, "elapsed_time": "0:09:56", "remaining_time": "0:54:44", "throughput": 2637.66, "total_tokens": 1573856} {"current_steps": 5870, "total_steps": 38150, "loss": 0.3814, "lr": 4.9559792065271116e-05, "epoch": 1.5386631716906947, "percentage": 15.39, "elapsed_time": "0:09:57", "remaining_time": "0:54:43", "throughput": 2637.64, "total_tokens": 1574976} {"current_steps": 5875, "total_steps": 38150, "loss": 0.6464, "lr": 4.955765263308495e-05, "epoch": 1.5399737876802098, "percentage": 15.4, "elapsed_time": "0:09:57", "remaining_time": "0:54:42", "throughput": 2637.49, "total_tokens": 1576016} {"current_steps": 5880, "total_steps": 38150, "loss": 0.4023, "lr": 4.9555508061024514e-05, "epoch": 1.5412844036697249, "percentage": 15.41, "elapsed_time": "0:09:58", "remaining_time": "0:54:41", "throughput": 2637.98, "total_tokens": 1577552} {"current_steps": 5885, "total_steps": 38150, "loss": 0.3169, "lr": 4.955335834953867e-05, "epoch": 1.54259501965924, "percentage": 15.43, "elapsed_time": "0:09:58", "remaining_time": "0:54:41", "throughput": 2638.37, "total_tokens": 1578944} {"current_steps": 5890, "total_steps": 38150, "loss": 0.3249, "lr": 4.955120349907736e-05, "epoch": 1.543905635648755, "percentage": 15.44, "elapsed_time": "0:09:58", "remaining_time": "0:54:40", "throughput": 2638.73, "total_tokens": 1580336} {"current_steps": 5895, "total_steps": 38150, "loss": 0.8458, "lr": 4.954904351009157e-05, "epoch": 1.5452162516382701, "percentage": 15.45, "elapsed_time": "0:09:59", "remaining_time": "0:54:39", "throughput": 2638.74, "total_tokens": 1581456} {"current_steps": 5900, "total_steps": 38150, "loss": 0.4874, "lr": 4.954687838303339e-05, "epoch": 1.546526867627785, "percentage": 15.47, "elapsed_time": "0:09:59", "remaining_time": "0:54:38", "throughput": 2639.19, "total_tokens": 1582976} {"current_steps": 5905, "total_steps": 38150, "loss": 0.3836, "lr": 4.9544708118355984e-05, "epoch": 1.5478374836173001, "percentage": 15.48, "elapsed_time": "0:10:00", "remaining_time": "0:54:37", "throughput": 2639.68, "total_tokens": 1584544} {"current_steps": 5910, "total_steps": 38150, "loss": 0.6509, "lr": 4.9542532716513576e-05, "epoch": 1.5491480996068152, "percentage": 15.49, "elapsed_time": "0:10:00", "remaining_time": "0:54:37", "throughput": 2640.02, "total_tokens": 1585936} {"current_steps": 5915, "total_steps": 38150, "loss": 0.4894, "lr": 4.9540352177961466e-05, "epoch": 1.5504587155963303, "percentage": 15.5, "elapsed_time": "0:10:01", "remaining_time": "0:54:36", "throughput": 2640.01, "total_tokens": 1587056} {"current_steps": 5920, "total_steps": 38150, "loss": 0.448, "lr": 4.953816650315606e-05, "epoch": 1.5517693315858454, "percentage": 15.52, "elapsed_time": "0:10:01", "remaining_time": "0:54:35", "throughput": 2640.61, "total_tokens": 1588704} {"current_steps": 5925, "total_steps": 38150, "loss": 0.3448, "lr": 4.9535975692554805e-05, "epoch": 1.5530799475753603, "percentage": 15.53, "elapsed_time": "0:10:02", "remaining_time": "0:54:34", "throughput": 2640.73, "total_tokens": 1590016} {"current_steps": 5930, "total_steps": 38150, "loss": 0.512, "lr": 4.953377974661623e-05, "epoch": 1.5543905635648754, "percentage": 15.54, "elapsed_time": "0:10:02", "remaining_time": "0:54:33", "throughput": 2640.69, "total_tokens": 1591200} {"current_steps": 5935, "total_steps": 38150, "loss": 0.5671, "lr": 4.953157866579994e-05, "epoch": 1.5557011795543905, "percentage": 15.56, "elapsed_time": "0:10:03", "remaining_time": "0:54:33", "throughput": 2640.92, "total_tokens": 1592576} {"current_steps": 5940, "total_steps": 38150, "loss": 0.2956, "lr": 4.9529372450566624e-05, "epoch": 1.5570117955439056, "percentage": 15.57, "elapsed_time": "0:10:03", "remaining_time": "0:54:32", "throughput": 2640.77, "total_tokens": 1593680} {"current_steps": 5945, "total_steps": 38150, "loss": 0.4718, "lr": 4.952716110137804e-05, "epoch": 1.5583224115334207, "percentage": 15.58, "elapsed_time": "0:10:03", "remaining_time": "0:54:31", "throughput": 2640.77, "total_tokens": 1594800} {"current_steps": 5950, "total_steps": 38150, "loss": 0.4343, "lr": 4.952494461869702e-05, "epoch": 1.5596330275229358, "percentage": 15.6, "elapsed_time": "0:10:04", "remaining_time": "0:54:30", "throughput": 2640.92, "total_tokens": 1596096} {"current_steps": 5955, "total_steps": 38150, "loss": 0.5395, "lr": 4.952272300298747e-05, "epoch": 1.5609436435124509, "percentage": 15.61, "elapsed_time": "0:10:04", "remaining_time": "0:54:29", "throughput": 2640.95, "total_tokens": 1597344} {"current_steps": 5960, "total_steps": 38150, "loss": 0.4992, "lr": 4.952049625471436e-05, "epoch": 1.562254259501966, "percentage": 15.62, "elapsed_time": "0:10:05", "remaining_time": "0:54:29", "throughput": 2641.35, "total_tokens": 1598864} {"current_steps": 5965, "total_steps": 38150, "loss": 0.432, "lr": 4.951826437434375e-05, "epoch": 1.563564875491481, "percentage": 15.64, "elapsed_time": "0:10:05", "remaining_time": "0:54:28", "throughput": 2641.45, "total_tokens": 1600144} {"current_steps": 5970, "total_steps": 38150, "loss": 0.4207, "lr": 4.951602736234278e-05, "epoch": 1.5648754914809961, "percentage": 15.65, "elapsed_time": "0:10:06", "remaining_time": "0:54:28", "throughput": 2642.3, "total_tokens": 1602080} {"current_steps": 5975, "total_steps": 38150, "loss": 0.4634, "lr": 4.9513785219179634e-05, "epoch": 1.5661861074705112, "percentage": 15.66, "elapsed_time": "0:10:06", "remaining_time": "0:54:27", "throughput": 2642.72, "total_tokens": 1603664} {"current_steps": 5980, "total_steps": 38150, "loss": 0.5595, "lr": 4.95115379453236e-05, "epoch": 1.5674967234600263, "percentage": 15.67, "elapsed_time": "0:10:07", "remaining_time": "0:54:27", "throughput": 2643.47, "total_tokens": 1605616} {"current_steps": 5985, "total_steps": 38150, "loss": 0.4519, "lr": 4.950928554124503e-05, "epoch": 1.5688073394495414, "percentage": 15.69, "elapsed_time": "0:10:07", "remaining_time": "0:54:26", "throughput": 2643.48, "total_tokens": 1606720} {"current_steps": 5990, "total_steps": 38150, "loss": 0.834, "lr": 4.950702800741534e-05, "epoch": 1.5701179554390565, "percentage": 15.7, "elapsed_time": "0:10:08", "remaining_time": "0:54:25", "throughput": 2643.9, "total_tokens": 1608240} {"current_steps": 5995, "total_steps": 38150, "loss": 0.6621, "lr": 4.950476534430703e-05, "epoch": 1.5714285714285714, "percentage": 15.71, "elapsed_time": "0:10:08", "remaining_time": "0:54:24", "throughput": 2644.09, "total_tokens": 1609504} {"current_steps": 6000, "total_steps": 38150, "loss": 0.4699, "lr": 4.950249755239369e-05, "epoch": 1.5727391874180865, "percentage": 15.73, "elapsed_time": "0:10:09", "remaining_time": "0:54:23", "throughput": 2644.07, "total_tokens": 1610608} {"current_steps": 6005, "total_steps": 38150, "loss": 0.5832, "lr": 4.950022463214994e-05, "epoch": 1.5740498034076016, "percentage": 15.74, "elapsed_time": "0:10:09", "remaining_time": "0:54:23", "throughput": 2644.28, "total_tokens": 1611968} {"current_steps": 6010, "total_steps": 38150, "loss": 0.3024, "lr": 4.949794658405151e-05, "epoch": 1.5753604193971167, "percentage": 15.75, "elapsed_time": "0:10:10", "remaining_time": "0:54:22", "throughput": 2644.87, "total_tokens": 1613712} {"current_steps": 6015, "total_steps": 38150, "loss": 0.4357, "lr": 4.9495663408575185e-05, "epoch": 1.5766710353866316, "percentage": 15.77, "elapsed_time": "0:10:10", "remaining_time": "0:54:22", "throughput": 2645.35, "total_tokens": 1615280} {"current_steps": 6020, "total_steps": 38150, "loss": 0.4228, "lr": 4.949337510619884e-05, "epoch": 1.5779816513761467, "percentage": 15.78, "elapsed_time": "0:10:11", "remaining_time": "0:54:21", "throughput": 2646.05, "total_tokens": 1616992} {"current_steps": 6025, "total_steps": 38150, "loss": 0.491, "lr": 4.94910816774014e-05, "epoch": 1.5792922673656618, "percentage": 15.79, "elapsed_time": "0:10:11", "remaining_time": "0:54:20", "throughput": 2646.6, "total_tokens": 1618592} {"current_steps": 6030, "total_steps": 38150, "loss": 0.4701, "lr": 4.9488783122662886e-05, "epoch": 1.5806028833551768, "percentage": 15.81, "elapsed_time": "0:10:12", "remaining_time": "0:54:19", "throughput": 2646.73, "total_tokens": 1619824} {"current_steps": 6035, "total_steps": 38150, "loss": 0.4997, "lr": 4.9486479442464374e-05, "epoch": 1.581913499344692, "percentage": 15.82, "elapsed_time": "0:10:12", "remaining_time": "0:54:18", "throughput": 2646.54, "total_tokens": 1620800} {"current_steps": 6040, "total_steps": 38150, "loss": 0.504, "lr": 4.948417063728803e-05, "epoch": 1.583224115334207, "percentage": 15.83, "elapsed_time": "0:10:12", "remaining_time": "0:54:18", "throughput": 2646.61, "total_tokens": 1622000} {"current_steps": 6045, "total_steps": 38150, "loss": 0.3577, "lr": 4.948185670761707e-05, "epoch": 1.5845347313237221, "percentage": 15.85, "elapsed_time": "0:10:13", "remaining_time": "0:54:17", "throughput": 2646.81, "total_tokens": 1623328} {"current_steps": 6050, "total_steps": 38150, "loss": 0.4029, "lr": 4.94795376539358e-05, "epoch": 1.5858453473132372, "percentage": 15.86, "elapsed_time": "0:10:13", "remaining_time": "0:54:16", "throughput": 2646.77, "total_tokens": 1624432} {"current_steps": 6055, "total_steps": 38150, "loss": 0.4645, "lr": 4.947721347672961e-05, "epoch": 1.5871559633027523, "percentage": 15.87, "elapsed_time": "0:10:14", "remaining_time": "0:54:16", "throughput": 2647.52, "total_tokens": 1626304} {"current_steps": 6060, "total_steps": 38150, "loss": 0.6423, "lr": 4.9474884176484924e-05, "epoch": 1.5884665792922674, "percentage": 15.88, "elapsed_time": "0:10:14", "remaining_time": "0:54:15", "throughput": 2648.63, "total_tokens": 1628480} {"current_steps": 6065, "total_steps": 38150, "loss": 0.6244, "lr": 4.947254975368927e-05, "epoch": 1.5897771952817825, "percentage": 15.9, "elapsed_time": "0:10:15", "remaining_time": "0:54:15", "throughput": 2649.02, "total_tokens": 1630048} {"current_steps": 6070, "total_steps": 38150, "loss": 0.4844, "lr": 4.947021020883124e-05, "epoch": 1.5910878112712976, "percentage": 15.91, "elapsed_time": "0:10:15", "remaining_time": "0:54:14", "throughput": 2649.5, "total_tokens": 1631600} {"current_steps": 6075, "total_steps": 38150, "loss": 0.4394, "lr": 4.9467865542400494e-05, "epoch": 1.5923984272608127, "percentage": 15.92, "elapsed_time": "0:10:21", "remaining_time": "0:54:41", "throughput": 2628.19, "total_tokens": 1633232} {"current_steps": 6080, "total_steps": 38150, "loss": 0.454, "lr": 4.946551575488776e-05, "epoch": 1.5937090432503278, "percentage": 15.94, "elapsed_time": "0:10:21", "remaining_time": "0:54:40", "throughput": 2628.35, "total_tokens": 1634592} {"current_steps": 6085, "total_steps": 38150, "loss": 0.4252, "lr": 4.946316084678486e-05, "epoch": 1.5950196592398427, "percentage": 15.95, "elapsed_time": "0:10:22", "remaining_time": "0:54:39", "throughput": 2628.4, "total_tokens": 1635760} {"current_steps": 6090, "total_steps": 38150, "loss": 0.6135, "lr": 4.946080081858466e-05, "epoch": 1.5963302752293578, "percentage": 15.96, "elapsed_time": "0:10:22", "remaining_time": "0:54:38", "throughput": 2628.66, "total_tokens": 1637040} {"current_steps": 6095, "total_steps": 38150, "loss": 0.4372, "lr": 4.945843567078111e-05, "epoch": 1.5976408912188729, "percentage": 15.98, "elapsed_time": "0:10:23", "remaining_time": "0:54:37", "throughput": 2629.03, "total_tokens": 1638464} {"current_steps": 6100, "total_steps": 38150, "loss": 0.6158, "lr": 4.9456065403869246e-05, "epoch": 1.598951507208388, "percentage": 15.99, "elapsed_time": "0:10:23", "remaining_time": "0:54:36", "throughput": 2629.3, "total_tokens": 1639792} {"current_steps": 6105, "total_steps": 38150, "loss": 0.3245, "lr": 4.9453690018345144e-05, "epoch": 1.600262123197903, "percentage": 16.0, "elapsed_time": "0:10:24", "remaining_time": "0:54:36", "throughput": 2628.89, "total_tokens": 1641056} {"current_steps": 6110, "total_steps": 38150, "loss": 0.7569, "lr": 4.945130951470597e-05, "epoch": 1.601572739187418, "percentage": 16.02, "elapsed_time": "0:10:24", "remaining_time": "0:54:35", "throughput": 2628.95, "total_tokens": 1642208} {"current_steps": 6115, "total_steps": 38150, "loss": 0.3095, "lr": 4.944892389344997e-05, "epoch": 1.602883355176933, "percentage": 16.03, "elapsed_time": "0:10:25", "remaining_time": "0:54:34", "throughput": 2629.31, "total_tokens": 1643664} {"current_steps": 6120, "total_steps": 38150, "loss": 0.4127, "lr": 4.9446533155076444e-05, "epoch": 1.6041939711664481, "percentage": 16.04, "elapsed_time": "0:10:25", "remaining_time": "0:54:34", "throughput": 2629.45, "total_tokens": 1644976} {"current_steps": 6125, "total_steps": 38150, "loss": 0.7607, "lr": 4.9444137300085766e-05, "epoch": 1.6055045871559632, "percentage": 16.06, "elapsed_time": "0:10:26", "remaining_time": "0:54:33", "throughput": 2629.7, "total_tokens": 1646352} {"current_steps": 6130, "total_steps": 38150, "loss": 0.4382, "lr": 4.944173632897938e-05, "epoch": 1.6068152031454783, "percentage": 16.07, "elapsed_time": "0:10:26", "remaining_time": "0:54:32", "throughput": 2629.43, "total_tokens": 1647296} {"current_steps": 6135, "total_steps": 38150, "loss": 0.6308, "lr": 4.943933024225983e-05, "epoch": 1.6081258191349934, "percentage": 16.08, "elapsed_time": "0:10:28", "remaining_time": "0:54:38", "throughput": 2625.33, "total_tokens": 1649152} {"current_steps": 6140, "total_steps": 38150, "loss": 0.5584, "lr": 4.943691904043067e-05, "epoch": 1.6094364351245085, "percentage": 16.09, "elapsed_time": "0:10:28", "remaining_time": "0:54:37", "throughput": 2625.25, "total_tokens": 1650208} {"current_steps": 6145, "total_steps": 38150, "loss": 0.5498, "lr": 4.943450272399659e-05, "epoch": 1.6107470511140236, "percentage": 16.11, "elapsed_time": "0:10:29", "remaining_time": "0:54:36", "throughput": 2624.71, "total_tokens": 1650960} {"current_steps": 6150, "total_steps": 38150, "loss": 0.4105, "lr": 4.94320812934633e-05, "epoch": 1.6120576671035387, "percentage": 16.12, "elapsed_time": "0:10:29", "remaining_time": "0:54:35", "throughput": 2624.89, "total_tokens": 1652240} {"current_steps": 6155, "total_steps": 38150, "loss": 0.5949, "lr": 4.942965474933762e-05, "epoch": 1.6133682830930538, "percentage": 16.13, "elapsed_time": "0:10:29", "remaining_time": "0:54:34", "throughput": 2625.15, "total_tokens": 1653568} {"current_steps": 6160, "total_steps": 38150, "loss": 0.6382, "lr": 4.9427223092127406e-05, "epoch": 1.614678899082569, "percentage": 16.15, "elapsed_time": "0:10:30", "remaining_time": "0:54:33", "throughput": 2625.37, "total_tokens": 1654944} {"current_steps": 6165, "total_steps": 38150, "loss": 0.6448, "lr": 4.942478632234161e-05, "epoch": 1.615989515072084, "percentage": 16.16, "elapsed_time": "0:10:30", "remaining_time": "0:54:32", "throughput": 2625.62, "total_tokens": 1656352} {"current_steps": 6170, "total_steps": 38150, "loss": 0.4469, "lr": 4.942234444049024e-05, "epoch": 1.617300131061599, "percentage": 16.17, "elapsed_time": "0:10:31", "remaining_time": "0:54:32", "throughput": 2625.96, "total_tokens": 1657792} {"current_steps": 6175, "total_steps": 38150, "loss": 0.5089, "lr": 4.9419897447084375e-05, "epoch": 1.6186107470511142, "percentage": 16.19, "elapsed_time": "0:10:31", "remaining_time": "0:54:31", "throughput": 2626.14, "total_tokens": 1659072} {"current_steps": 6180, "total_steps": 38150, "loss": 0.2221, "lr": 4.9417445342636166e-05, "epoch": 1.619921363040629, "percentage": 16.2, "elapsed_time": "0:10:32", "remaining_time": "0:54:30", "throughput": 2626.59, "total_tokens": 1660688} {"current_steps": 6185, "total_steps": 38150, "loss": 0.4258, "lr": 4.941498812765884e-05, "epoch": 1.6212319790301442, "percentage": 16.21, "elapsed_time": "0:10:32", "remaining_time": "0:54:30", "throughput": 2627.18, "total_tokens": 1662352} {"current_steps": 6190, "total_steps": 38150, "loss": 0.7969, "lr": 4.941252580266668e-05, "epoch": 1.6225425950196593, "percentage": 16.23, "elapsed_time": "0:10:33", "remaining_time": "0:54:29", "throughput": 2626.74, "total_tokens": 1663168} {"current_steps": 6195, "total_steps": 38150, "loss": 0.5362, "lr": 4.941005836817506e-05, "epoch": 1.6238532110091743, "percentage": 16.24, "elapsed_time": "0:10:33", "remaining_time": "0:54:28", "throughput": 2627.34, "total_tokens": 1664896} {"current_steps": 6200, "total_steps": 38150, "loss": 0.4574, "lr": 4.940758582470039e-05, "epoch": 1.6251638269986892, "percentage": 16.25, "elapsed_time": "0:10:34", "remaining_time": "0:54:27", "throughput": 2627.38, "total_tokens": 1666048} {"current_steps": 6205, "total_steps": 38150, "loss": 0.6305, "lr": 4.940510817276019e-05, "epoch": 1.6264744429882043, "percentage": 16.26, "elapsed_time": "0:10:34", "remaining_time": "0:54:26", "throughput": 2627.41, "total_tokens": 1667184} {"current_steps": 6210, "total_steps": 38150, "loss": 0.2986, "lr": 4.940262541287302e-05, "epoch": 1.6277850589777194, "percentage": 16.28, "elapsed_time": "0:10:34", "remaining_time": "0:54:25", "throughput": 2627.58, "total_tokens": 1668496} {"current_steps": 6215, "total_steps": 38150, "loss": 0.8126, "lr": 4.94001375455585e-05, "epoch": 1.6290956749672345, "percentage": 16.29, "elapsed_time": "0:10:35", "remaining_time": "0:54:25", "throughput": 2627.71, "total_tokens": 1669776} {"current_steps": 6220, "total_steps": 38150, "loss": 0.5268, "lr": 4.939764457133737e-05, "epoch": 1.6304062909567496, "percentage": 16.3, "elapsed_time": "0:10:35", "remaining_time": "0:54:24", "throughput": 2628.09, "total_tokens": 1671296} {"current_steps": 6225, "total_steps": 38150, "loss": 0.4387, "lr": 4.939514649073137e-05, "epoch": 1.6317169069462647, "percentage": 16.32, "elapsed_time": "0:10:36", "remaining_time": "0:54:23", "throughput": 2628.28, "total_tokens": 1672672} {"current_steps": 6230, "total_steps": 38150, "loss": 0.4052, "lr": 4.939264330426337e-05, "epoch": 1.6330275229357798, "percentage": 16.33, "elapsed_time": "0:10:36", "remaining_time": "0:54:23", "throughput": 2628.36, "total_tokens": 1673904} {"current_steps": 6235, "total_steps": 38150, "loss": 0.4185, "lr": 4.9390135012457275e-05, "epoch": 1.634338138925295, "percentage": 16.34, "elapsed_time": "0:10:37", "remaining_time": "0:54:22", "throughput": 2628.71, "total_tokens": 1675296} {"current_steps": 6240, "total_steps": 38150, "loss": 0.7141, "lr": 4.938762161583807e-05, "epoch": 1.63564875491481, "percentage": 16.36, "elapsed_time": "0:10:37", "remaining_time": "0:54:21", "throughput": 2628.69, "total_tokens": 1676400} {"current_steps": 6245, "total_steps": 38150, "loss": 0.4396, "lr": 4.9385103114931784e-05, "epoch": 1.636959370904325, "percentage": 16.37, "elapsed_time": "0:10:38", "remaining_time": "0:54:20", "throughput": 2629.41, "total_tokens": 1678064} {"current_steps": 6250, "total_steps": 38150, "loss": 0.5207, "lr": 4.9382579510265556e-05, "epoch": 1.6382699868938402, "percentage": 16.38, "elapsed_time": "0:10:38", "remaining_time": "0:54:19", "throughput": 2630.08, "total_tokens": 1679824} {"current_steps": 6255, "total_steps": 38150, "loss": 0.4025, "lr": 4.9380050802367573e-05, "epoch": 1.6395806028833553, "percentage": 16.4, "elapsed_time": "0:10:39", "remaining_time": "0:54:19", "throughput": 2629.99, "total_tokens": 1680960} {"current_steps": 6260, "total_steps": 38150, "loss": 0.5129, "lr": 4.937751699176708e-05, "epoch": 1.6408912188728704, "percentage": 16.41, "elapsed_time": "0:10:39", "remaining_time": "0:54:18", "throughput": 2630.06, "total_tokens": 1682144} {"current_steps": 6265, "total_steps": 38150, "loss": 0.5223, "lr": 4.93749780789944e-05, "epoch": 1.6422018348623855, "percentage": 16.42, "elapsed_time": "0:10:40", "remaining_time": "0:54:17", "throughput": 2630.61, "total_tokens": 1683744} {"current_steps": 6270, "total_steps": 38150, "loss": 0.3233, "lr": 4.937243406458093e-05, "epoch": 1.6435124508519003, "percentage": 16.44, "elapsed_time": "0:10:40", "remaining_time": "0:54:16", "throughput": 2630.93, "total_tokens": 1685136} {"current_steps": 6275, "total_steps": 38150, "loss": 0.5983, "lr": 4.9369884949059115e-05, "epoch": 1.6448230668414154, "percentage": 16.45, "elapsed_time": "0:10:40", "remaining_time": "0:54:15", "throughput": 2630.99, "total_tokens": 1686400} {"current_steps": 6280, "total_steps": 38150, "loss": 0.4134, "lr": 4.936733073296249e-05, "epoch": 1.6461336828309305, "percentage": 16.46, "elapsed_time": "0:10:41", "remaining_time": "0:54:15", "throughput": 2630.85, "total_tokens": 1687424} {"current_steps": 6285, "total_steps": 38150, "loss": 0.4579, "lr": 4.936477141682565e-05, "epoch": 1.6474442988204456, "percentage": 16.47, "elapsed_time": "0:10:41", "remaining_time": "0:54:14", "throughput": 2631.33, "total_tokens": 1688976} {"current_steps": 6290, "total_steps": 38150, "loss": 0.3171, "lr": 4.9362207001184246e-05, "epoch": 1.6487549148099607, "percentage": 16.49, "elapsed_time": "0:10:42", "remaining_time": "0:54:13", "throughput": 2631.88, "total_tokens": 1690608} {"current_steps": 6295, "total_steps": 38150, "loss": 0.5504, "lr": 4.9359637486575016e-05, "epoch": 1.6500655307994756, "percentage": 16.5, "elapsed_time": "0:10:42", "remaining_time": "0:54:12", "throughput": 2631.91, "total_tokens": 1691760} {"current_steps": 6300, "total_steps": 38150, "loss": 0.5074, "lr": 4.9357062873535746e-05, "epoch": 1.6513761467889907, "percentage": 16.51, "elapsed_time": "0:10:43", "remaining_time": "0:54:12", "throughput": 2632.3, "total_tokens": 1693280} {"current_steps": 6305, "total_steps": 38150, "loss": 0.4299, "lr": 4.9354483162605305e-05, "epoch": 1.6526867627785058, "percentage": 16.53, "elapsed_time": "0:10:43", "remaining_time": "0:54:11", "throughput": 2632.14, "total_tokens": 1694272} {"current_steps": 6310, "total_steps": 38150, "loss": 0.4654, "lr": 4.9351898354323625e-05, "epoch": 1.6539973787680209, "percentage": 16.54, "elapsed_time": "0:10:44", "remaining_time": "0:54:10", "throughput": 2632.41, "total_tokens": 1695696} {"current_steps": 6315, "total_steps": 38150, "loss": 0.4604, "lr": 4.934930844923168e-05, "epoch": 1.655307994757536, "percentage": 16.55, "elapsed_time": "0:10:44", "remaining_time": "0:54:09", "throughput": 2632.27, "total_tokens": 1696704} {"current_steps": 6320, "total_steps": 38150, "loss": 0.4551, "lr": 4.934671344787156e-05, "epoch": 1.656618610747051, "percentage": 16.57, "elapsed_time": "0:10:45", "remaining_time": "0:54:08", "throughput": 2632.4, "total_tokens": 1697936} {"current_steps": 6325, "total_steps": 38150, "loss": 0.4205, "lr": 4.9344113350786386e-05, "epoch": 1.6579292267365662, "percentage": 16.58, "elapsed_time": "0:10:45", "remaining_time": "0:54:07", "throughput": 2632.83, "total_tokens": 1699456} {"current_steps": 6330, "total_steps": 38150, "loss": 0.4247, "lr": 4.934150815852034e-05, "epoch": 1.6592398427260813, "percentage": 16.59, "elapsed_time": "0:10:45", "remaining_time": "0:54:06", "throughput": 2632.72, "total_tokens": 1700512} {"current_steps": 6335, "total_steps": 38150, "loss": 0.4676, "lr": 4.933889787161871e-05, "epoch": 1.6605504587155964, "percentage": 16.61, "elapsed_time": "0:10:46", "remaining_time": "0:54:06", "throughput": 2632.89, "total_tokens": 1701760} {"current_steps": 6340, "total_steps": 38150, "loss": 0.6863, "lr": 4.9336282490627803e-05, "epoch": 1.6618610747051115, "percentage": 16.62, "elapsed_time": "0:10:46", "remaining_time": "0:54:05", "throughput": 2632.89, "total_tokens": 1702880} {"current_steps": 6345, "total_steps": 38150, "loss": 0.6484, "lr": 4.9333662016095016e-05, "epoch": 1.6631716906946266, "percentage": 16.63, "elapsed_time": "0:10:47", "remaining_time": "0:54:04", "throughput": 2632.95, "total_tokens": 1704064} {"current_steps": 6350, "total_steps": 38150, "loss": 0.4714, "lr": 4.9331036448568826e-05, "epoch": 1.6644823066841417, "percentage": 16.64, "elapsed_time": "0:10:47", "remaining_time": "0:54:03", "throughput": 2633.02, "total_tokens": 1705264} {"current_steps": 6355, "total_steps": 38150, "loss": 0.3859, "lr": 4.932840578859873e-05, "epoch": 1.6657929226736568, "percentage": 16.66, "elapsed_time": "0:10:48", "remaining_time": "0:54:02", "throughput": 2633.39, "total_tokens": 1706736} {"current_steps": 6360, "total_steps": 38150, "loss": 0.4932, "lr": 4.932577003673535e-05, "epoch": 1.6671035386631718, "percentage": 16.67, "elapsed_time": "0:10:48", "remaining_time": "0:54:01", "throughput": 2633.57, "total_tokens": 1708000} {"current_steps": 6365, "total_steps": 38150, "loss": 0.4994, "lr": 4.932312919353034e-05, "epoch": 1.6684141546526867, "percentage": 16.68, "elapsed_time": "0:10:49", "remaining_time": "0:54:01", "throughput": 2634.01, "total_tokens": 1709536} {"current_steps": 6370, "total_steps": 38150, "loss": 0.4205, "lr": 4.932048325953641e-05, "epoch": 1.6697247706422018, "percentage": 16.7, "elapsed_time": "0:10:49", "remaining_time": "0:54:00", "throughput": 2634.22, "total_tokens": 1710816} {"current_steps": 6375, "total_steps": 38150, "loss": 0.4272, "lr": 4.931783223530736e-05, "epoch": 1.671035386631717, "percentage": 16.71, "elapsed_time": "0:10:49", "remaining_time": "0:53:59", "throughput": 2634.57, "total_tokens": 1712288} {"current_steps": 6380, "total_steps": 38150, "loss": 0.4461, "lr": 4.9315176121398035e-05, "epoch": 1.672346002621232, "percentage": 16.72, "elapsed_time": "0:10:50", "remaining_time": "0:53:59", "throughput": 2635.29, "total_tokens": 1714192} {"current_steps": 6385, "total_steps": 38150, "loss": 0.3382, "lr": 4.931251491836436e-05, "epoch": 1.673656618610747, "percentage": 16.74, "elapsed_time": "0:10:50", "remaining_time": "0:53:58", "throughput": 2635.11, "total_tokens": 1715280} {"current_steps": 6390, "total_steps": 38150, "loss": 0.3578, "lr": 4.930984862676332e-05, "epoch": 1.674967234600262, "percentage": 16.75, "elapsed_time": "0:10:51", "remaining_time": "0:53:57", "throughput": 2635.56, "total_tokens": 1716864} {"current_steps": 6395, "total_steps": 38150, "loss": 0.475, "lr": 4.930717724715298e-05, "epoch": 1.676277850589777, "percentage": 16.76, "elapsed_time": "0:10:51", "remaining_time": "0:53:56", "throughput": 2635.56, "total_tokens": 1717984} {"current_steps": 6400, "total_steps": 38150, "loss": 0.7982, "lr": 4.930450078009243e-05, "epoch": 1.6775884665792922, "percentage": 16.78, "elapsed_time": "0:10:52", "remaining_time": "0:53:55", "throughput": 2635.59, "total_tokens": 1719120} {"current_steps": 6405, "total_steps": 38150, "loss": 0.7724, "lr": 4.930181922614186e-05, "epoch": 1.6788990825688073, "percentage": 16.79, "elapsed_time": "0:10:52", "remaining_time": "0:53:55", "throughput": 2636.49, "total_tokens": 1721136} {"current_steps": 6410, "total_steps": 38150, "loss": 0.5078, "lr": 4.929913258586252e-05, "epoch": 1.6802096985583224, "percentage": 16.8, "elapsed_time": "0:10:53", "remaining_time": "0:53:54", "throughput": 2636.83, "total_tokens": 1722528} {"current_steps": 6415, "total_steps": 38150, "loss": 0.4908, "lr": 4.9296440859816715e-05, "epoch": 1.6815203145478375, "percentage": 16.82, "elapsed_time": "0:10:53", "remaining_time": "0:53:53", "throughput": 2637.08, "total_tokens": 1723856} {"current_steps": 6420, "total_steps": 38150, "loss": 0.4685, "lr": 4.9293744048567825e-05, "epoch": 1.6828309305373526, "percentage": 16.83, "elapsed_time": "0:10:54", "remaining_time": "0:53:52", "throughput": 2637.08, "total_tokens": 1724976} {"current_steps": 6425, "total_steps": 38150, "loss": 0.7041, "lr": 4.929104215268027e-05, "epoch": 1.6841415465268676, "percentage": 16.84, "elapsed_time": "0:10:54", "remaining_time": "0:53:52", "throughput": 2637.78, "total_tokens": 1726656} {"current_steps": 6430, "total_steps": 38150, "loss": 0.6325, "lr": 4.9288335172719575e-05, "epoch": 1.6854521625163827, "percentage": 16.85, "elapsed_time": "0:10:55", "remaining_time": "0:53:51", "throughput": 2637.84, "total_tokens": 1727920} {"current_steps": 6435, "total_steps": 38150, "loss": 0.5742, "lr": 4.9285623109252286e-05, "epoch": 1.6867627785058978, "percentage": 16.87, "elapsed_time": "0:10:55", "remaining_time": "0:53:50", "throughput": 2637.93, "total_tokens": 1729200} {"current_steps": 6440, "total_steps": 38150, "loss": 0.2873, "lr": 4.928290596284606e-05, "epoch": 1.688073394495413, "percentage": 16.88, "elapsed_time": "0:10:55", "remaining_time": "0:53:49", "throughput": 2637.95, "total_tokens": 1730352} {"current_steps": 6445, "total_steps": 38150, "loss": 0.3992, "lr": 4.928018373406955e-05, "epoch": 1.689384010484928, "percentage": 16.89, "elapsed_time": "0:10:56", "remaining_time": "0:53:48", "throughput": 2638.11, "total_tokens": 1731616} {"current_steps": 6450, "total_steps": 38150, "loss": 0.6935, "lr": 4.927745642349255e-05, "epoch": 1.6906946264744431, "percentage": 16.91, "elapsed_time": "0:10:56", "remaining_time": "0:53:48", "throughput": 2638.37, "total_tokens": 1732960} {"current_steps": 6455, "total_steps": 38150, "loss": 0.6478, "lr": 4.927472403168587e-05, "epoch": 1.6920052424639582, "percentage": 16.92, "elapsed_time": "0:10:57", "remaining_time": "0:53:47", "throughput": 2638.43, "total_tokens": 1734160} {"current_steps": 6460, "total_steps": 38150, "loss": 0.5031, "lr": 4.92719865592214e-05, "epoch": 1.693315858453473, "percentage": 16.93, "elapsed_time": "0:10:57", "remaining_time": "0:53:46", "throughput": 2638.56, "total_tokens": 1735392} {"current_steps": 6465, "total_steps": 38150, "loss": 0.5273, "lr": 4.9269244006672065e-05, "epoch": 1.6946264744429882, "percentage": 16.95, "elapsed_time": "0:10:58", "remaining_time": "0:53:45", "throughput": 2638.56, "total_tokens": 1736576} {"current_steps": 6470, "total_steps": 38150, "loss": 0.5046, "lr": 4.9266496374611904e-05, "epoch": 1.6959370904325033, "percentage": 16.96, "elapsed_time": "0:10:58", "remaining_time": "0:53:44", "throughput": 2638.7, "total_tokens": 1737792} {"current_steps": 6475, "total_steps": 38150, "loss": 0.5997, "lr": 4.926374366361598e-05, "epoch": 1.6972477064220184, "percentage": 16.97, "elapsed_time": "0:10:59", "remaining_time": "0:53:43", "throughput": 2638.94, "total_tokens": 1739184} {"current_steps": 6480, "total_steps": 38150, "loss": 0.4816, "lr": 4.926098587426043e-05, "epoch": 1.6985583224115333, "percentage": 16.99, "elapsed_time": "0:10:59", "remaining_time": "0:53:43", "throughput": 2639.32, "total_tokens": 1740624} {"current_steps": 6485, "total_steps": 38150, "loss": 0.3772, "lr": 4.9258223007122454e-05, "epoch": 1.6998689384010484, "percentage": 17.0, "elapsed_time": "0:11:00", "remaining_time": "0:53:42", "throughput": 2639.92, "total_tokens": 1742480} {"current_steps": 6490, "total_steps": 38150, "loss": 0.4265, "lr": 4.925545506278032e-05, "epoch": 1.7011795543905635, "percentage": 17.01, "elapsed_time": "0:11:00", "remaining_time": "0:53:42", "throughput": 2640.12, "total_tokens": 1743808} {"current_steps": 6495, "total_steps": 38150, "loss": 0.6889, "lr": 4.9252682041813356e-05, "epoch": 1.7024901703800785, "percentage": 17.02, "elapsed_time": "0:11:00", "remaining_time": "0:53:41", "throughput": 2639.77, "total_tokens": 1744704} {"current_steps": 6500, "total_steps": 38150, "loss": 0.3576, "lr": 4.924990394480195e-05, "epoch": 1.7038007863695936, "percentage": 17.04, "elapsed_time": "0:11:01", "remaining_time": "0:53:40", "throughput": 2639.78, "total_tokens": 1745872} {"current_steps": 6505, "total_steps": 38150, "loss": 0.4876, "lr": 4.9247120772327534e-05, "epoch": 1.7051114023591087, "percentage": 17.05, "elapsed_time": "0:11:01", "remaining_time": "0:53:39", "throughput": 2639.98, "total_tokens": 1747184} {"current_steps": 6510, "total_steps": 38150, "loss": 0.6374, "lr": 4.924433252497264e-05, "epoch": 1.7064220183486238, "percentage": 17.06, "elapsed_time": "0:11:02", "remaining_time": "0:53:39", "throughput": 2640.5, "total_tokens": 1748880} {"current_steps": 6515, "total_steps": 38150, "loss": 0.687, "lr": 4.924153920332084e-05, "epoch": 1.707732634338139, "percentage": 17.08, "elapsed_time": "0:11:02", "remaining_time": "0:53:38", "throughput": 2640.81, "total_tokens": 1750400} {"current_steps": 6520, "total_steps": 38150, "loss": 0.3968, "lr": 4.923874080795677e-05, "epoch": 1.709043250327654, "percentage": 17.09, "elapsed_time": "0:11:03", "remaining_time": "0:53:38", "throughput": 2641.18, "total_tokens": 1752000} {"current_steps": 6525, "total_steps": 38150, "loss": 0.6991, "lr": 4.923593733946614e-05, "epoch": 1.7103538663171691, "percentage": 17.1, "elapsed_time": "0:11:03", "remaining_time": "0:53:37", "throughput": 2641.55, "total_tokens": 1753520} {"current_steps": 6530, "total_steps": 38150, "loss": 0.5648, "lr": 4.92331287984357e-05, "epoch": 1.7116644823066842, "percentage": 17.12, "elapsed_time": "0:11:04", "remaining_time": "0:53:36", "throughput": 2641.59, "total_tokens": 1754704} {"current_steps": 6535, "total_steps": 38150, "loss": 0.4611, "lr": 4.9230315185453266e-05, "epoch": 1.7129750982961993, "percentage": 17.13, "elapsed_time": "0:11:04", "remaining_time": "0:53:35", "throughput": 2641.08, "total_tokens": 1755488} {"current_steps": 6540, "total_steps": 38150, "loss": 0.3577, "lr": 4.922749650110773e-05, "epoch": 1.7142857142857144, "percentage": 17.14, "elapsed_time": "0:11:05", "remaining_time": "0:53:34", "throughput": 2641.17, "total_tokens": 1756688} {"current_steps": 6545, "total_steps": 38150, "loss": 0.5254, "lr": 4.9224672745989045e-05, "epoch": 1.7155963302752295, "percentage": 17.16, "elapsed_time": "0:11:05", "remaining_time": "0:53:34", "throughput": 2641.56, "total_tokens": 1758256} {"current_steps": 6550, "total_steps": 38150, "loss": 0.6037, "lr": 4.922184392068821e-05, "epoch": 1.7169069462647444, "percentage": 17.17, "elapsed_time": "0:11:06", "remaining_time": "0:53:33", "throughput": 2641.54, "total_tokens": 1759392} {"current_steps": 6555, "total_steps": 38150, "loss": 0.4874, "lr": 4.921901002579729e-05, "epoch": 1.7182175622542595, "percentage": 17.18, "elapsed_time": "0:11:06", "remaining_time": "0:53:32", "throughput": 2641.78, "total_tokens": 1760800} {"current_steps": 6560, "total_steps": 38150, "loss": 0.4038, "lr": 4.921617106190942e-05, "epoch": 1.7195281782437746, "percentage": 17.2, "elapsed_time": "0:11:06", "remaining_time": "0:53:31", "throughput": 2641.61, "total_tokens": 1761872} {"current_steps": 6565, "total_steps": 38150, "loss": 0.5099, "lr": 4.9213327029618796e-05, "epoch": 1.7208387942332897, "percentage": 17.21, "elapsed_time": "0:11:07", "remaining_time": "0:53:31", "throughput": 2641.95, "total_tokens": 1763392} {"current_steps": 6570, "total_steps": 38150, "loss": 0.4802, "lr": 4.921047792952066e-05, "epoch": 1.7221494102228048, "percentage": 17.22, "elapsed_time": "0:11:07", "remaining_time": "0:53:30", "throughput": 2642.29, "total_tokens": 1764832} {"current_steps": 6575, "total_steps": 38150, "loss": 0.3665, "lr": 4.920762376221132e-05, "epoch": 1.7234600262123196, "percentage": 17.23, "elapsed_time": "0:11:08", "remaining_time": "0:53:29", "throughput": 2642.59, "total_tokens": 1766304} {"current_steps": 6580, "total_steps": 38150, "loss": 0.3015, "lr": 4.920476452828815e-05, "epoch": 1.7247706422018347, "percentage": 17.25, "elapsed_time": "0:11:08", "remaining_time": "0:53:29", "throughput": 2642.78, "total_tokens": 1767632} {"current_steps": 6585, "total_steps": 38150, "loss": 0.3602, "lr": 4.9201900228349594e-05, "epoch": 1.7260812581913498, "percentage": 17.26, "elapsed_time": "0:11:09", "remaining_time": "0:53:28", "throughput": 2642.9, "total_tokens": 1768944} {"current_steps": 6590, "total_steps": 38150, "loss": 0.5524, "lr": 4.9199030862995144e-05, "epoch": 1.727391874180865, "percentage": 17.27, "elapsed_time": "0:11:09", "remaining_time": "0:53:28", "throughput": 2643.35, "total_tokens": 1770672} {"current_steps": 6595, "total_steps": 38150, "loss": 0.5582, "lr": 4.919615643282533e-05, "epoch": 1.72870249017038, "percentage": 17.29, "elapsed_time": "0:11:10", "remaining_time": "0:53:27", "throughput": 2643.32, "total_tokens": 1771808} {"current_steps": 6600, "total_steps": 38150, "loss": 0.5623, "lr": 4.91932769384418e-05, "epoch": 1.7300131061598951, "percentage": 17.3, "elapsed_time": "0:11:10", "remaining_time": "0:53:26", "throughput": 2643.32, "total_tokens": 1773056} {"current_steps": 6605, "total_steps": 38150, "loss": 0.6349, "lr": 4.91903923804472e-05, "epoch": 1.7313237221494102, "percentage": 17.31, "elapsed_time": "0:11:11", "remaining_time": "0:53:25", "throughput": 2643.73, "total_tokens": 1774528} {"current_steps": 6610, "total_steps": 38150, "loss": 0.7762, "lr": 4.918750275944528e-05, "epoch": 1.7326343381389253, "percentage": 17.33, "elapsed_time": "0:11:11", "remaining_time": "0:53:24", "throughput": 2643.68, "total_tokens": 1775680} {"current_steps": 6615, "total_steps": 38150, "loss": 0.4057, "lr": 4.9184608076040816e-05, "epoch": 1.7339449541284404, "percentage": 17.34, "elapsed_time": "0:11:12", "remaining_time": "0:53:24", "throughput": 2643.82, "total_tokens": 1776944} {"current_steps": 6620, "total_steps": 38150, "loss": 0.4373, "lr": 4.918170833083967e-05, "epoch": 1.7352555701179555, "percentage": 17.35, "elapsed_time": "0:11:12", "remaining_time": "0:53:23", "throughput": 2644.14, "total_tokens": 1778432} {"current_steps": 6625, "total_steps": 38150, "loss": 0.5407, "lr": 4.9178803524448756e-05, "epoch": 1.7365661861074706, "percentage": 17.37, "elapsed_time": "0:11:13", "remaining_time": "0:53:22", "throughput": 2644.03, "total_tokens": 1779520} {"current_steps": 6630, "total_steps": 38150, "loss": 0.7205, "lr": 4.9175893657476046e-05, "epoch": 1.7378768020969857, "percentage": 17.38, "elapsed_time": "0:11:13", "remaining_time": "0:53:21", "throughput": 2644.17, "total_tokens": 1780864} {"current_steps": 6635, "total_steps": 38150, "loss": 0.4595, "lr": 4.917297873053056e-05, "epoch": 1.7391874180865008, "percentage": 17.39, "elapsed_time": "0:11:14", "remaining_time": "0:53:21", "throughput": 2644.64, "total_tokens": 1782608} {"current_steps": 6640, "total_steps": 38150, "loss": 0.4745, "lr": 4.91700587442224e-05, "epoch": 1.7404980340760159, "percentage": 17.4, "elapsed_time": "0:11:14", "remaining_time": "0:53:20", "throughput": 2644.53, "total_tokens": 1783680} {"current_steps": 6645, "total_steps": 38150, "loss": 0.5299, "lr": 4.91671336991627e-05, "epoch": 1.7418086500655308, "percentage": 17.42, "elapsed_time": "0:11:14", "remaining_time": "0:53:19", "throughput": 2644.38, "total_tokens": 1784720} {"current_steps": 6650, "total_steps": 38150, "loss": 0.6534, "lr": 4.916420359596368e-05, "epoch": 1.7431192660550459, "percentage": 17.43, "elapsed_time": "0:11:15", "remaining_time": "0:53:19", "throughput": 2644.25, "total_tokens": 1785792} {"current_steps": 6655, "total_steps": 38150, "loss": 0.3575, "lr": 4.91612684352386e-05, "epoch": 1.744429882044561, "percentage": 17.44, "elapsed_time": "0:11:15", "remaining_time": "0:53:18", "throughput": 2644.32, "total_tokens": 1787008} {"current_steps": 6660, "total_steps": 38150, "loss": 0.3958, "lr": 4.915832821760178e-05, "epoch": 1.745740498034076, "percentage": 17.46, "elapsed_time": "0:11:16", "remaining_time": "0:53:17", "throughput": 2644.51, "total_tokens": 1788384} {"current_steps": 6665, "total_steps": 38150, "loss": 0.7378, "lr": 4.915538294366861e-05, "epoch": 1.747051114023591, "percentage": 17.47, "elapsed_time": "0:11:16", "remaining_time": "0:53:16", "throughput": 2644.87, "total_tokens": 1789888} {"current_steps": 6670, "total_steps": 38150, "loss": 0.4678, "lr": 4.915243261405553e-05, "epoch": 1.748361730013106, "percentage": 17.48, "elapsed_time": "0:11:17", "remaining_time": "0:53:16", "throughput": 2644.94, "total_tokens": 1791088} {"current_steps": 6675, "total_steps": 38150, "loss": 0.4892, "lr": 4.9149477229380023e-05, "epoch": 1.7496723460026211, "percentage": 17.5, "elapsed_time": "0:11:17", "remaining_time": "0:53:15", "throughput": 2645.12, "total_tokens": 1792384} {"current_steps": 6680, "total_steps": 38150, "loss": 0.5519, "lr": 4.914651679026068e-05, "epoch": 1.7509829619921362, "percentage": 17.51, "elapsed_time": "0:11:18", "remaining_time": "0:53:14", "throughput": 2645.32, "total_tokens": 1793776} {"current_steps": 6685, "total_steps": 38150, "loss": 0.3658, "lr": 4.9143551297317076e-05, "epoch": 1.7522935779816513, "percentage": 17.52, "elapsed_time": "0:11:18", "remaining_time": "0:53:13", "throughput": 2645.23, "total_tokens": 1794880} {"current_steps": 6690, "total_steps": 38150, "loss": 0.3853, "lr": 4.9140580751169906e-05, "epoch": 1.7536041939711664, "percentage": 17.54, "elapsed_time": "0:11:18", "remaining_time": "0:53:12", "throughput": 2645.2, "total_tokens": 1796016} {"current_steps": 6695, "total_steps": 38150, "loss": 0.5429, "lr": 4.91376051524409e-05, "epoch": 1.7549148099606815, "percentage": 17.55, "elapsed_time": "0:11:19", "remaining_time": "0:53:12", "throughput": 2645.31, "total_tokens": 1797264} {"current_steps": 6700, "total_steps": 38150, "loss": 0.36, "lr": 4.913462450175285e-05, "epoch": 1.7562254259501966, "percentage": 17.56, "elapsed_time": "0:11:19", "remaining_time": "0:53:11", "throughput": 2645.25, "total_tokens": 1798368} {"current_steps": 6705, "total_steps": 38150, "loss": 0.3876, "lr": 4.913163879972957e-05, "epoch": 1.7575360419397117, "percentage": 17.58, "elapsed_time": "0:11:20", "remaining_time": "0:53:10", "throughput": 2645.54, "total_tokens": 1799744} {"current_steps": 6710, "total_steps": 38150, "loss": 0.4997, "lr": 4.9128648046996004e-05, "epoch": 1.7588466579292268, "percentage": 17.59, "elapsed_time": "0:11:20", "remaining_time": "0:53:09", "throughput": 2645.56, "total_tokens": 1800992} {"current_steps": 6715, "total_steps": 38150, "loss": 0.5297, "lr": 4.912565224417809e-05, "epoch": 1.7601572739187419, "percentage": 17.6, "elapsed_time": "0:11:21", "remaining_time": "0:53:09", "throughput": 2646.03, "total_tokens": 1802640} {"current_steps": 6720, "total_steps": 38150, "loss": 0.3772, "lr": 4.9122651391902855e-05, "epoch": 1.761467889908257, "percentage": 17.61, "elapsed_time": "0:11:21", "remaining_time": "0:53:08", "throughput": 2646.19, "total_tokens": 1803920} {"current_steps": 6725, "total_steps": 38150, "loss": 0.5314, "lr": 4.9119645490798347e-05, "epoch": 1.762778505897772, "percentage": 17.63, "elapsed_time": "0:11:22", "remaining_time": "0:53:07", "throughput": 2646.2, "total_tokens": 1805088} {"current_steps": 6730, "total_steps": 38150, "loss": 0.6178, "lr": 4.911663454149372e-05, "epoch": 1.7640891218872872, "percentage": 17.64, "elapsed_time": "0:11:22", "remaining_time": "0:53:06", "throughput": 2646.44, "total_tokens": 1806512} {"current_steps": 6735, "total_steps": 38150, "loss": 0.6562, "lr": 4.911361854461916e-05, "epoch": 1.765399737876802, "percentage": 17.65, "elapsed_time": "0:11:23", "remaining_time": "0:53:06", "throughput": 2646.94, "total_tokens": 1808064} {"current_steps": 6740, "total_steps": 38150, "loss": 0.2593, "lr": 4.91105975008059e-05, "epoch": 1.7667103538663171, "percentage": 17.67, "elapsed_time": "0:11:23", "remaining_time": "0:53:05", "throughput": 2646.96, "total_tokens": 1809216} {"current_steps": 6745, "total_steps": 38150, "loss": 0.472, "lr": 4.910757141068624e-05, "epoch": 1.7680209698558322, "percentage": 17.68, "elapsed_time": "0:11:23", "remaining_time": "0:53:04", "throughput": 2646.97, "total_tokens": 1810368} {"current_steps": 6750, "total_steps": 38150, "loss": 0.3699, "lr": 4.910454027489354e-05, "epoch": 1.7693315858453473, "percentage": 17.69, "elapsed_time": "0:11:24", "remaining_time": "0:53:03", "throughput": 2647.46, "total_tokens": 1812000} {"current_steps": 6755, "total_steps": 38150, "loss": 0.5355, "lr": 4.910150409406221e-05, "epoch": 1.7706422018348624, "percentage": 17.71, "elapsed_time": "0:11:24", "remaining_time": "0:53:03", "throughput": 2647.54, "total_tokens": 1813232} {"current_steps": 6760, "total_steps": 38150, "loss": 0.4123, "lr": 4.909846286882772e-05, "epoch": 1.7719528178243773, "percentage": 17.72, "elapsed_time": "0:11:25", "remaining_time": "0:53:02", "throughput": 2647.93, "total_tokens": 1814832} {"current_steps": 6765, "total_steps": 38150, "loss": 0.3869, "lr": 4.909541659982659e-05, "epoch": 1.7732634338138924, "percentage": 17.73, "elapsed_time": "0:11:25", "remaining_time": "0:53:01", "throughput": 2647.68, "total_tokens": 1815808} {"current_steps": 6770, "total_steps": 38150, "loss": 0.3981, "lr": 4.9092365287696396e-05, "epoch": 1.7745740498034075, "percentage": 17.75, "elapsed_time": "0:11:26", "remaining_time": "0:53:00", "throughput": 2648.09, "total_tokens": 1817296} {"current_steps": 6775, "total_steps": 38150, "loss": 0.3364, "lr": 4.908930893307578e-05, "epoch": 1.7758846657929226, "percentage": 17.76, "elapsed_time": "0:11:26", "remaining_time": "0:53:00", "throughput": 2648.18, "total_tokens": 1818528} {"current_steps": 6780, "total_steps": 38150, "loss": 0.4895, "lr": 4.9086247536604425e-05, "epoch": 1.7771952817824377, "percentage": 17.77, "elapsed_time": "0:11:27", "remaining_time": "0:52:59", "throughput": 2648.35, "total_tokens": 1819888} {"current_steps": 6785, "total_steps": 38150, "loss": 0.4091, "lr": 4.908318109892308e-05, "epoch": 1.7785058977719528, "percentage": 17.79, "elapsed_time": "0:11:27", "remaining_time": "0:52:58", "throughput": 2648.52, "total_tokens": 1821232} {"current_steps": 6790, "total_steps": 38150, "loss": 0.4059, "lr": 4.9080109620673546e-05, "epoch": 1.7798165137614679, "percentage": 17.8, "elapsed_time": "0:11:28", "remaining_time": "0:52:57", "throughput": 2648.69, "total_tokens": 1822544} {"current_steps": 6795, "total_steps": 38150, "loss": 0.5584, "lr": 4.9077033102498666e-05, "epoch": 1.781127129750983, "percentage": 17.81, "elapsed_time": "0:11:28", "remaining_time": "0:52:57", "throughput": 2648.68, "total_tokens": 1823712} {"current_steps": 6800, "total_steps": 38150, "loss": 0.4401, "lr": 4.907395154504236e-05, "epoch": 1.782437745740498, "percentage": 17.82, "elapsed_time": "0:11:28", "remaining_time": "0:52:56", "throughput": 2648.52, "total_tokens": 1824736} {"current_steps": 6805, "total_steps": 38150, "loss": 0.3558, "lr": 4.9070864948949604e-05, "epoch": 1.7837483617300132, "percentage": 17.84, "elapsed_time": "0:11:29", "remaining_time": "0:52:55", "throughput": 2648.57, "total_tokens": 1825920} {"current_steps": 6810, "total_steps": 38150, "loss": 0.5049, "lr": 4.9067773314866396e-05, "epoch": 1.7850589777195283, "percentage": 17.85, "elapsed_time": "0:11:29", "remaining_time": "0:52:54", "throughput": 2648.61, "total_tokens": 1827104} {"current_steps": 6815, "total_steps": 38150, "loss": 0.3654, "lr": 4.906467664343982e-05, "epoch": 1.7863695937090434, "percentage": 17.86, "elapsed_time": "0:11:30", "remaining_time": "0:52:54", "throughput": 2649.29, "total_tokens": 1829024} {"current_steps": 6820, "total_steps": 38150, "loss": 0.3996, "lr": 4.9061574935318006e-05, "epoch": 1.7876802096985585, "percentage": 17.88, "elapsed_time": "0:11:30", "remaining_time": "0:52:53", "throughput": 2649.47, "total_tokens": 1830336} {"current_steps": 6825, "total_steps": 38150, "loss": 0.4375, "lr": 4.905846819115013e-05, "epoch": 1.7889908256880735, "percentage": 17.89, "elapsed_time": "0:11:31", "remaining_time": "0:52:52", "throughput": 2649.32, "total_tokens": 1831360} {"current_steps": 6830, "total_steps": 38150, "loss": 0.235, "lr": 4.905535641158644e-05, "epoch": 1.7903014416775884, "percentage": 17.9, "elapsed_time": "0:11:31", "remaining_time": "0:52:51", "throughput": 2649.7, "total_tokens": 1832800} {"current_steps": 6835, "total_steps": 38150, "loss": 0.3785, "lr": 4.9052239597278206e-05, "epoch": 1.7916120576671035, "percentage": 17.92, "elapsed_time": "0:11:32", "remaining_time": "0:52:51", "throughput": 2649.46, "total_tokens": 1833792} {"current_steps": 6840, "total_steps": 38150, "loss": 0.4301, "lr": 4.904911774887779e-05, "epoch": 1.7929226736566186, "percentage": 17.93, "elapsed_time": "0:11:32", "remaining_time": "0:52:50", "throughput": 2649.52, "total_tokens": 1835008} {"current_steps": 6845, "total_steps": 38150, "loss": 0.4316, "lr": 4.904599086703858e-05, "epoch": 1.7942332896461337, "percentage": 17.94, "elapsed_time": "0:11:33", "remaining_time": "0:52:49", "throughput": 2649.65, "total_tokens": 1836256} {"current_steps": 6850, "total_steps": 38150, "loss": 0.4564, "lr": 4.904285895241503e-05, "epoch": 1.7955439056356488, "percentage": 17.96, "elapsed_time": "0:11:33", "remaining_time": "0:52:48", "throughput": 2649.66, "total_tokens": 1837408} {"current_steps": 6855, "total_steps": 38150, "loss": 0.5461, "lr": 4.903972200566265e-05, "epoch": 1.7968545216251637, "percentage": 17.97, "elapsed_time": "0:11:33", "remaining_time": "0:52:47", "throughput": 2649.89, "total_tokens": 1838736} {"current_steps": 6860, "total_steps": 38150, "loss": 0.4436, "lr": 4.903658002743798e-05, "epoch": 1.7981651376146788, "percentage": 17.98, "elapsed_time": "0:11:34", "remaining_time": "0:52:47", "throughput": 2650.03, "total_tokens": 1840016} {"current_steps": 6865, "total_steps": 38150, "loss": 0.4894, "lr": 4.9033433018398654e-05, "epoch": 1.7994757536041939, "percentage": 17.99, "elapsed_time": "0:11:34", "remaining_time": "0:52:46", "throughput": 2649.86, "total_tokens": 1841040} {"current_steps": 6870, "total_steps": 38150, "loss": 0.3675, "lr": 4.9030280979203314e-05, "epoch": 1.800786369593709, "percentage": 18.01, "elapsed_time": "0:11:35", "remaining_time": "0:52:45", "throughput": 2649.79, "total_tokens": 1842128} {"current_steps": 6875, "total_steps": 38150, "loss": 0.2298, "lr": 4.90271239105117e-05, "epoch": 1.802096985583224, "percentage": 18.02, "elapsed_time": "0:11:35", "remaining_time": "0:52:44", "throughput": 2650.16, "total_tokens": 1843632} {"current_steps": 6880, "total_steps": 38150, "loss": 0.4957, "lr": 4.902396181298455e-05, "epoch": 1.8034076015727392, "percentage": 18.03, "elapsed_time": "0:11:36", "remaining_time": "0:52:43", "throughput": 2650.07, "total_tokens": 1844704} {"current_steps": 6885, "total_steps": 38150, "loss": 0.5148, "lr": 4.902079468728371e-05, "epoch": 1.8047182175622543, "percentage": 18.05, "elapsed_time": "0:11:36", "remaining_time": "0:52:43", "throughput": 2650.28, "total_tokens": 1846080} {"current_steps": 6890, "total_steps": 38150, "loss": 0.4484, "lr": 4.901762253407205e-05, "epoch": 1.8060288335517694, "percentage": 18.06, "elapsed_time": "0:11:36", "remaining_time": "0:52:42", "throughput": 2650.01, "total_tokens": 1847024} {"current_steps": 6895, "total_steps": 38150, "loss": 0.4711, "lr": 4.9014445354013496e-05, "epoch": 1.8073394495412844, "percentage": 18.07, "elapsed_time": "0:11:37", "remaining_time": "0:52:41", "throughput": 2650.21, "total_tokens": 1848352} {"current_steps": 6900, "total_steps": 38150, "loss": 0.5996, "lr": 4.901126314777301e-05, "epoch": 1.8086500655307995, "percentage": 18.09, "elapsed_time": "0:11:37", "remaining_time": "0:52:40", "throughput": 2650.01, "total_tokens": 1849360} {"current_steps": 6905, "total_steps": 38150, "loss": 0.4712, "lr": 4.9008075916016646e-05, "epoch": 1.8099606815203146, "percentage": 18.1, "elapsed_time": "0:11:38", "remaining_time": "0:52:39", "throughput": 2650.42, "total_tokens": 1850848} {"current_steps": 6910, "total_steps": 38150, "loss": 0.4763, "lr": 4.900488365941147e-05, "epoch": 1.8112712975098297, "percentage": 18.11, "elapsed_time": "0:11:38", "remaining_time": "0:52:39", "throughput": 2650.18, "total_tokens": 1851824} {"current_steps": 6915, "total_steps": 38150, "loss": 0.4406, "lr": 4.900168637862563e-05, "epoch": 1.8125819134993448, "percentage": 18.13, "elapsed_time": "0:11:39", "remaining_time": "0:52:38", "throughput": 2650.25, "total_tokens": 1853056} {"current_steps": 6920, "total_steps": 38150, "loss": 0.4498, "lr": 4.899848407432829e-05, "epoch": 1.81389252948886, "percentage": 18.14, "elapsed_time": "0:11:39", "remaining_time": "0:52:37", "throughput": 2650.52, "total_tokens": 1854480} {"current_steps": 6925, "total_steps": 38150, "loss": 0.4228, "lr": 4.8995276747189714e-05, "epoch": 1.8152031454783748, "percentage": 18.15, "elapsed_time": "0:11:40", "remaining_time": "0:52:37", "throughput": 2651.17, "total_tokens": 1856384} {"current_steps": 6930, "total_steps": 38150, "loss": 0.2889, "lr": 4.899206439788117e-05, "epoch": 1.81651376146789, "percentage": 18.17, "elapsed_time": "0:11:40", "remaining_time": "0:52:36", "throughput": 2651.11, "total_tokens": 1857584} {"current_steps": 6935, "total_steps": 38150, "loss": 0.7707, "lr": 4.898884702707499e-05, "epoch": 1.817824377457405, "percentage": 18.18, "elapsed_time": "0:11:41", "remaining_time": "0:52:35", "throughput": 2651.28, "total_tokens": 1858960} {"current_steps": 6940, "total_steps": 38150, "loss": 0.5675, "lr": 4.898562463544459e-05, "epoch": 1.81913499344692, "percentage": 18.19, "elapsed_time": "0:11:41", "remaining_time": "0:52:35", "throughput": 2651.06, "total_tokens": 1859920} {"current_steps": 6945, "total_steps": 38150, "loss": 0.5555, "lr": 4.89823972236644e-05, "epoch": 1.820445609436435, "percentage": 18.2, "elapsed_time": "0:11:42", "remaining_time": "0:52:34", "throughput": 2651.21, "total_tokens": 1861280} {"current_steps": 6950, "total_steps": 38150, "loss": 0.584, "lr": 4.89791647924099e-05, "epoch": 1.82175622542595, "percentage": 18.22, "elapsed_time": "0:11:42", "remaining_time": "0:52:33", "throughput": 2651.31, "total_tokens": 1862576} {"current_steps": 6955, "total_steps": 38150, "loss": 0.5641, "lr": 4.8975927342357646e-05, "epoch": 1.8230668414154652, "percentage": 18.23, "elapsed_time": "0:11:42", "remaining_time": "0:52:33", "throughput": 2651.77, "total_tokens": 1864192} {"current_steps": 6960, "total_steps": 38150, "loss": 0.4247, "lr": 4.897268487418523e-05, "epoch": 1.8243774574049803, "percentage": 18.24, "elapsed_time": "0:11:43", "remaining_time": "0:52:32", "throughput": 2652.08, "total_tokens": 1865664} {"current_steps": 6965, "total_steps": 38150, "loss": 0.5206, "lr": 4.896943738857128e-05, "epoch": 1.8256880733944953, "percentage": 18.26, "elapsed_time": "0:11:43", "remaining_time": "0:52:31", "throughput": 2652.32, "total_tokens": 1867072} {"current_steps": 6970, "total_steps": 38150, "loss": 0.4323, "lr": 4.896618488619551e-05, "epoch": 1.8269986893840104, "percentage": 18.27, "elapsed_time": "0:11:44", "remaining_time": "0:52:31", "throughput": 2652.22, "total_tokens": 1868160} {"current_steps": 6975, "total_steps": 38150, "loss": 0.4551, "lr": 4.8962927367738655e-05, "epoch": 1.8283093053735255, "percentage": 18.28, "elapsed_time": "0:11:44", "remaining_time": "0:52:30", "throughput": 2651.96, "total_tokens": 1869104} {"current_steps": 6980, "total_steps": 38150, "loss": 0.4155, "lr": 4.89596648338825e-05, "epoch": 1.8296199213630406, "percentage": 18.3, "elapsed_time": "0:11:45", "remaining_time": "0:52:29", "throughput": 2652.21, "total_tokens": 1870448} {"current_steps": 6985, "total_steps": 38150, "loss": 0.6055, "lr": 4.89563972853099e-05, "epoch": 1.8309305373525557, "percentage": 18.31, "elapsed_time": "0:11:45", "remaining_time": "0:52:28", "throughput": 2652.45, "total_tokens": 1871904} {"current_steps": 6990, "total_steps": 38150, "loss": 0.3008, "lr": 4.895312472270475e-05, "epoch": 1.8322411533420708, "percentage": 18.32, "elapsed_time": "0:11:46", "remaining_time": "0:52:27", "throughput": 2652.63, "total_tokens": 1873216} {"current_steps": 6995, "total_steps": 38150, "loss": 0.5842, "lr": 4.894984714675197e-05, "epoch": 1.833551769331586, "percentage": 18.34, "elapsed_time": "0:11:46", "remaining_time": "0:52:27", "throughput": 2652.73, "total_tokens": 1874480} {"current_steps": 7000, "total_steps": 38150, "loss": 0.5178, "lr": 4.8946564558137566e-05, "epoch": 1.834862385321101, "percentage": 18.35, "elapsed_time": "0:11:47", "remaining_time": "0:52:26", "throughput": 2653.17, "total_tokens": 1876064} {"current_steps": 7005, "total_steps": 38150, "loss": 0.2944, "lr": 4.894327695754858e-05, "epoch": 1.8361730013106161, "percentage": 18.36, "elapsed_time": "0:11:47", "remaining_time": "0:52:25", "throughput": 2653.42, "total_tokens": 1877488} {"current_steps": 7010, "total_steps": 38150, "loss": 0.4502, "lr": 4.893998434567309e-05, "epoch": 1.8374836173001312, "percentage": 18.37, "elapsed_time": "0:11:48", "remaining_time": "0:52:25", "throughput": 2653.64, "total_tokens": 1878880} {"current_steps": 7015, "total_steps": 38150, "loss": 0.441, "lr": 4.893668672320025e-05, "epoch": 1.838794233289646, "percentage": 18.39, "elapsed_time": "0:11:48", "remaining_time": "0:52:24", "throughput": 2654.03, "total_tokens": 1880416} {"current_steps": 7020, "total_steps": 38150, "loss": 0.4927, "lr": 4.893338409082023e-05, "epoch": 1.8401048492791612, "percentage": 18.4, "elapsed_time": "0:11:49", "remaining_time": "0:52:24", "throughput": 2653.61, "total_tokens": 1881936} {"current_steps": 7025, "total_steps": 38150, "loss": 0.4503, "lr": 4.8930076449224285e-05, "epoch": 1.8414154652686763, "percentage": 18.41, "elapsed_time": "0:11:49", "remaining_time": "0:52:24", "throughput": 2653.56, "total_tokens": 1883056} {"current_steps": 7030, "total_steps": 38150, "loss": 0.4519, "lr": 4.892676379910468e-05, "epoch": 1.8427260812581914, "percentage": 18.43, "elapsed_time": "0:11:50", "remaining_time": "0:52:23", "throughput": 2653.55, "total_tokens": 1884192} {"current_steps": 7035, "total_steps": 38150, "loss": 0.4078, "lr": 4.8923446141154746e-05, "epoch": 1.8440366972477065, "percentage": 18.44, "elapsed_time": "0:11:50", "remaining_time": "0:52:22", "throughput": 2654.07, "total_tokens": 1885968} {"current_steps": 7040, "total_steps": 38150, "loss": 0.5244, "lr": 4.8920123476068894e-05, "epoch": 1.8453473132372213, "percentage": 18.45, "elapsed_time": "0:11:51", "remaining_time": "0:52:22", "throughput": 2653.95, "total_tokens": 1887024} {"current_steps": 7045, "total_steps": 38150, "loss": 0.5197, "lr": 4.891679580454251e-05, "epoch": 1.8466579292267364, "percentage": 18.47, "elapsed_time": "0:11:51", "remaining_time": "0:52:21", "throughput": 2654.09, "total_tokens": 1888288} {"current_steps": 7050, "total_steps": 38150, "loss": 0.5468, "lr": 4.89134631272721e-05, "epoch": 1.8479685452162515, "percentage": 18.48, "elapsed_time": "0:11:52", "remaining_time": "0:52:20", "throughput": 2654.61, "total_tokens": 1890128} {"current_steps": 7055, "total_steps": 38150, "loss": 0.5916, "lr": 4.891012544495517e-05, "epoch": 1.8492791612057666, "percentage": 18.49, "elapsed_time": "0:11:52", "remaining_time": "0:52:20", "throughput": 2654.87, "total_tokens": 1891584} {"current_steps": 7060, "total_steps": 38150, "loss": 0.4005, "lr": 4.890678275829029e-05, "epoch": 1.8505897771952817, "percentage": 18.51, "elapsed_time": "0:11:52", "remaining_time": "0:52:19", "throughput": 2655.14, "total_tokens": 1892944} {"current_steps": 7065, "total_steps": 38150, "loss": 0.4141, "lr": 4.89034350679771e-05, "epoch": 1.8519003931847968, "percentage": 18.52, "elapsed_time": "0:11:53", "remaining_time": "0:52:18", "throughput": 2655.2, "total_tokens": 1894144} {"current_steps": 7070, "total_steps": 38150, "loss": 0.665, "lr": 4.890008237471625e-05, "epoch": 1.853211009174312, "percentage": 18.53, "elapsed_time": "0:11:53", "remaining_time": "0:52:17", "throughput": 2654.91, "total_tokens": 1895056} {"current_steps": 7075, "total_steps": 38150, "loss": 0.47, "lr": 4.889672467920945e-05, "epoch": 1.854521625163827, "percentage": 18.55, "elapsed_time": "0:11:54", "remaining_time": "0:52:17", "throughput": 2655.06, "total_tokens": 1896416} {"current_steps": 7080, "total_steps": 38150, "loss": 0.5784, "lr": 4.889336198215947e-05, "epoch": 1.855832241153342, "percentage": 18.56, "elapsed_time": "0:11:54", "remaining_time": "0:52:16", "throughput": 2654.92, "total_tokens": 1897456} {"current_steps": 7085, "total_steps": 38150, "loss": 0.4671, "lr": 4.888999428427011e-05, "epoch": 1.8571428571428572, "percentage": 18.57, "elapsed_time": "0:11:55", "remaining_time": "0:52:15", "throughput": 2655.08, "total_tokens": 1898816} {"current_steps": 7090, "total_steps": 38150, "loss": 0.5511, "lr": 4.8886621586246226e-05, "epoch": 1.8584534731323723, "percentage": 18.58, "elapsed_time": "0:11:55", "remaining_time": "0:52:15", "throughput": 2655.24, "total_tokens": 1900176} {"current_steps": 7095, "total_steps": 38150, "loss": 0.3163, "lr": 4.8883243888793715e-05, "epoch": 1.8597640891218874, "percentage": 18.6, "elapsed_time": "0:11:56", "remaining_time": "0:52:14", "throughput": 2655.35, "total_tokens": 1901424} {"current_steps": 7100, "total_steps": 38150, "loss": 0.3249, "lr": 4.887986119261953e-05, "epoch": 1.8610747051114025, "percentage": 18.61, "elapsed_time": "0:11:56", "remaining_time": "0:52:14", "throughput": 2656.2, "total_tokens": 1903616} {"current_steps": 7105, "total_steps": 38150, "loss": 0.3334, "lr": 4.887647349843165e-05, "epoch": 1.8623853211009176, "percentage": 18.62, "elapsed_time": "0:11:57", "remaining_time": "0:52:13", "throughput": 2656.32, "total_tokens": 1904928} {"current_steps": 7110, "total_steps": 38150, "loss": 0.4514, "lr": 4.887308080693913e-05, "epoch": 1.8636959370904325, "percentage": 18.64, "elapsed_time": "0:11:57", "remaining_time": "0:52:14", "throughput": 2657.29, "total_tokens": 1907632} {"current_steps": 7115, "total_steps": 38150, "loss": 0.3851, "lr": 4.886968311885204e-05, "epoch": 1.8650065530799476, "percentage": 18.65, "elapsed_time": "0:11:58", "remaining_time": "0:52:13", "throughput": 2657.17, "total_tokens": 1908672} {"current_steps": 7120, "total_steps": 38150, "loss": 1.016, "lr": 4.8866280434881516e-05, "epoch": 1.8663171690694627, "percentage": 18.66, "elapsed_time": "0:11:58", "remaining_time": "0:52:12", "throughput": 2657.12, "total_tokens": 1909808} {"current_steps": 7125, "total_steps": 38150, "loss": 0.4676, "lr": 4.886287275573974e-05, "epoch": 1.8676277850589778, "percentage": 18.68, "elapsed_time": "0:11:59", "remaining_time": "0:52:11", "throughput": 2657.49, "total_tokens": 1911248} {"current_steps": 7130, "total_steps": 38150, "loss": 0.5536, "lr": 4.885946008213993e-05, "epoch": 1.8689384010484926, "percentage": 18.69, "elapsed_time": "0:11:59", "remaining_time": "0:52:11", "throughput": 2657.73, "total_tokens": 1912688} {"current_steps": 7135, "total_steps": 38150, "loss": 0.5481, "lr": 4.885604241479635e-05, "epoch": 1.8702490170380077, "percentage": 18.7, "elapsed_time": "0:12:00", "remaining_time": "0:52:10", "throughput": 2658.24, "total_tokens": 1914384} {"current_steps": 7140, "total_steps": 38150, "loss": 0.3867, "lr": 4.885261975442431e-05, "epoch": 1.8715596330275228, "percentage": 18.72, "elapsed_time": "0:12:00", "remaining_time": "0:52:09", "throughput": 2658.41, "total_tokens": 1915696} {"current_steps": 7145, "total_steps": 38150, "loss": 0.6435, "lr": 4.884919210174017e-05, "epoch": 1.872870249017038, "percentage": 18.73, "elapsed_time": "0:12:01", "remaining_time": "0:52:09", "throughput": 2658.91, "total_tokens": 1917424} {"current_steps": 7150, "total_steps": 38150, "loss": 0.3624, "lr": 4.8845759457461326e-05, "epoch": 1.874180865006553, "percentage": 18.74, "elapsed_time": "0:12:01", "remaining_time": "0:52:08", "throughput": 2659.2, "total_tokens": 1918800} {"current_steps": 7155, "total_steps": 38150, "loss": 0.3654, "lr": 4.8842321822306235e-05, "epoch": 1.875491480996068, "percentage": 18.75, "elapsed_time": "0:12:02", "remaining_time": "0:52:07", "throughput": 2659.45, "total_tokens": 1920240} {"current_steps": 7160, "total_steps": 38150, "loss": 0.5913, "lr": 4.8838879196994385e-05, "epoch": 1.8768020969855832, "percentage": 18.77, "elapsed_time": "0:12:02", "remaining_time": "0:52:07", "throughput": 2659.73, "total_tokens": 1921696} {"current_steps": 7165, "total_steps": 38150, "loss": 0.6107, "lr": 4.88354315822463e-05, "epoch": 1.8781127129750983, "percentage": 18.78, "elapsed_time": "0:12:02", "remaining_time": "0:52:06", "throughput": 2659.69, "total_tokens": 1922848} {"current_steps": 7170, "total_steps": 38150, "loss": 0.4324, "lr": 4.8831978978783585e-05, "epoch": 1.8794233289646134, "percentage": 18.79, "elapsed_time": "0:12:03", "remaining_time": "0:52:05", "throughput": 2659.89, "total_tokens": 1924160} {"current_steps": 7175, "total_steps": 38150, "loss": 0.4357, "lr": 4.882852138732884e-05, "epoch": 1.8807339449541285, "percentage": 18.81, "elapsed_time": "0:12:03", "remaining_time": "0:52:05", "throughput": 2660.34, "total_tokens": 1925792} {"current_steps": 7180, "total_steps": 38150, "loss": 0.3262, "lr": 4.882505880860574e-05, "epoch": 1.8820445609436436, "percentage": 18.82, "elapsed_time": "0:12:04", "remaining_time": "0:52:04", "throughput": 2660.71, "total_tokens": 1927312} {"current_steps": 7185, "total_steps": 38150, "loss": 0.4171, "lr": 4.8821591243339e-05, "epoch": 1.8833551769331587, "percentage": 18.83, "elapsed_time": "0:12:04", "remaining_time": "0:52:04", "throughput": 2661.42, "total_tokens": 1929248} {"current_steps": 7190, "total_steps": 38150, "loss": 0.3429, "lr": 4.8818118692254375e-05, "epoch": 1.8846657929226738, "percentage": 18.85, "elapsed_time": "0:12:05", "remaining_time": "0:52:03", "throughput": 2661.49, "total_tokens": 1930464} {"current_steps": 7195, "total_steps": 38150, "loss": 0.488, "lr": 4.881464115607865e-05, "epoch": 1.8859764089121889, "percentage": 18.86, "elapsed_time": "0:12:05", "remaining_time": "0:52:02", "throughput": 2661.42, "total_tokens": 1931552} {"current_steps": 7200, "total_steps": 38150, "loss": 0.2718, "lr": 4.88111586355397e-05, "epoch": 1.8872870249017037, "percentage": 18.87, "elapsed_time": "0:12:06", "remaining_time": "0:52:01", "throughput": 2661.5, "total_tokens": 1932768} {"current_steps": 7205, "total_steps": 38150, "loss": 0.3948, "lr": 4.880767113136637e-05, "epoch": 1.8885976408912188, "percentage": 18.89, "elapsed_time": "0:12:06", "remaining_time": "0:52:00", "throughput": 2661.67, "total_tokens": 1934064} {"current_steps": 7210, "total_steps": 38150, "loss": 0.4868, "lr": 4.880417864428862e-05, "epoch": 1.889908256880734, "percentage": 18.9, "elapsed_time": "0:12:07", "remaining_time": "0:52:00", "throughput": 2662.21, "total_tokens": 1935744} {"current_steps": 7215, "total_steps": 38150, "loss": 0.5078, "lr": 4.880068117503741e-05, "epoch": 1.891218872870249, "percentage": 18.91, "elapsed_time": "0:12:07", "remaining_time": "0:51:59", "throughput": 2662.57, "total_tokens": 1937232} {"current_steps": 7220, "total_steps": 38150, "loss": 0.5124, "lr": 4.879717872434475e-05, "epoch": 1.8925294888597641, "percentage": 18.93, "elapsed_time": "0:12:08", "remaining_time": "0:51:58", "throughput": 2662.89, "total_tokens": 1938704} {"current_steps": 7225, "total_steps": 38150, "loss": 0.6806, "lr": 4.879367129294371e-05, "epoch": 1.893840104849279, "percentage": 18.94, "elapsed_time": "0:12:08", "remaining_time": "0:51:58", "throughput": 2662.65, "total_tokens": 1939696} {"current_steps": 7230, "total_steps": 38150, "loss": 0.5547, "lr": 4.879015888156837e-05, "epoch": 1.895150720838794, "percentage": 18.95, "elapsed_time": "0:12:08", "remaining_time": "0:51:57", "throughput": 2662.71, "total_tokens": 1940960} {"current_steps": 7235, "total_steps": 38150, "loss": 0.5603, "lr": 4.8786641490953886e-05, "epoch": 1.8964613368283092, "percentage": 18.96, "elapsed_time": "0:12:09", "remaining_time": "0:51:56", "throughput": 2662.69, "total_tokens": 1942160} {"current_steps": 7240, "total_steps": 38150, "loss": 0.4578, "lr": 4.878311912183644e-05, "epoch": 1.8977719528178243, "percentage": 18.98, "elapsed_time": "0:12:09", "remaining_time": "0:51:56", "throughput": 2663.17, "total_tokens": 1943840} {"current_steps": 7245, "total_steps": 38150, "loss": 0.3062, "lr": 4.877959177495326e-05, "epoch": 1.8990825688073394, "percentage": 18.99, "elapsed_time": "0:12:10", "remaining_time": "0:51:55", "throughput": 2663.05, "total_tokens": 1944896} {"current_steps": 7250, "total_steps": 38150, "loss": 0.5118, "lr": 4.87760594510426e-05, "epoch": 1.9003931847968545, "percentage": 19.0, "elapsed_time": "0:12:10", "remaining_time": "0:51:54", "throughput": 2662.9, "total_tokens": 1945952} {"current_steps": 7255, "total_steps": 38150, "loss": 0.445, "lr": 4.877252215084379e-05, "epoch": 1.9017038007863696, "percentage": 19.02, "elapsed_time": "0:12:11", "remaining_time": "0:51:53", "throughput": 2662.87, "total_tokens": 1947072} {"current_steps": 7260, "total_steps": 38150, "loss": 0.3714, "lr": 4.876897987509716e-05, "epoch": 1.9030144167758847, "percentage": 19.03, "elapsed_time": "0:12:11", "remaining_time": "0:51:52", "throughput": 2662.78, "total_tokens": 1948128} {"current_steps": 7265, "total_steps": 38150, "loss": 0.498, "lr": 4.876543262454412e-05, "epoch": 1.9043250327653998, "percentage": 19.04, "elapsed_time": "0:12:12", "remaining_time": "0:51:52", "throughput": 2662.83, "total_tokens": 1949344} {"current_steps": 7270, "total_steps": 38150, "loss": 0.4699, "lr": 4.8761880399927084e-05, "epoch": 1.9056356487549149, "percentage": 19.06, "elapsed_time": "0:12:12", "remaining_time": "0:51:51", "throughput": 2663.15, "total_tokens": 1950848} {"current_steps": 7275, "total_steps": 38150, "loss": 0.4883, "lr": 4.875832320198954e-05, "epoch": 1.90694626474443, "percentage": 19.07, "elapsed_time": "0:12:12", "remaining_time": "0:51:50", "throughput": 2663.03, "total_tokens": 1951904} {"current_steps": 7280, "total_steps": 38150, "loss": 0.565, "lr": 4.8754761031476005e-05, "epoch": 1.908256880733945, "percentage": 19.08, "elapsed_time": "0:12:13", "remaining_time": "0:51:50", "throughput": 2663.52, "total_tokens": 1953664} {"current_steps": 7285, "total_steps": 38150, "loss": 0.4738, "lr": 4.875119388913203e-05, "epoch": 1.9095674967234602, "percentage": 19.1, "elapsed_time": "0:12:14", "remaining_time": "0:51:49", "throughput": 2663.89, "total_tokens": 1955328} {"current_steps": 7290, "total_steps": 38150, "loss": 0.4558, "lr": 4.874762177570422e-05, "epoch": 1.9108781127129753, "percentage": 19.11, "elapsed_time": "0:12:14", "remaining_time": "0:51:49", "throughput": 2664.05, "total_tokens": 1956624} {"current_steps": 7295, "total_steps": 38150, "loss": 0.4743, "lr": 4.874404469194019e-05, "epoch": 1.9121887287024901, "percentage": 19.12, "elapsed_time": "0:12:14", "remaining_time": "0:51:48", "throughput": 2664.16, "total_tokens": 1957872} {"current_steps": 7300, "total_steps": 38150, "loss": 0.3227, "lr": 4.8740462638588644e-05, "epoch": 1.9134993446920052, "percentage": 19.13, "elapsed_time": "0:12:15", "remaining_time": "0:51:47", "throughput": 2663.97, "total_tokens": 1958864} {"current_steps": 7305, "total_steps": 38150, "loss": 0.5353, "lr": 4.873687561639929e-05, "epoch": 1.9148099606815203, "percentage": 19.15, "elapsed_time": "0:12:15", "remaining_time": "0:51:46", "throughput": 2664.13, "total_tokens": 1960160} {"current_steps": 7310, "total_steps": 38150, "loss": 0.6231, "lr": 4.8733283626122875e-05, "epoch": 1.9161205766710354, "percentage": 19.16, "elapsed_time": "0:12:16", "remaining_time": "0:51:45", "throughput": 2664.02, "total_tokens": 1961248} {"current_steps": 7315, "total_steps": 38150, "loss": 0.3777, "lr": 4.872968666851121e-05, "epoch": 1.9174311926605505, "percentage": 19.17, "elapsed_time": "0:12:16", "remaining_time": "0:51:45", "throughput": 2664.03, "total_tokens": 1962400} {"current_steps": 7320, "total_steps": 38150, "loss": 0.546, "lr": 4.872608474431712e-05, "epoch": 1.9187418086500654, "percentage": 19.19, "elapsed_time": "0:12:17", "remaining_time": "0:51:44", "throughput": 2664.71, "total_tokens": 1964352} {"current_steps": 7325, "total_steps": 38150, "loss": 0.3009, "lr": 4.87224778542945e-05, "epoch": 1.9200524246395805, "percentage": 19.2, "elapsed_time": "0:12:17", "remaining_time": "0:51:43", "throughput": 2664.57, "total_tokens": 1965376} {"current_steps": 7330, "total_steps": 38150, "loss": 0.4398, "lr": 4.871886599919825e-05, "epoch": 1.9213630406290956, "percentage": 19.21, "elapsed_time": "0:12:18", "remaining_time": "0:51:43", "throughput": 2664.55, "total_tokens": 1966512} {"current_steps": 7335, "total_steps": 38150, "loss": 0.5583, "lr": 4.871524917978433e-05, "epoch": 1.9226736566186107, "percentage": 19.23, "elapsed_time": "0:12:18", "remaining_time": "0:51:42", "throughput": 2664.89, "total_tokens": 1968112} {"current_steps": 7340, "total_steps": 38150, "loss": 0.3906, "lr": 4.8711627396809725e-05, "epoch": 1.9239842726081258, "percentage": 19.24, "elapsed_time": "0:12:18", "remaining_time": "0:51:41", "throughput": 2665.12, "total_tokens": 1969472} {"current_steps": 7345, "total_steps": 38150, "loss": 0.5405, "lr": 4.870800065103248e-05, "epoch": 1.9252948885976409, "percentage": 19.25, "elapsed_time": "0:12:19", "remaining_time": "0:51:41", "throughput": 2665.3, "total_tokens": 1970768} {"current_steps": 7350, "total_steps": 38150, "loss": 0.6332, "lr": 4.870436894321167e-05, "epoch": 1.926605504587156, "percentage": 19.27, "elapsed_time": "0:12:19", "remaining_time": "0:51:40", "throughput": 2665.76, "total_tokens": 1972432} {"current_steps": 7355, "total_steps": 38150, "loss": 0.7686, "lr": 4.87007322741074e-05, "epoch": 1.927916120576671, "percentage": 19.28, "elapsed_time": "0:12:20", "remaining_time": "0:51:40", "throughput": 2666.14, "total_tokens": 1974128} {"current_steps": 7360, "total_steps": 38150, "loss": 0.3668, "lr": 4.8697090644480804e-05, "epoch": 1.9292267365661862, "percentage": 19.29, "elapsed_time": "0:12:20", "remaining_time": "0:51:39", "throughput": 2666.45, "total_tokens": 1975616} {"current_steps": 7365, "total_steps": 38150, "loss": 0.6144, "lr": 4.86934440550941e-05, "epoch": 1.9305373525557012, "percentage": 19.31, "elapsed_time": "0:12:21", "remaining_time": "0:51:38", "throughput": 2666.56, "total_tokens": 1976944} {"current_steps": 7370, "total_steps": 38150, "loss": 0.5629, "lr": 4.868979250671047e-05, "epoch": 1.9318479685452163, "percentage": 19.32, "elapsed_time": "0:12:21", "remaining_time": "0:51:38", "throughput": 2666.26, "total_tokens": 1977856} {"current_steps": 7375, "total_steps": 38150, "loss": 0.4331, "lr": 4.868613600009422e-05, "epoch": 1.9331585845347314, "percentage": 19.33, "elapsed_time": "0:12:22", "remaining_time": "0:51:37", "throughput": 2666.43, "total_tokens": 1979184} {"current_steps": 7380, "total_steps": 38150, "loss": 0.4027, "lr": 4.8682474536010624e-05, "epoch": 1.9344692005242465, "percentage": 19.34, "elapsed_time": "0:12:22", "remaining_time": "0:51:36", "throughput": 2666.54, "total_tokens": 1980512} {"current_steps": 7385, "total_steps": 38150, "loss": 0.3142, "lr": 4.8678808115226026e-05, "epoch": 1.9357798165137616, "percentage": 19.36, "elapsed_time": "0:12:23", "remaining_time": "0:51:36", "throughput": 2666.75, "total_tokens": 1981936} {"current_steps": 7390, "total_steps": 38150, "loss": 0.4944, "lr": 4.867513673850781e-05, "epoch": 1.9370904325032765, "percentage": 19.37, "elapsed_time": "0:12:23", "remaining_time": "0:51:35", "throughput": 2666.96, "total_tokens": 1983376} {"current_steps": 7395, "total_steps": 38150, "loss": 0.578, "lr": 4.867146040662438e-05, "epoch": 1.9384010484927916, "percentage": 19.38, "elapsed_time": "0:12:24", "remaining_time": "0:51:34", "throughput": 2667.26, "total_tokens": 1984912} {"current_steps": 7400, "total_steps": 38150, "loss": 0.4446, "lr": 4.8667779120345185e-05, "epoch": 1.9397116644823067, "percentage": 19.4, "elapsed_time": "0:12:24", "remaining_time": "0:51:34", "throughput": 2667.31, "total_tokens": 1986112} {"current_steps": 7405, "total_steps": 38150, "loss": 0.4738, "lr": 4.866409288044072e-05, "epoch": 1.9410222804718218, "percentage": 19.41, "elapsed_time": "0:12:25", "remaining_time": "0:51:33", "throughput": 2667.83, "total_tokens": 1987824} {"current_steps": 7410, "total_steps": 38150, "loss": 0.4426, "lr": 4.86604016876825e-05, "epoch": 1.9423328964613367, "percentage": 19.42, "elapsed_time": "0:12:25", "remaining_time": "0:51:32", "throughput": 2667.57, "total_tokens": 1988752} {"current_steps": 7415, "total_steps": 38150, "loss": 0.5628, "lr": 4.8656705542843085e-05, "epoch": 1.9436435124508518, "percentage": 19.44, "elapsed_time": "0:12:26", "remaining_time": "0:51:32", "throughput": 2668.01, "total_tokens": 1990384} {"current_steps": 7420, "total_steps": 38150, "loss": 0.6938, "lr": 4.865300444669608e-05, "epoch": 1.9449541284403669, "percentage": 19.45, "elapsed_time": "0:12:26", "remaining_time": "0:51:31", "throughput": 2667.97, "total_tokens": 1991504} {"current_steps": 7425, "total_steps": 38150, "loss": 0.3184, "lr": 4.864929840001612e-05, "epoch": 1.946264744429882, "percentage": 19.46, "elapsed_time": "0:12:26", "remaining_time": "0:51:30", "throughput": 2668.31, "total_tokens": 1993040} {"current_steps": 7430, "total_steps": 38150, "loss": 0.3466, "lr": 4.8645587403578855e-05, "epoch": 1.947575360419397, "percentage": 19.48, "elapsed_time": "0:12:27", "remaining_time": "0:51:30", "throughput": 2668.27, "total_tokens": 1994176} {"current_steps": 7435, "total_steps": 38150, "loss": 0.3685, "lr": 4.864187145816101e-05, "epoch": 1.9488859764089121, "percentage": 19.49, "elapsed_time": "0:12:27", "remaining_time": "0:51:29", "throughput": 2668.15, "total_tokens": 1995232} {"current_steps": 7440, "total_steps": 38150, "loss": 0.6535, "lr": 4.863815056454032e-05, "epoch": 1.9501965923984272, "percentage": 19.5, "elapsed_time": "0:12:28", "remaining_time": "0:51:28", "throughput": 2668.22, "total_tokens": 1996464} {"current_steps": 7445, "total_steps": 38150, "loss": 0.3803, "lr": 4.863442472349555e-05, "epoch": 1.9515072083879423, "percentage": 19.52, "elapsed_time": "0:12:28", "remaining_time": "0:51:27", "throughput": 2668.07, "total_tokens": 1997488} {"current_steps": 7450, "total_steps": 38150, "loss": 0.4319, "lr": 4.8630693935806536e-05, "epoch": 1.9528178243774574, "percentage": 19.53, "elapsed_time": "0:12:29", "remaining_time": "0:51:26", "throughput": 2668.05, "total_tokens": 1998608} {"current_steps": 7455, "total_steps": 38150, "loss": 0.6473, "lr": 4.8626958202254106e-05, "epoch": 1.9541284403669725, "percentage": 19.54, "elapsed_time": "0:12:29", "remaining_time": "0:51:26", "throughput": 2668.01, "total_tokens": 1999728} {"current_steps": 7460, "total_steps": 38150, "loss": 0.5921, "lr": 4.862321752362015e-05, "epoch": 1.9554390563564876, "percentage": 19.55, "elapsed_time": "0:12:29", "remaining_time": "0:51:25", "throughput": 2667.97, "total_tokens": 2000848} {"current_steps": 7465, "total_steps": 38150, "loss": 0.7304, "lr": 4.8619471900687583e-05, "epoch": 1.9567496723460027, "percentage": 19.57, "elapsed_time": "0:12:30", "remaining_time": "0:51:24", "throughput": 2667.76, "total_tokens": 2001840} {"current_steps": 7470, "total_steps": 38150, "loss": 0.4053, "lr": 4.861572133424036e-05, "epoch": 1.9580602883355178, "percentage": 19.58, "elapsed_time": "0:12:30", "remaining_time": "0:51:23", "throughput": 2667.85, "total_tokens": 2003072} {"current_steps": 7475, "total_steps": 38150, "loss": 0.4924, "lr": 4.8611965825063466e-05, "epoch": 1.959370904325033, "percentage": 19.59, "elapsed_time": "0:12:31", "remaining_time": "0:51:23", "throughput": 2668.02, "total_tokens": 2004448} {"current_steps": 7480, "total_steps": 38150, "loss": 0.4546, "lr": 4.8608205373942915e-05, "epoch": 1.9606815203145478, "percentage": 19.61, "elapsed_time": "0:12:31", "remaining_time": "0:51:22", "throughput": 2667.89, "total_tokens": 2005472} {"current_steps": 7485, "total_steps": 38150, "loss": 0.3472, "lr": 4.860443998166578e-05, "epoch": 1.9619921363040629, "percentage": 19.62, "elapsed_time": "0:12:32", "remaining_time": "0:51:21", "throughput": 2668.01, "total_tokens": 2006752} {"current_steps": 7490, "total_steps": 38150, "loss": 0.5099, "lr": 4.860066964902014e-05, "epoch": 1.963302752293578, "percentage": 19.63, "elapsed_time": "0:12:32", "remaining_time": "0:51:20", "throughput": 2668.09, "total_tokens": 2008048} {"current_steps": 7495, "total_steps": 38150, "loss": 0.5158, "lr": 4.859689437679512e-05, "epoch": 1.964613368283093, "percentage": 19.65, "elapsed_time": "0:12:33", "remaining_time": "0:51:20", "throughput": 2668.36, "total_tokens": 2009520} {"current_steps": 7500, "total_steps": 38150, "loss": 0.4353, "lr": 4.859311416578088e-05, "epoch": 1.9659239842726082, "percentage": 19.66, "elapsed_time": "0:12:33", "remaining_time": "0:51:19", "throughput": 2668.55, "total_tokens": 2010848} {"current_steps": 7505, "total_steps": 38150, "loss": 0.7076, "lr": 4.8589329016768615e-05, "epoch": 1.967234600262123, "percentage": 19.67, "elapsed_time": "0:12:33", "remaining_time": "0:51:18", "throughput": 2668.91, "total_tokens": 2012336} {"current_steps": 7510, "total_steps": 38150, "loss": 0.5284, "lr": 4.8585538930550547e-05, "epoch": 1.9685452162516381, "percentage": 19.69, "elapsed_time": "0:12:34", "remaining_time": "0:51:18", "throughput": 2669.27, "total_tokens": 2013872} {"current_steps": 7515, "total_steps": 38150, "loss": 0.3982, "lr": 4.858174390791993e-05, "epoch": 1.9698558322411532, "percentage": 19.7, "elapsed_time": "0:12:34", "remaining_time": "0:51:17", "throughput": 2669.29, "total_tokens": 2015040} {"current_steps": 7520, "total_steps": 38150, "loss": 0.3339, "lr": 4.857794394967106e-05, "epoch": 1.9711664482306683, "percentage": 19.71, "elapsed_time": "0:12:35", "remaining_time": "0:51:16", "throughput": 2669.28, "total_tokens": 2016256} {"current_steps": 7525, "total_steps": 38150, "loss": 0.3635, "lr": 4.8574139056599256e-05, "epoch": 1.9724770642201834, "percentage": 19.72, "elapsed_time": "0:12:35", "remaining_time": "0:51:16", "throughput": 2669.71, "total_tokens": 2017984} {"current_steps": 7530, "total_steps": 38150, "loss": 0.5411, "lr": 4.8570329229500884e-05, "epoch": 1.9737876802096985, "percentage": 19.74, "elapsed_time": "0:12:36", "remaining_time": "0:51:15", "throughput": 2669.96, "total_tokens": 2019488} {"current_steps": 7535, "total_steps": 38150, "loss": 0.3798, "lr": 4.8566514469173326e-05, "epoch": 1.9750982961992136, "percentage": 19.75, "elapsed_time": "0:12:36", "remaining_time": "0:51:15", "throughput": 2669.96, "total_tokens": 2020736} {"current_steps": 7540, "total_steps": 38150, "loss": 0.4181, "lr": 4.8562694776415016e-05, "epoch": 1.9764089121887287, "percentage": 19.76, "elapsed_time": "0:12:37", "remaining_time": "0:51:14", "throughput": 2670.26, "total_tokens": 2022240} {"current_steps": 7545, "total_steps": 38150, "loss": 0.7083, "lr": 4.8558870152025404e-05, "epoch": 1.9777195281782438, "percentage": 19.78, "elapsed_time": "0:12:37", "remaining_time": "0:51:14", "throughput": 2670.59, "total_tokens": 2023936} {"current_steps": 7550, "total_steps": 38150, "loss": 0.3999, "lr": 4.855504059680497e-05, "epoch": 1.979030144167759, "percentage": 19.79, "elapsed_time": "0:12:38", "remaining_time": "0:51:13", "throughput": 2670.77, "total_tokens": 2025248} {"current_steps": 7555, "total_steps": 38150, "loss": 0.3243, "lr": 4.855120611155524e-05, "epoch": 1.980340760157274, "percentage": 19.8, "elapsed_time": "0:12:38", "remaining_time": "0:51:12", "throughput": 2671.22, "total_tokens": 2026960} {"current_steps": 7560, "total_steps": 38150, "loss": 0.4281, "lr": 4.854736669707876e-05, "epoch": 1.981651376146789, "percentage": 19.82, "elapsed_time": "0:12:39", "remaining_time": "0:51:12", "throughput": 2671.5, "total_tokens": 2028384} {"current_steps": 7565, "total_steps": 38150, "loss": 0.521, "lr": 4.854352235417913e-05, "epoch": 1.9829619921363042, "percentage": 19.83, "elapsed_time": "0:12:39", "remaining_time": "0:51:11", "throughput": 2671.76, "total_tokens": 2029856} {"current_steps": 7570, "total_steps": 38150, "loss": 0.3568, "lr": 4.853967308366094e-05, "epoch": 1.9842726081258193, "percentage": 19.84, "elapsed_time": "0:12:40", "remaining_time": "0:51:10", "throughput": 2671.88, "total_tokens": 2031104} {"current_steps": 7575, "total_steps": 38150, "loss": 0.5399, "lr": 4.8535818886329855e-05, "epoch": 1.9855832241153342, "percentage": 19.86, "elapsed_time": "0:12:40", "remaining_time": "0:51:10", "throughput": 2671.99, "total_tokens": 2032368} {"current_steps": 7580, "total_steps": 38150, "loss": 0.4129, "lr": 4.853195976299254e-05, "epoch": 1.9868938401048493, "percentage": 19.87, "elapsed_time": "0:12:41", "remaining_time": "0:51:09", "throughput": 2672.01, "total_tokens": 2033536} {"current_steps": 7585, "total_steps": 38150, "loss": 0.4641, "lr": 4.85280957144567e-05, "epoch": 1.9882044560943644, "percentage": 19.88, "elapsed_time": "0:12:41", "remaining_time": "0:51:09", "throughput": 2672.67, "total_tokens": 2035600} {"current_steps": 7590, "total_steps": 38150, "loss": 0.5591, "lr": 4.852422674153109e-05, "epoch": 1.9895150720838795, "percentage": 19.9, "elapsed_time": "0:12:42", "remaining_time": "0:51:08", "throughput": 2672.87, "total_tokens": 2036928} {"current_steps": 7595, "total_steps": 38150, "loss": 0.3377, "lr": 4.852035284502547e-05, "epoch": 1.9908256880733946, "percentage": 19.91, "elapsed_time": "0:12:42", "remaining_time": "0:51:07", "throughput": 2672.91, "total_tokens": 2038144} {"current_steps": 7600, "total_steps": 38150, "loss": 0.5126, "lr": 4.851647402575063e-05, "epoch": 1.9921363040629094, "percentage": 19.92, "elapsed_time": "0:12:42", "remaining_time": "0:51:06", "throughput": 2672.93, "total_tokens": 2039328} {"current_steps": 7605, "total_steps": 38150, "loss": 0.5164, "lr": 4.851259028451842e-05, "epoch": 1.9934469200524245, "percentage": 19.93, "elapsed_time": "0:12:43", "remaining_time": "0:51:06", "throughput": 2672.94, "total_tokens": 2040496} {"current_steps": 7610, "total_steps": 38150, "loss": 0.4688, "lr": 4.850870162214168e-05, "epoch": 1.9947575360419396, "percentage": 19.95, "elapsed_time": "0:12:43", "remaining_time": "0:51:05", "throughput": 2673.13, "total_tokens": 2041904} {"current_steps": 7615, "total_steps": 38150, "loss": 0.6058, "lr": 4.850480803943432e-05, "epoch": 1.9960681520314547, "percentage": 19.96, "elapsed_time": "0:12:44", "remaining_time": "0:51:04", "throughput": 2673.37, "total_tokens": 2043376} {"current_steps": 7620, "total_steps": 38150, "loss": 0.4699, "lr": 4.8500909537211246e-05, "epoch": 1.9973787680209698, "percentage": 19.97, "elapsed_time": "0:12:44", "remaining_time": "0:51:04", "throughput": 2673.49, "total_tokens": 2044736} {"current_steps": 7625, "total_steps": 38150, "loss": 0.345, "lr": 4.849700611628841e-05, "epoch": 1.998689384010485, "percentage": 19.99, "elapsed_time": "0:12:45", "remaining_time": "0:51:03", "throughput": 2673.66, "total_tokens": 2046016} {"current_steps": 7630, "total_steps": 38150, "loss": 0.5013, "lr": 4.84930977774828e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:12:45", "remaining_time": "0:51:03", "throughput": 2673.25, "total_tokens": 2047128} {"current_steps": 7632, "total_steps": 38150, "eval_loss": 0.4960760176181793, "epoch": 2.000524246395806, "percentage": 20.01, "elapsed_time": "0:13:03", "remaining_time": "0:52:11", "throughput": 2614.48, "total_tokens": 2047464} {"current_steps": 7635, "total_steps": 38150, "loss": 0.4151, "lr": 4.8489184521612416e-05, "epoch": 2.001310615989515, "percentage": 20.01, "elapsed_time": "0:13:05", "remaining_time": "0:52:17", "throughput": 2609.22, "total_tokens": 2048456} {"current_steps": 7640, "total_steps": 38150, "loss": 0.4935, "lr": 4.848526634949629e-05, "epoch": 2.00262123197903, "percentage": 20.03, "elapsed_time": "0:13:05", "remaining_time": "0:52:16", "throughput": 2608.96, "total_tokens": 2049368} {"current_steps": 7645, "total_steps": 38150, "loss": 0.3583, "lr": 4.848134326195451e-05, "epoch": 2.0039318479685453, "percentage": 20.04, "elapsed_time": "0:13:05", "remaining_time": "0:52:16", "throughput": 2609.12, "total_tokens": 2050728} {"current_steps": 7650, "total_steps": 38150, "loss": 0.3566, "lr": 4.847741525980815e-05, "epoch": 2.0052424639580604, "percentage": 20.05, "elapsed_time": "0:13:06", "remaining_time": "0:52:15", "throughput": 2609.09, "total_tokens": 2051864} {"current_steps": 7655, "total_steps": 38150, "loss": 0.6319, "lr": 4.8473482343879344e-05, "epoch": 2.0065530799475755, "percentage": 20.07, "elapsed_time": "0:13:06", "remaining_time": "0:52:14", "throughput": 2609.29, "total_tokens": 2053240} {"current_steps": 7660, "total_steps": 38150, "loss": 0.4577, "lr": 4.8469544514991235e-05, "epoch": 2.0078636959370906, "percentage": 20.08, "elapsed_time": "0:13:07", "remaining_time": "0:52:13", "throughput": 2609.16, "total_tokens": 2054280} {"current_steps": 7665, "total_steps": 38150, "loss": 0.3051, "lr": 4.846560177396802e-05, "epoch": 2.0091743119266057, "percentage": 20.09, "elapsed_time": "0:13:07", "remaining_time": "0:52:13", "throughput": 2609.16, "total_tokens": 2055400} {"current_steps": 7670, "total_steps": 38150, "loss": 0.4865, "lr": 4.8461654121634905e-05, "epoch": 2.0104849279161208, "percentage": 20.1, "elapsed_time": "0:13:08", "remaining_time": "0:52:12", "throughput": 2609.51, "total_tokens": 2056952} {"current_steps": 7675, "total_steps": 38150, "loss": 0.381, "lr": 4.8457701558818106e-05, "epoch": 2.011795543905636, "percentage": 20.12, "elapsed_time": "0:13:08", "remaining_time": "0:52:11", "throughput": 2609.52, "total_tokens": 2058104} {"current_steps": 7680, "total_steps": 38150, "loss": 0.349, "lr": 4.845374408634491e-05, "epoch": 2.0131061598951505, "percentage": 20.13, "elapsed_time": "0:13:09", "remaining_time": "0:52:10", "throughput": 2609.51, "total_tokens": 2059224} {"current_steps": 7685, "total_steps": 38150, "loss": 0.4083, "lr": 4.84497817050436e-05, "epoch": 2.0144167758846656, "percentage": 20.14, "elapsed_time": "0:13:09", "remaining_time": "0:52:10", "throughput": 2609.82, "total_tokens": 2060776} {"current_steps": 7690, "total_steps": 38150, "loss": 0.5723, "lr": 4.8445814415743504e-05, "epoch": 2.0157273918741807, "percentage": 20.16, "elapsed_time": "0:13:10", "remaining_time": "0:52:09", "throughput": 2609.91, "total_tokens": 2062120} {"current_steps": 7695, "total_steps": 38150, "loss": 0.3991, "lr": 4.844184221927495e-05, "epoch": 2.017038007863696, "percentage": 20.17, "elapsed_time": "0:13:10", "remaining_time": "0:52:08", "throughput": 2609.83, "total_tokens": 2063208} {"current_steps": 7700, "total_steps": 38150, "loss": 0.6443, "lr": 4.843786511646933e-05, "epoch": 2.018348623853211, "percentage": 20.18, "elapsed_time": "0:13:11", "remaining_time": "0:52:08", "throughput": 2610.39, "total_tokens": 2065096} {"current_steps": 7705, "total_steps": 38150, "loss": 0.5346, "lr": 4.843388310815904e-05, "epoch": 2.019659239842726, "percentage": 20.2, "elapsed_time": "0:13:11", "remaining_time": "0:52:08", "throughput": 2611.27, "total_tokens": 2067304} {"current_steps": 7710, "total_steps": 38150, "loss": 0.4206, "lr": 4.8429896195177504e-05, "epoch": 2.020969855832241, "percentage": 20.21, "elapsed_time": "0:13:12", "remaining_time": "0:52:07", "throughput": 2611.56, "total_tokens": 2068728} {"current_steps": 7715, "total_steps": 38150, "loss": 0.51, "lr": 4.842590437835918e-05, "epoch": 2.022280471821756, "percentage": 20.22, "elapsed_time": "0:13:12", "remaining_time": "0:52:06", "throughput": 2611.57, "total_tokens": 2069880} {"current_steps": 7720, "total_steps": 38150, "loss": 0.3809, "lr": 4.8421907658539545e-05, "epoch": 2.0235910878112713, "percentage": 20.24, "elapsed_time": "0:13:13", "remaining_time": "0:52:05", "throughput": 2611.65, "total_tokens": 2071096} {"current_steps": 7725, "total_steps": 38150, "loss": 0.4317, "lr": 4.84179060365551e-05, "epoch": 2.0249017038007864, "percentage": 20.25, "elapsed_time": "0:13:13", "remaining_time": "0:52:06", "throughput": 2612.95, "total_tokens": 2074312} {"current_steps": 7730, "total_steps": 38150, "loss": 0.5679, "lr": 4.84138995132434e-05, "epoch": 2.0262123197903015, "percentage": 20.26, "elapsed_time": "0:13:14", "remaining_time": "0:52:05", "throughput": 2613.23, "total_tokens": 2075688} {"current_steps": 7735, "total_steps": 38150, "loss": 0.3894, "lr": 4.840988808944298e-05, "epoch": 2.0275229357798166, "percentage": 20.28, "elapsed_time": "0:13:14", "remaining_time": "0:52:05", "throughput": 2613.18, "total_tokens": 2076808} {"current_steps": 7740, "total_steps": 38150, "loss": 0.3782, "lr": 4.8405871765993433e-05, "epoch": 2.0288335517693317, "percentage": 20.29, "elapsed_time": "0:13:15", "remaining_time": "0:52:04", "throughput": 2613.59, "total_tokens": 2078440} {"current_steps": 7745, "total_steps": 38150, "loss": 0.4853, "lr": 4.840185054373536e-05, "epoch": 2.0301441677588468, "percentage": 20.3, "elapsed_time": "0:13:15", "remaining_time": "0:52:03", "throughput": 2613.6, "total_tokens": 2079656} {"current_steps": 7750, "total_steps": 38150, "loss": 0.5816, "lr": 4.839782442351042e-05, "epoch": 2.031454783748362, "percentage": 20.31, "elapsed_time": "0:13:16", "remaining_time": "0:52:02", "throughput": 2613.49, "total_tokens": 2080712} {"current_steps": 7755, "total_steps": 38150, "loss": 0.4526, "lr": 4.839379340616124e-05, "epoch": 2.032765399737877, "percentage": 20.33, "elapsed_time": "0:13:16", "remaining_time": "0:52:02", "throughput": 2613.73, "total_tokens": 2082088} {"current_steps": 7760, "total_steps": 38150, "loss": 0.4667, "lr": 4.838975749253153e-05, "epoch": 2.034076015727392, "percentage": 20.34, "elapsed_time": "0:13:17", "remaining_time": "0:52:01", "throughput": 2613.75, "total_tokens": 2083208} {"current_steps": 7765, "total_steps": 38150, "loss": 0.42, "lr": 4.838571668346599e-05, "epoch": 2.035386631716907, "percentage": 20.35, "elapsed_time": "0:13:17", "remaining_time": "0:52:00", "throughput": 2613.72, "total_tokens": 2084312} {"current_steps": 7770, "total_steps": 38150, "loss": 0.3791, "lr": 4.838167097981036e-05, "epoch": 2.036697247706422, "percentage": 20.37, "elapsed_time": "0:13:17", "remaining_time": "0:51:59", "throughput": 2614.12, "total_tokens": 2085880} {"current_steps": 7775, "total_steps": 38150, "loss": 0.4417, "lr": 4.8377620382411385e-05, "epoch": 2.038007863695937, "percentage": 20.38, "elapsed_time": "0:13:18", "remaining_time": "0:51:59", "throughput": 2614.2, "total_tokens": 2087080} {"current_steps": 7780, "total_steps": 38150, "loss": 0.4089, "lr": 4.837356489211686e-05, "epoch": 2.039318479685452, "percentage": 20.39, "elapsed_time": "0:13:18", "remaining_time": "0:51:58", "throughput": 2614.32, "total_tokens": 2088440} {"current_steps": 7785, "total_steps": 38150, "loss": 0.412, "lr": 4.836950450977559e-05, "epoch": 2.040629095674967, "percentage": 20.41, "elapsed_time": "0:13:19", "remaining_time": "0:51:57", "throughput": 2614.18, "total_tokens": 2089432} {"current_steps": 7790, "total_steps": 38150, "loss": 0.3061, "lr": 4.836543923623741e-05, "epoch": 2.041939711664482, "percentage": 20.42, "elapsed_time": "0:13:19", "remaining_time": "0:51:56", "throughput": 2614.5, "total_tokens": 2090952} {"current_steps": 7795, "total_steps": 38150, "loss": 0.6361, "lr": 4.8361369072353164e-05, "epoch": 2.0432503276539973, "percentage": 20.43, "elapsed_time": "0:13:20", "remaining_time": "0:51:56", "throughput": 2614.93, "total_tokens": 2092648} {"current_steps": 7800, "total_steps": 38150, "loss": 0.4726, "lr": 4.835729401897474e-05, "epoch": 2.0445609436435124, "percentage": 20.45, "elapsed_time": "0:13:20", "remaining_time": "0:51:55", "throughput": 2614.99, "total_tokens": 2093896} {"current_steps": 7805, "total_steps": 38150, "loss": 0.4295, "lr": 4.835321407695503e-05, "epoch": 2.0458715596330275, "percentage": 20.46, "elapsed_time": "0:13:21", "remaining_time": "0:51:55", "throughput": 2615.2, "total_tokens": 2095320} {"current_steps": 7810, "total_steps": 38150, "loss": 0.3812, "lr": 4.834912924714797e-05, "epoch": 2.0471821756225426, "percentage": 20.47, "elapsed_time": "0:13:21", "remaining_time": "0:51:54", "throughput": 2615.26, "total_tokens": 2096488} {"current_steps": 7815, "total_steps": 38150, "loss": 0.5354, "lr": 4.834503953040851e-05, "epoch": 2.0484927916120577, "percentage": 20.48, "elapsed_time": "0:13:22", "remaining_time": "0:51:53", "throughput": 2615.5, "total_tokens": 2097880} {"current_steps": 7820, "total_steps": 38150, "loss": 0.4753, "lr": 4.83409449275926e-05, "epoch": 2.0498034076015728, "percentage": 20.5, "elapsed_time": "0:13:22", "remaining_time": "0:51:52", "throughput": 2615.66, "total_tokens": 2099160} {"current_steps": 7825, "total_steps": 38150, "loss": 0.3719, "lr": 4.8336845439557256e-05, "epoch": 2.051114023591088, "percentage": 20.51, "elapsed_time": "0:13:22", "remaining_time": "0:51:51", "throughput": 2616.04, "total_tokens": 2100632} {"current_steps": 7830, "total_steps": 38150, "loss": 0.2624, "lr": 4.833274106716048e-05, "epoch": 2.052424639580603, "percentage": 20.52, "elapsed_time": "0:13:23", "remaining_time": "0:51:51", "throughput": 2615.98, "total_tokens": 2101688} {"current_steps": 7835, "total_steps": 38150, "loss": 0.367, "lr": 4.832863181126132e-05, "epoch": 2.053735255570118, "percentage": 20.54, "elapsed_time": "0:13:23", "remaining_time": "0:51:50", "throughput": 2616.27, "total_tokens": 2103176} {"current_steps": 7840, "total_steps": 38150, "loss": 0.7646, "lr": 4.832451767271983e-05, "epoch": 2.055045871559633, "percentage": 20.55, "elapsed_time": "0:13:24", "remaining_time": "0:51:49", "throughput": 2616.23, "total_tokens": 2104360} {"current_steps": 7845, "total_steps": 38150, "loss": 0.3736, "lr": 4.832039865239708e-05, "epoch": 2.0563564875491482, "percentage": 20.56, "elapsed_time": "0:13:24", "remaining_time": "0:51:49", "throughput": 2616.75, "total_tokens": 2106072} {"current_steps": 7850, "total_steps": 38150, "loss": 0.3456, "lr": 4.83162747511552e-05, "epoch": 2.0576671035386633, "percentage": 20.58, "elapsed_time": "0:13:25", "remaining_time": "0:51:48", "throughput": 2616.85, "total_tokens": 2107288} {"current_steps": 7855, "total_steps": 38150, "loss": 0.4113, "lr": 4.83121459698573e-05, "epoch": 2.0589777195281784, "percentage": 20.59, "elapsed_time": "0:13:25", "remaining_time": "0:51:47", "throughput": 2616.9, "total_tokens": 2108456} {"current_steps": 7860, "total_steps": 38150, "loss": 0.5566, "lr": 4.830801230936752e-05, "epoch": 2.0602883355176935, "percentage": 20.6, "elapsed_time": "0:13:26", "remaining_time": "0:51:46", "throughput": 2617.15, "total_tokens": 2109896} {"current_steps": 7865, "total_steps": 38150, "loss": 0.4262, "lr": 4.830387377055105e-05, "epoch": 2.061598951507208, "percentage": 20.62, "elapsed_time": "0:13:26", "remaining_time": "0:51:46", "throughput": 2617.54, "total_tokens": 2111560} {"current_steps": 7870, "total_steps": 38150, "loss": 0.5241, "lr": 4.829973035427406e-05, "epoch": 2.0629095674967233, "percentage": 20.63, "elapsed_time": "0:13:27", "remaining_time": "0:51:45", "throughput": 2617.42, "total_tokens": 2112584} {"current_steps": 7875, "total_steps": 38150, "loss": 0.331, "lr": 4.8295582061403766e-05, "epoch": 2.0642201834862384, "percentage": 20.64, "elapsed_time": "0:13:27", "remaining_time": "0:51:45", "throughput": 2617.96, "total_tokens": 2114424} {"current_steps": 7880, "total_steps": 38150, "loss": 0.4728, "lr": 4.8291428892808396e-05, "epoch": 2.0655307994757535, "percentage": 20.66, "elapsed_time": "0:13:28", "remaining_time": "0:51:44", "throughput": 2618.08, "total_tokens": 2115672} {"current_steps": 7885, "total_steps": 38150, "loss": 0.5759, "lr": 4.8287270849357205e-05, "epoch": 2.0668414154652686, "percentage": 20.67, "elapsed_time": "0:13:28", "remaining_time": "0:51:43", "throughput": 2618.52, "total_tokens": 2117336} {"current_steps": 7890, "total_steps": 38150, "loss": 0.3356, "lr": 4.828310793192046e-05, "epoch": 2.0681520314547837, "percentage": 20.68, "elapsed_time": "0:13:29", "remaining_time": "0:51:43", "throughput": 2618.71, "total_tokens": 2118792} {"current_steps": 7895, "total_steps": 38150, "loss": 0.4875, "lr": 4.827894014136945e-05, "epoch": 2.0694626474442988, "percentage": 20.69, "elapsed_time": "0:13:29", "remaining_time": "0:51:42", "throughput": 2618.87, "total_tokens": 2120072} {"current_steps": 7900, "total_steps": 38150, "loss": 0.3931, "lr": 4.827476747857651e-05, "epoch": 2.070773263433814, "percentage": 20.71, "elapsed_time": "0:13:29", "remaining_time": "0:51:41", "throughput": 2618.58, "total_tokens": 2120952} {"current_steps": 7905, "total_steps": 38150, "loss": 0.3772, "lr": 4.827058994441494e-05, "epoch": 2.072083879423329, "percentage": 20.72, "elapsed_time": "0:13:30", "remaining_time": "0:51:40", "throughput": 2618.34, "total_tokens": 2121880} {"current_steps": 7910, "total_steps": 38150, "loss": 0.5332, "lr": 4.82664075397591e-05, "epoch": 2.073394495412844, "percentage": 20.73, "elapsed_time": "0:13:30", "remaining_time": "0:51:39", "throughput": 2618.48, "total_tokens": 2123128} {"current_steps": 7915, "total_steps": 38150, "loss": 0.4384, "lr": 4.826222026548437e-05, "epoch": 2.074705111402359, "percentage": 20.75, "elapsed_time": "0:13:31", "remaining_time": "0:51:39", "throughput": 2619.05, "total_tokens": 2125016} {"current_steps": 7920, "total_steps": 38150, "loss": 1.2038, "lr": 4.825802812246713e-05, "epoch": 2.0760157273918742, "percentage": 20.76, "elapsed_time": "0:13:31", "remaining_time": "0:51:38", "throughput": 2618.97, "total_tokens": 2126088} {"current_steps": 7925, "total_steps": 38150, "loss": 0.3906, "lr": 4.8253831111584794e-05, "epoch": 2.0773263433813893, "percentage": 20.77, "elapsed_time": "0:13:32", "remaining_time": "0:51:38", "throughput": 2619.16, "total_tokens": 2127576} {"current_steps": 7930, "total_steps": 38150, "loss": 0.3431, "lr": 4.8249629233715776e-05, "epoch": 2.0786369593709044, "percentage": 20.79, "elapsed_time": "0:13:32", "remaining_time": "0:51:37", "throughput": 2619.22, "total_tokens": 2128776} {"current_steps": 7935, "total_steps": 38150, "loss": 0.4383, "lr": 4.824542248973954e-05, "epoch": 2.0799475753604195, "percentage": 20.8, "elapsed_time": "0:13:33", "remaining_time": "0:51:36", "throughput": 2619.3, "total_tokens": 2130056} {"current_steps": 7940, "total_steps": 38150, "loss": 0.4033, "lr": 4.824121088053654e-05, "epoch": 2.0812581913499346, "percentage": 20.81, "elapsed_time": "0:13:33", "remaining_time": "0:51:35", "throughput": 2619.49, "total_tokens": 2131432} {"current_steps": 7945, "total_steps": 38150, "loss": 0.3579, "lr": 4.8236994406988255e-05, "epoch": 2.0825688073394497, "percentage": 20.83, "elapsed_time": "0:13:34", "remaining_time": "0:51:35", "throughput": 2619.42, "total_tokens": 2132584} {"current_steps": 7950, "total_steps": 38150, "loss": 0.3566, "lr": 4.82327730699772e-05, "epoch": 2.083879423328965, "percentage": 20.84, "elapsed_time": "0:13:34", "remaining_time": "0:51:34", "throughput": 2619.84, "total_tokens": 2134184} {"current_steps": 7955, "total_steps": 38150, "loss": 0.4886, "lr": 4.822854687038688e-05, "epoch": 2.08519003931848, "percentage": 20.85, "elapsed_time": "0:13:35", "remaining_time": "0:51:33", "throughput": 2620.09, "total_tokens": 2135624} {"current_steps": 7960, "total_steps": 38150, "loss": 0.4466, "lr": 4.8224315809101836e-05, "epoch": 2.0865006553079946, "percentage": 20.87, "elapsed_time": "0:13:35", "remaining_time": "0:51:33", "throughput": 2620.03, "total_tokens": 2136712} {"current_steps": 7965, "total_steps": 38150, "loss": 0.6535, "lr": 4.822007988700762e-05, "epoch": 2.0878112712975097, "percentage": 20.88, "elapsed_time": "0:13:36", "remaining_time": "0:51:32", "throughput": 2620.38, "total_tokens": 2138264} {"current_steps": 7970, "total_steps": 38150, "loss": 0.4829, "lr": 4.821583910499081e-05, "epoch": 2.0891218872870247, "percentage": 20.89, "elapsed_time": "0:13:36", "remaining_time": "0:51:31", "throughput": 2620.31, "total_tokens": 2139368} {"current_steps": 7975, "total_steps": 38150, "loss": 0.6046, "lr": 4.8211593463938985e-05, "epoch": 2.09043250327654, "percentage": 20.9, "elapsed_time": "0:13:36", "remaining_time": "0:51:30", "throughput": 2620.23, "total_tokens": 2140456} {"current_steps": 7980, "total_steps": 38150, "loss": 0.4958, "lr": 4.8207342964740755e-05, "epoch": 2.091743119266055, "percentage": 20.92, "elapsed_time": "0:13:37", "remaining_time": "0:51:30", "throughput": 2620.61, "total_tokens": 2142024} {"current_steps": 7985, "total_steps": 38150, "loss": 0.5429, "lr": 4.8203087608285744e-05, "epoch": 2.09305373525557, "percentage": 20.93, "elapsed_time": "0:13:37", "remaining_time": "0:51:29", "throughput": 2620.64, "total_tokens": 2143208} {"current_steps": 7990, "total_steps": 38150, "loss": 0.2736, "lr": 4.819882739546458e-05, "epoch": 2.094364351245085, "percentage": 20.94, "elapsed_time": "0:13:38", "remaining_time": "0:51:28", "throughput": 2620.95, "total_tokens": 2144712} {"current_steps": 7995, "total_steps": 38150, "loss": 0.4935, "lr": 4.8194562327168946e-05, "epoch": 2.0956749672346002, "percentage": 20.96, "elapsed_time": "0:13:38", "remaining_time": "0:51:28", "throughput": 2621.36, "total_tokens": 2146392} {"current_steps": 8000, "total_steps": 38150, "loss": 0.5112, "lr": 4.819029240429148e-05, "epoch": 2.0969855832241153, "percentage": 20.97, "elapsed_time": "0:13:39", "remaining_time": "0:51:27", "throughput": 2621.89, "total_tokens": 2148136} {"current_steps": 8005, "total_steps": 38150, "loss": 0.4612, "lr": 4.818601762772588e-05, "epoch": 2.0982961992136304, "percentage": 20.98, "elapsed_time": "0:13:39", "remaining_time": "0:51:27", "throughput": 2622.04, "total_tokens": 2149480} {"current_steps": 8010, "total_steps": 38150, "loss": 0.6092, "lr": 4.818173799836686e-05, "epoch": 2.0996068152031455, "percentage": 21.0, "elapsed_time": "0:13:40", "remaining_time": "0:51:26", "throughput": 2622.26, "total_tokens": 2150904} {"current_steps": 8015, "total_steps": 38150, "loss": 0.3421, "lr": 4.817745351711013e-05, "epoch": 2.1009174311926606, "percentage": 21.01, "elapsed_time": "0:13:40", "remaining_time": "0:51:25", "throughput": 2622.29, "total_tokens": 2152056} {"current_steps": 8020, "total_steps": 38150, "loss": 0.5246, "lr": 4.817316418485243e-05, "epoch": 2.1022280471821757, "percentage": 21.02, "elapsed_time": "0:13:41", "remaining_time": "0:51:24", "throughput": 2622.18, "total_tokens": 2153080} {"current_steps": 8025, "total_steps": 38150, "loss": 0.2316, "lr": 4.81688700024915e-05, "epoch": 2.103538663171691, "percentage": 21.04, "elapsed_time": "0:13:41", "remaining_time": "0:51:23", "throughput": 2622.29, "total_tokens": 2154312} {"current_steps": 8030, "total_steps": 38150, "loss": 0.4507, "lr": 4.816457097092611e-05, "epoch": 2.104849279161206, "percentage": 21.05, "elapsed_time": "0:13:41", "remaining_time": "0:51:23", "throughput": 2622.36, "total_tokens": 2155528} {"current_steps": 8035, "total_steps": 38150, "loss": 0.3278, "lr": 4.816026709105605e-05, "epoch": 2.106159895150721, "percentage": 21.06, "elapsed_time": "0:13:42", "remaining_time": "0:51:22", "throughput": 2622.25, "total_tokens": 2156568} {"current_steps": 8040, "total_steps": 38150, "loss": 0.5457, "lr": 4.81559583637821e-05, "epoch": 2.107470511140236, "percentage": 21.07, "elapsed_time": "0:13:42", "remaining_time": "0:51:21", "throughput": 2622.54, "total_tokens": 2158056} {"current_steps": 8045, "total_steps": 38150, "loss": 0.3783, "lr": 4.8151644790006077e-05, "epoch": 2.108781127129751, "percentage": 21.09, "elapsed_time": "0:13:43", "remaining_time": "0:51:20", "throughput": 2622.51, "total_tokens": 2159160} {"current_steps": 8050, "total_steps": 38150, "loss": 0.4502, "lr": 4.8147326370630796e-05, "epoch": 2.1100917431192663, "percentage": 21.1, "elapsed_time": "0:13:43", "remaining_time": "0:51:20", "throughput": 2622.77, "total_tokens": 2160632} {"current_steps": 8055, "total_steps": 38150, "loss": 0.451, "lr": 4.814300310656011e-05, "epoch": 2.111402359108781, "percentage": 21.11, "elapsed_time": "0:13:44", "remaining_time": "0:51:19", "throughput": 2623.06, "total_tokens": 2162152} {"current_steps": 8060, "total_steps": 38150, "loss": 0.5495, "lr": 4.8138674998698854e-05, "epoch": 2.112712975098296, "percentage": 21.13, "elapsed_time": "0:13:44", "remaining_time": "0:51:19", "throughput": 2623.6, "total_tokens": 2163896} {"current_steps": 8065, "total_steps": 38150, "loss": 0.3351, "lr": 4.8134342047952906e-05, "epoch": 2.114023591087811, "percentage": 21.14, "elapsed_time": "0:13:45", "remaining_time": "0:51:18", "throughput": 2623.74, "total_tokens": 2165240} {"current_steps": 8070, "total_steps": 38150, "loss": 0.3075, "lr": 4.8130004255229146e-05, "epoch": 2.1153342070773262, "percentage": 21.15, "elapsed_time": "0:13:45", "remaining_time": "0:51:17", "throughput": 2623.86, "total_tokens": 2166600} {"current_steps": 8075, "total_steps": 38150, "loss": 0.4641, "lr": 4.8125661621435445e-05, "epoch": 2.1166448230668413, "percentage": 21.17, "elapsed_time": "0:13:46", "remaining_time": "0:51:17", "throughput": 2624.1, "total_tokens": 2168056} {"current_steps": 8080, "total_steps": 38150, "loss": 0.356, "lr": 4.8121314147480736e-05, "epoch": 2.1179554390563564, "percentage": 21.18, "elapsed_time": "0:13:46", "remaining_time": "0:51:16", "throughput": 2624.34, "total_tokens": 2169480} {"current_steps": 8085, "total_steps": 38150, "loss": 0.5278, "lr": 4.811696183427493e-05, "epoch": 2.1192660550458715, "percentage": 21.19, "elapsed_time": "0:13:47", "remaining_time": "0:51:15", "throughput": 2624.3, "total_tokens": 2170632} {"current_steps": 8090, "total_steps": 38150, "loss": 0.4615, "lr": 4.811260468272895e-05, "epoch": 2.1205766710353866, "percentage": 21.21, "elapsed_time": "0:13:47", "remaining_time": "0:51:15", "throughput": 2624.62, "total_tokens": 2172072} {"current_steps": 8095, "total_steps": 38150, "loss": 0.7033, "lr": 4.810824269375475e-05, "epoch": 2.1218872870249017, "percentage": 21.22, "elapsed_time": "0:13:48", "remaining_time": "0:51:14", "throughput": 2624.73, "total_tokens": 2173416} {"current_steps": 8100, "total_steps": 38150, "loss": 0.5072, "lr": 4.810387586826527e-05, "epoch": 2.123197903014417, "percentage": 21.23, "elapsed_time": "0:13:48", "remaining_time": "0:51:13", "throughput": 2624.71, "total_tokens": 2174536} {"current_steps": 8105, "total_steps": 38150, "loss": 0.556, "lr": 4.80995042071745e-05, "epoch": 2.124508519003932, "percentage": 21.25, "elapsed_time": "0:13:48", "remaining_time": "0:51:13", "throughput": 2625.19, "total_tokens": 2176280} {"current_steps": 8110, "total_steps": 38150, "loss": 0.3431, "lr": 4.809512771139741e-05, "epoch": 2.125819134993447, "percentage": 21.26, "elapsed_time": "0:13:49", "remaining_time": "0:51:12", "throughput": 2625.61, "total_tokens": 2177928} {"current_steps": 8115, "total_steps": 38150, "loss": 0.3465, "lr": 4.809074638184999e-05, "epoch": 2.127129750982962, "percentage": 21.27, "elapsed_time": "0:13:49", "remaining_time": "0:51:11", "throughput": 2625.77, "total_tokens": 2179208} {"current_steps": 8120, "total_steps": 38150, "loss": 0.3543, "lr": 4.808636021944927e-05, "epoch": 2.128440366972477, "percentage": 21.28, "elapsed_time": "0:13:50", "remaining_time": "0:51:10", "throughput": 2625.93, "total_tokens": 2180520} {"current_steps": 8125, "total_steps": 38150, "loss": 0.5503, "lr": 4.808196922511323e-05, "epoch": 2.1297509829619923, "percentage": 21.3, "elapsed_time": "0:13:50", "remaining_time": "0:51:10", "throughput": 2626.0, "total_tokens": 2181800} {"current_steps": 8130, "total_steps": 38150, "loss": 0.449, "lr": 4.8077573399760914e-05, "epoch": 2.1310615989515074, "percentage": 21.31, "elapsed_time": "0:13:51", "remaining_time": "0:51:09", "throughput": 2626.05, "total_tokens": 2183016} {"current_steps": 8135, "total_steps": 38150, "loss": 0.4442, "lr": 4.807317274431236e-05, "epoch": 2.1323722149410225, "percentage": 21.32, "elapsed_time": "0:13:51", "remaining_time": "0:51:08", "throughput": 2626.35, "total_tokens": 2184504} {"current_steps": 8140, "total_steps": 38150, "loss": 0.3541, "lr": 4.806876725968862e-05, "epoch": 2.133682830930537, "percentage": 21.34, "elapsed_time": "0:13:52", "remaining_time": "0:51:08", "throughput": 2626.24, "total_tokens": 2185544} {"current_steps": 8145, "total_steps": 38150, "loss": 0.2752, "lr": 4.806435694681175e-05, "epoch": 2.134993446920052, "percentage": 21.35, "elapsed_time": "0:13:52", "remaining_time": "0:51:07", "throughput": 2626.61, "total_tokens": 2187192} {"current_steps": 8150, "total_steps": 38150, "loss": 0.4924, "lr": 4.805994180660483e-05, "epoch": 2.1363040629095673, "percentage": 21.36, "elapsed_time": "0:13:53", "remaining_time": "0:51:06", "throughput": 2626.78, "total_tokens": 2188504} {"current_steps": 8155, "total_steps": 38150, "loss": 0.4521, "lr": 4.805552183999193e-05, "epoch": 2.1376146788990824, "percentage": 21.38, "elapsed_time": "0:13:53", "remaining_time": "0:51:06", "throughput": 2627.0, "total_tokens": 2189928} {"current_steps": 8160, "total_steps": 38150, "loss": 0.5876, "lr": 4.8051097047898144e-05, "epoch": 2.1389252948885975, "percentage": 21.39, "elapsed_time": "0:13:54", "remaining_time": "0:51:05", "throughput": 2627.39, "total_tokens": 2191768} {"current_steps": 8165, "total_steps": 38150, "loss": 0.3982, "lr": 4.8046667431249585e-05, "epoch": 2.1402359108781126, "percentage": 21.4, "elapsed_time": "0:13:54", "remaining_time": "0:51:05", "throughput": 2627.51, "total_tokens": 2193080} {"current_steps": 8170, "total_steps": 38150, "loss": 0.6818, "lr": 4.804223299097334e-05, "epoch": 2.1415465268676277, "percentage": 21.42, "elapsed_time": "0:13:55", "remaining_time": "0:51:04", "throughput": 2627.39, "total_tokens": 2194104} {"current_steps": 8175, "total_steps": 38150, "loss": 0.4585, "lr": 4.803779372799755e-05, "epoch": 2.142857142857143, "percentage": 21.43, "elapsed_time": "0:13:55", "remaining_time": "0:51:04", "throughput": 2628.56, "total_tokens": 2197176} {"current_steps": 8180, "total_steps": 38150, "loss": 0.388, "lr": 4.803334964325134e-05, "epoch": 2.144167758846658, "percentage": 21.44, "elapsed_time": "0:13:56", "remaining_time": "0:51:04", "throughput": 2628.48, "total_tokens": 2198232} {"current_steps": 8185, "total_steps": 38150, "loss": 0.4804, "lr": 4.802890073766485e-05, "epoch": 2.145478374836173, "percentage": 21.45, "elapsed_time": "0:13:56", "remaining_time": "0:51:03", "throughput": 2628.68, "total_tokens": 2199576} {"current_steps": 8190, "total_steps": 38150, "loss": 0.7601, "lr": 4.802444701216923e-05, "epoch": 2.146788990825688, "percentage": 21.47, "elapsed_time": "0:13:57", "remaining_time": "0:51:02", "throughput": 2628.64, "total_tokens": 2200728} {"current_steps": 8195, "total_steps": 38150, "loss": 0.4281, "lr": 4.801998846769662e-05, "epoch": 2.148099606815203, "percentage": 21.48, "elapsed_time": "0:13:57", "remaining_time": "0:51:02", "throughput": 2629.0, "total_tokens": 2202296} {"current_steps": 8200, "total_steps": 38150, "loss": 0.4946, "lr": 4.801552510518021e-05, "epoch": 2.1494102228047183, "percentage": 21.49, "elapsed_time": "0:13:58", "remaining_time": "0:51:01", "throughput": 2629.05, "total_tokens": 2203480} {"current_steps": 8205, "total_steps": 38150, "loss": 0.4024, "lr": 4.801105692555415e-05, "epoch": 2.1507208387942334, "percentage": 21.51, "elapsed_time": "0:13:58", "remaining_time": "0:51:00", "throughput": 2629.0, "total_tokens": 2204584} {"current_steps": 8210, "total_steps": 38150, "loss": 0.4478, "lr": 4.800658392975366e-05, "epoch": 2.1520314547837485, "percentage": 21.52, "elapsed_time": "0:13:59", "remaining_time": "0:50:59", "throughput": 2628.68, "total_tokens": 2205464} {"current_steps": 8215, "total_steps": 38150, "loss": 0.6832, "lr": 4.800210611871488e-05, "epoch": 2.1533420707732636, "percentage": 21.53, "elapsed_time": "0:13:59", "remaining_time": "0:50:58", "throughput": 2628.99, "total_tokens": 2206936} {"current_steps": 8220, "total_steps": 38150, "loss": 0.4925, "lr": 4.7997623493375054e-05, "epoch": 2.1546526867627787, "percentage": 21.55, "elapsed_time": "0:13:59", "remaining_time": "0:50:58", "throughput": 2628.91, "total_tokens": 2208120} {"current_steps": 8225, "total_steps": 38150, "loss": 0.4825, "lr": 4.7993136054672356e-05, "epoch": 2.1559633027522938, "percentage": 21.56, "elapsed_time": "0:14:00", "remaining_time": "0:50:57", "throughput": 2629.19, "total_tokens": 2209608} {"current_steps": 8230, "total_steps": 38150, "loss": 0.2816, "lr": 4.798864380354601e-05, "epoch": 2.157273918741809, "percentage": 21.57, "elapsed_time": "0:14:00", "remaining_time": "0:50:57", "throughput": 2629.41, "total_tokens": 2211080} {"current_steps": 8235, "total_steps": 38150, "loss": 0.5742, "lr": 4.798414674093624e-05, "epoch": 2.1585845347313235, "percentage": 21.59, "elapsed_time": "0:14:01", "remaining_time": "0:50:56", "throughput": 2629.9, "total_tokens": 2212984} {"current_steps": 8240, "total_steps": 38150, "loss": 0.4363, "lr": 4.7979644867784276e-05, "epoch": 2.1598951507208386, "percentage": 21.6, "elapsed_time": "0:14:01", "remaining_time": "0:50:56", "throughput": 2629.86, "total_tokens": 2214136} {"current_steps": 8245, "total_steps": 38150, "loss": 0.5167, "lr": 4.797513818503234e-05, "epoch": 2.1612057667103537, "percentage": 21.61, "elapsed_time": "0:14:02", "remaining_time": "0:50:55", "throughput": 2629.69, "total_tokens": 2215080} {"current_steps": 8250, "total_steps": 38150, "loss": 0.32, "lr": 4.797062669362369e-05, "epoch": 2.162516382699869, "percentage": 21.63, "elapsed_time": "0:14:02", "remaining_time": "0:50:54", "throughput": 2629.79, "total_tokens": 2216328} {"current_steps": 8255, "total_steps": 38150, "loss": 0.5996, "lr": 4.796611039450255e-05, "epoch": 2.163826998689384, "percentage": 21.64, "elapsed_time": "0:14:03", "remaining_time": "0:50:53", "throughput": 2629.91, "total_tokens": 2217608} {"current_steps": 8260, "total_steps": 38150, "loss": 0.4528, "lr": 4.796158928861419e-05, "epoch": 2.165137614678899, "percentage": 21.65, "elapsed_time": "0:14:03", "remaining_time": "0:50:52", "throughput": 2629.81, "total_tokens": 2218712} {"current_steps": 8265, "total_steps": 38150, "loss": 0.3988, "lr": 4.7957063376904875e-05, "epoch": 2.166448230668414, "percentage": 21.66, "elapsed_time": "0:14:04", "remaining_time": "0:50:52", "throughput": 2629.83, "total_tokens": 2219880} {"current_steps": 8270, "total_steps": 38150, "loss": 0.5308, "lr": 4.7952532660321854e-05, "epoch": 2.167758846657929, "percentage": 21.68, "elapsed_time": "0:14:04", "remaining_time": "0:50:51", "throughput": 2629.91, "total_tokens": 2221064} {"current_steps": 8275, "total_steps": 38150, "loss": 0.4302, "lr": 4.794799713981341e-05, "epoch": 2.1690694626474443, "percentage": 21.69, "elapsed_time": "0:14:05", "remaining_time": "0:50:50", "throughput": 2630.09, "total_tokens": 2222440} {"current_steps": 8280, "total_steps": 38150, "loss": 0.4094, "lr": 4.7943456816328815e-05, "epoch": 2.1703800786369594, "percentage": 21.7, "elapsed_time": "0:14:05", "remaining_time": "0:50:49", "throughput": 2630.29, "total_tokens": 2223768} {"current_steps": 8285, "total_steps": 38150, "loss": 0.4225, "lr": 4.7938911690818347e-05, "epoch": 2.1716906946264745, "percentage": 21.72, "elapsed_time": "0:14:05", "remaining_time": "0:50:49", "throughput": 2630.55, "total_tokens": 2225320} {"current_steps": 8290, "total_steps": 38150, "loss": 0.3917, "lr": 4.79343617642333e-05, "epoch": 2.1730013106159896, "percentage": 21.73, "elapsed_time": "0:14:06", "remaining_time": "0:50:48", "throughput": 2630.9, "total_tokens": 2226792} {"current_steps": 8295, "total_steps": 38150, "loss": 0.4384, "lr": 4.792980703752597e-05, "epoch": 2.1743119266055047, "percentage": 21.74, "elapsed_time": "0:14:06", "remaining_time": "0:50:48", "throughput": 2631.16, "total_tokens": 2228248} {"current_steps": 8300, "total_steps": 38150, "loss": 0.3454, "lr": 4.792524751164964e-05, "epoch": 2.1756225425950197, "percentage": 21.76, "elapsed_time": "0:14:07", "remaining_time": "0:50:47", "throughput": 2631.42, "total_tokens": 2229640} {"current_steps": 8305, "total_steps": 38150, "loss": 0.3094, "lr": 4.792068318755861e-05, "epoch": 2.176933158584535, "percentage": 21.77, "elapsed_time": "0:14:07", "remaining_time": "0:50:46", "throughput": 2631.59, "total_tokens": 2230936} {"current_steps": 8310, "total_steps": 38150, "loss": 0.4469, "lr": 4.791611406620821e-05, "epoch": 2.17824377457405, "percentage": 21.78, "elapsed_time": "0:14:08", "remaining_time": "0:50:45", "throughput": 2631.7, "total_tokens": 2232264} {"current_steps": 8315, "total_steps": 38150, "loss": 0.3739, "lr": 4.7911540148554725e-05, "epoch": 2.179554390563565, "percentage": 21.8, "elapsed_time": "0:14:08", "remaining_time": "0:50:45", "throughput": 2631.65, "total_tokens": 2233416} {"current_steps": 8320, "total_steps": 38150, "loss": 0.4151, "lr": 4.790696143555546e-05, "epoch": 2.18086500655308, "percentage": 21.81, "elapsed_time": "0:14:09", "remaining_time": "0:50:44", "throughput": 2632.01, "total_tokens": 2235032} {"current_steps": 8325, "total_steps": 38150, "loss": 0.8006, "lr": 4.790237792816877e-05, "epoch": 2.1821756225425952, "percentage": 21.82, "elapsed_time": "0:14:09", "remaining_time": "0:50:43", "throughput": 2632.24, "total_tokens": 2236440} {"current_steps": 8330, "total_steps": 38150, "loss": 0.3095, "lr": 4.789778962735394e-05, "epoch": 2.18348623853211, "percentage": 21.83, "elapsed_time": "0:14:10", "remaining_time": "0:50:43", "throughput": 2632.52, "total_tokens": 2237912} {"current_steps": 8335, "total_steps": 38150, "loss": 0.4398, "lr": 4.78931965340713e-05, "epoch": 2.184796854521625, "percentage": 21.85, "elapsed_time": "0:14:10", "remaining_time": "0:50:42", "throughput": 2632.65, "total_tokens": 2239144} {"current_steps": 8340, "total_steps": 38150, "loss": 0.5023, "lr": 4.78885986492822e-05, "epoch": 2.18610747051114, "percentage": 21.86, "elapsed_time": "0:14:11", "remaining_time": "0:50:41", "throughput": 2633.16, "total_tokens": 2240840} {"current_steps": 8345, "total_steps": 38150, "loss": 0.4935, "lr": 4.788399597394894e-05, "epoch": 2.187418086500655, "percentage": 21.87, "elapsed_time": "0:14:11", "remaining_time": "0:50:41", "throughput": 2633.4, "total_tokens": 2242296} {"current_steps": 8350, "total_steps": 38150, "loss": 0.4482, "lr": 4.787938850903486e-05, "epoch": 2.1887287024901703, "percentage": 21.89, "elapsed_time": "0:14:11", "remaining_time": "0:50:40", "throughput": 2633.59, "total_tokens": 2243608} {"current_steps": 8355, "total_steps": 38150, "loss": 0.5492, "lr": 4.78747762555043e-05, "epoch": 2.1900393184796854, "percentage": 21.9, "elapsed_time": "0:14:12", "remaining_time": "0:50:39", "throughput": 2633.74, "total_tokens": 2244888} {"current_steps": 8360, "total_steps": 38150, "loss": 0.421, "lr": 4.7870159214322594e-05, "epoch": 2.1913499344692005, "percentage": 21.91, "elapsed_time": "0:14:12", "remaining_time": "0:50:38", "throughput": 2633.77, "total_tokens": 2246136} {"current_steps": 8365, "total_steps": 38150, "loss": 0.4918, "lr": 4.7865537386456084e-05, "epoch": 2.1926605504587156, "percentage": 21.93, "elapsed_time": "0:14:13", "remaining_time": "0:50:38", "throughput": 2633.99, "total_tokens": 2247480} {"current_steps": 8370, "total_steps": 38150, "loss": 0.337, "lr": 4.7860910772872104e-05, "epoch": 2.1939711664482306, "percentage": 21.94, "elapsed_time": "0:14:13", "remaining_time": "0:50:37", "throughput": 2633.78, "total_tokens": 2248456} {"current_steps": 8375, "total_steps": 38150, "loss": 0.752, "lr": 4.7856279374539e-05, "epoch": 2.1952817824377457, "percentage": 21.95, "elapsed_time": "0:14:14", "remaining_time": "0:50:36", "throughput": 2633.8, "total_tokens": 2249608} {"current_steps": 8380, "total_steps": 38150, "loss": 0.4285, "lr": 4.785164319242612e-05, "epoch": 2.196592398427261, "percentage": 21.97, "elapsed_time": "0:14:14", "remaining_time": "0:50:35", "throughput": 2633.7, "total_tokens": 2250648} {"current_steps": 8385, "total_steps": 38150, "loss": 0.6134, "lr": 4.78470022275038e-05, "epoch": 2.197903014416776, "percentage": 21.98, "elapsed_time": "0:14:15", "remaining_time": "0:50:35", "throughput": 2633.98, "total_tokens": 2252168} {"current_steps": 8390, "total_steps": 38150, "loss": 0.2692, "lr": 4.784235648074339e-05, "epoch": 2.199213630406291, "percentage": 21.99, "elapsed_time": "0:14:15", "remaining_time": "0:50:34", "throughput": 2634.15, "total_tokens": 2253464} {"current_steps": 8395, "total_steps": 38150, "loss": 0.3533, "lr": 4.783770595311724e-05, "epoch": 2.200524246395806, "percentage": 22.01, "elapsed_time": "0:14:15", "remaining_time": "0:50:33", "throughput": 2634.23, "total_tokens": 2254712} {"current_steps": 8400, "total_steps": 38150, "loss": 0.2886, "lr": 4.78330506455987e-05, "epoch": 2.2018348623853212, "percentage": 22.02, "elapsed_time": "0:14:16", "remaining_time": "0:50:32", "throughput": 2634.17, "total_tokens": 2255800} {"current_steps": 8405, "total_steps": 38150, "loss": 0.4786, "lr": 4.78283905591621e-05, "epoch": 2.2031454783748363, "percentage": 22.03, "elapsed_time": "0:14:16", "remaining_time": "0:50:32", "throughput": 2634.39, "total_tokens": 2257208} {"current_steps": 8410, "total_steps": 38150, "loss": 0.441, "lr": 4.78237256947828e-05, "epoch": 2.2044560943643514, "percentage": 22.04, "elapsed_time": "0:14:17", "remaining_time": "0:50:31", "throughput": 2634.59, "total_tokens": 2258600} {"current_steps": 8415, "total_steps": 38150, "loss": 0.5211, "lr": 4.7819056053437165e-05, "epoch": 2.2057667103538665, "percentage": 22.06, "elapsed_time": "0:14:17", "remaining_time": "0:50:30", "throughput": 2634.77, "total_tokens": 2259960} {"current_steps": 8420, "total_steps": 38150, "loss": 0.5039, "lr": 4.7814381636102515e-05, "epoch": 2.2070773263433816, "percentage": 22.07, "elapsed_time": "0:14:18", "remaining_time": "0:50:30", "throughput": 2634.58, "total_tokens": 2260888} {"current_steps": 8425, "total_steps": 38150, "loss": 0.4908, "lr": 4.780970244375721e-05, "epoch": 2.2083879423328963, "percentage": 22.08, "elapsed_time": "0:14:18", "remaining_time": "0:50:29", "throughput": 2634.87, "total_tokens": 2262376} {"current_steps": 8430, "total_steps": 38150, "loss": 0.4299, "lr": 4.780501847738059e-05, "epoch": 2.2096985583224114, "percentage": 22.1, "elapsed_time": "0:14:19", "remaining_time": "0:50:28", "throughput": 2634.83, "total_tokens": 2263432} {"current_steps": 8435, "total_steps": 38150, "loss": 0.4216, "lr": 4.7800329737953016e-05, "epoch": 2.2110091743119265, "percentage": 22.11, "elapsed_time": "0:14:19", "remaining_time": "0:50:27", "throughput": 2635.09, "total_tokens": 2264808} {"current_steps": 8440, "total_steps": 38150, "loss": 0.4388, "lr": 4.779563622645582e-05, "epoch": 2.2123197903014415, "percentage": 22.12, "elapsed_time": "0:14:19", "remaining_time": "0:50:27", "throughput": 2635.4, "total_tokens": 2266248} {"current_steps": 8445, "total_steps": 38150, "loss": 0.4034, "lr": 4.779093794387135e-05, "epoch": 2.2136304062909566, "percentage": 22.14, "elapsed_time": "0:14:20", "remaining_time": "0:50:26", "throughput": 2635.38, "total_tokens": 2267416} {"current_steps": 8450, "total_steps": 38150, "loss": 0.4313, "lr": 4.778623489118295e-05, "epoch": 2.2149410222804717, "percentage": 22.15, "elapsed_time": "0:14:20", "remaining_time": "0:50:25", "throughput": 2635.27, "total_tokens": 2268440} {"current_steps": 8455, "total_steps": 38150, "loss": 0.4603, "lr": 4.7781527069374957e-05, "epoch": 2.216251638269987, "percentage": 22.16, "elapsed_time": "0:14:21", "remaining_time": "0:50:24", "throughput": 2635.51, "total_tokens": 2269800} {"current_steps": 8460, "total_steps": 38150, "loss": 0.4566, "lr": 4.777681447943271e-05, "epoch": 2.217562254259502, "percentage": 22.18, "elapsed_time": "0:14:21", "remaining_time": "0:50:24", "throughput": 2635.84, "total_tokens": 2271256} {"current_steps": 8465, "total_steps": 38150, "loss": 0.3461, "lr": 4.777209712234255e-05, "epoch": 2.218872870249017, "percentage": 22.19, "elapsed_time": "0:14:22", "remaining_time": "0:50:23", "throughput": 2636.13, "total_tokens": 2272728} {"current_steps": 8470, "total_steps": 38150, "loss": 0.7434, "lr": 4.776737499909181e-05, "epoch": 2.220183486238532, "percentage": 22.2, "elapsed_time": "0:14:22", "remaining_time": "0:50:22", "throughput": 2636.36, "total_tokens": 2274072} {"current_steps": 8475, "total_steps": 38150, "loss": 0.4818, "lr": 4.776264811066882e-05, "epoch": 2.221494102228047, "percentage": 22.21, "elapsed_time": "0:14:23", "remaining_time": "0:50:22", "throughput": 2636.57, "total_tokens": 2275560} {"current_steps": 8480, "total_steps": 38150, "loss": 0.3445, "lr": 4.7757916458062905e-05, "epoch": 2.2228047182175623, "percentage": 22.23, "elapsed_time": "0:14:23", "remaining_time": "0:50:21", "throughput": 2636.71, "total_tokens": 2276840} {"current_steps": 8485, "total_steps": 38150, "loss": 0.6079, "lr": 4.7753180042264404e-05, "epoch": 2.2241153342070774, "percentage": 22.24, "elapsed_time": "0:14:23", "remaining_time": "0:50:20", "throughput": 2636.7, "total_tokens": 2277944} {"current_steps": 8490, "total_steps": 38150, "loss": 0.3587, "lr": 4.7748438864264636e-05, "epoch": 2.2254259501965925, "percentage": 22.25, "elapsed_time": "0:14:24", "remaining_time": "0:50:19", "throughput": 2636.4, "total_tokens": 2278792} {"current_steps": 8495, "total_steps": 38150, "loss": 0.3962, "lr": 4.774369292505592e-05, "epoch": 2.2267365661861076, "percentage": 22.27, "elapsed_time": "0:14:24", "remaining_time": "0:50:19", "throughput": 2636.81, "total_tokens": 2280488} {"current_steps": 8500, "total_steps": 38150, "loss": 0.4009, "lr": 4.773894222563157e-05, "epoch": 2.2280471821756227, "percentage": 22.28, "elapsed_time": "0:14:25", "remaining_time": "0:50:18", "throughput": 2636.85, "total_tokens": 2281640} {"current_steps": 8505, "total_steps": 38150, "loss": 0.3692, "lr": 4.7734186766985904e-05, "epoch": 2.229357798165138, "percentage": 22.29, "elapsed_time": "0:14:25", "remaining_time": "0:50:17", "throughput": 2636.84, "total_tokens": 2282744} {"current_steps": 8510, "total_steps": 38150, "loss": 0.2417, "lr": 4.772942655011423e-05, "epoch": 2.230668414154653, "percentage": 22.31, "elapsed_time": "0:14:26", "remaining_time": "0:50:16", "throughput": 2636.83, "total_tokens": 2283848} {"current_steps": 8515, "total_steps": 38150, "loss": 0.4677, "lr": 4.772466157601285e-05, "epoch": 2.231979030144168, "percentage": 22.32, "elapsed_time": "0:14:26", "remaining_time": "0:50:15", "throughput": 2636.87, "total_tokens": 2285000} {"current_steps": 8520, "total_steps": 38150, "loss": 0.3451, "lr": 4.771989184567907e-05, "epoch": 2.2332896461336826, "percentage": 22.33, "elapsed_time": "0:14:26", "remaining_time": "0:50:15", "throughput": 2636.82, "total_tokens": 2286056} {"current_steps": 8525, "total_steps": 38150, "loss": 0.6986, "lr": 4.7715117360111185e-05, "epoch": 2.2346002621231977, "percentage": 22.35, "elapsed_time": "0:14:27", "remaining_time": "0:50:14", "throughput": 2636.95, "total_tokens": 2287320} {"current_steps": 8530, "total_steps": 38150, "loss": 0.4901, "lr": 4.771033812030849e-05, "epoch": 2.235910878112713, "percentage": 22.36, "elapsed_time": "0:14:27", "remaining_time": "0:50:13", "throughput": 2636.77, "total_tokens": 2288280} {"current_steps": 8535, "total_steps": 38150, "loss": 0.4383, "lr": 4.7705554127271254e-05, "epoch": 2.237221494102228, "percentage": 22.37, "elapsed_time": "0:14:28", "remaining_time": "0:50:12", "throughput": 2636.88, "total_tokens": 2289576} {"current_steps": 8540, "total_steps": 38150, "loss": 0.3268, "lr": 4.770076538200078e-05, "epoch": 2.238532110091743, "percentage": 22.39, "elapsed_time": "0:14:28", "remaining_time": "0:50:12", "throughput": 2637.14, "total_tokens": 2291032} {"current_steps": 8545, "total_steps": 38150, "loss": 0.4504, "lr": 4.769597188549932e-05, "epoch": 2.239842726081258, "percentage": 22.4, "elapsed_time": "0:14:29", "remaining_time": "0:50:11", "throughput": 2637.58, "total_tokens": 2292824} {"current_steps": 8550, "total_steps": 38150, "loss": 0.4152, "lr": 4.769117363877018e-05, "epoch": 2.241153342070773, "percentage": 22.41, "elapsed_time": "0:14:29", "remaining_time": "0:50:11", "throughput": 2637.88, "total_tokens": 2294264} {"current_steps": 8555, "total_steps": 38150, "loss": 0.5358, "lr": 4.76863706428176e-05, "epoch": 2.2424639580602883, "percentage": 22.42, "elapsed_time": "0:14:30", "remaining_time": "0:50:10", "throughput": 2638.38, "total_tokens": 2295960} {"current_steps": 8560, "total_steps": 38150, "loss": 0.4933, "lr": 4.7681562898646836e-05, "epoch": 2.2437745740498034, "percentage": 22.44, "elapsed_time": "0:14:30", "remaining_time": "0:50:09", "throughput": 2638.49, "total_tokens": 2297336} {"current_steps": 8565, "total_steps": 38150, "loss": 0.3728, "lr": 4.767675040726416e-05, "epoch": 2.2450851900393185, "percentage": 22.45, "elapsed_time": "0:14:31", "remaining_time": "0:50:09", "throughput": 2638.62, "total_tokens": 2298568} {"current_steps": 8570, "total_steps": 38150, "loss": 0.4515, "lr": 4.76719331696768e-05, "epoch": 2.2463958060288336, "percentage": 22.46, "elapsed_time": "0:14:31", "remaining_time": "0:50:08", "throughput": 2638.52, "total_tokens": 2299576} {"current_steps": 8575, "total_steps": 38150, "loss": 0.5322, "lr": 4.7667111186893e-05, "epoch": 2.2477064220183487, "percentage": 22.48, "elapsed_time": "0:14:32", "remaining_time": "0:50:07", "throughput": 2639.0, "total_tokens": 2301288} {"current_steps": 8580, "total_steps": 38150, "loss": 0.3726, "lr": 4.766228445992199e-05, "epoch": 2.249017038007864, "percentage": 22.49, "elapsed_time": "0:14:32", "remaining_time": "0:50:06", "throughput": 2639.26, "total_tokens": 2302664} {"current_steps": 8585, "total_steps": 38150, "loss": 0.3679, "lr": 4.7657452989774e-05, "epoch": 2.250327653997379, "percentage": 22.5, "elapsed_time": "0:14:32", "remaining_time": "0:50:06", "throughput": 2639.39, "total_tokens": 2303960} {"current_steps": 8590, "total_steps": 38150, "loss": 0.3822, "lr": 4.765261677746026e-05, "epoch": 2.251638269986894, "percentage": 22.52, "elapsed_time": "0:14:33", "remaining_time": "0:50:05", "throughput": 2639.44, "total_tokens": 2305112} {"current_steps": 8595, "total_steps": 38150, "loss": 0.3362, "lr": 4.764777582399296e-05, "epoch": 2.252948885976409, "percentage": 22.53, "elapsed_time": "0:14:33", "remaining_time": "0:50:04", "throughput": 2639.67, "total_tokens": 2306600} {"current_steps": 8600, "total_steps": 38150, "loss": 0.4482, "lr": 4.764293013038531e-05, "epoch": 2.254259501965924, "percentage": 22.54, "elapsed_time": "0:14:34", "remaining_time": "0:50:04", "throughput": 2639.77, "total_tokens": 2307928} {"current_steps": 8605, "total_steps": 38150, "loss": 0.5352, "lr": 4.7638079697651514e-05, "epoch": 2.255570117955439, "percentage": 22.56, "elapsed_time": "0:14:34", "remaining_time": "0:50:03", "throughput": 2639.87, "total_tokens": 2309144} {"current_steps": 8610, "total_steps": 38150, "loss": 0.379, "lr": 4.763322452680675e-05, "epoch": 2.2568807339449544, "percentage": 22.57, "elapsed_time": "0:14:35", "remaining_time": "0:50:02", "throughput": 2639.91, "total_tokens": 2310296} {"current_steps": 8615, "total_steps": 38150, "loss": 0.3403, "lr": 4.76283646188672e-05, "epoch": 2.258191349934469, "percentage": 22.58, "elapsed_time": "0:14:35", "remaining_time": "0:50:01", "throughput": 2640.23, "total_tokens": 2311816} {"current_steps": 8620, "total_steps": 38150, "loss": 0.4279, "lr": 4.7623499974850036e-05, "epoch": 2.259501965923984, "percentage": 22.6, "elapsed_time": "0:14:36", "remaining_time": "0:50:01", "throughput": 2640.42, "total_tokens": 2313112} {"current_steps": 8625, "total_steps": 38150, "loss": 0.4525, "lr": 4.7618630595773424e-05, "epoch": 2.260812581913499, "percentage": 22.61, "elapsed_time": "0:14:36", "remaining_time": "0:50:00", "throughput": 2640.46, "total_tokens": 2314312} {"current_steps": 8630, "total_steps": 38150, "loss": 0.6885, "lr": 4.7613756482656505e-05, "epoch": 2.2621231979030143, "percentage": 22.62, "elapsed_time": "0:14:36", "remaining_time": "0:49:59", "throughput": 2640.48, "total_tokens": 2315432} {"current_steps": 8635, "total_steps": 38150, "loss": 0.3807, "lr": 4.760887763651942e-05, "epoch": 2.2634338138925294, "percentage": 22.63, "elapsed_time": "0:14:37", "remaining_time": "0:49:58", "throughput": 2640.92, "total_tokens": 2317128} {"current_steps": 8640, "total_steps": 38150, "loss": 0.4486, "lr": 4.7603994058383315e-05, "epoch": 2.2647444298820445, "percentage": 22.65, "elapsed_time": "0:14:37", "remaining_time": "0:49:58", "throughput": 2641.32, "total_tokens": 2318904} {"current_steps": 8645, "total_steps": 38150, "loss": 0.5333, "lr": 4.759910574927032e-05, "epoch": 2.2660550458715596, "percentage": 22.66, "elapsed_time": "0:14:38", "remaining_time": "0:49:58", "throughput": 2642.29, "total_tokens": 2321384} {"current_steps": 8650, "total_steps": 38150, "loss": 0.3772, "lr": 4.759421271020353e-05, "epoch": 2.2673656618610747, "percentage": 22.67, "elapsed_time": "0:14:39", "remaining_time": "0:49:57", "throughput": 2642.49, "total_tokens": 2322776} {"current_steps": 8655, "total_steps": 38150, "loss": 0.3439, "lr": 4.758931494220707e-05, "epoch": 2.26867627785059, "percentage": 22.69, "elapsed_time": "0:14:39", "remaining_time": "0:49:57", "throughput": 2642.81, "total_tokens": 2324376} {"current_steps": 8660, "total_steps": 38150, "loss": 0.4738, "lr": 4.7584412446306e-05, "epoch": 2.269986893840105, "percentage": 22.7, "elapsed_time": "0:14:39", "remaining_time": "0:49:56", "throughput": 2642.91, "total_tokens": 2325688} {"current_steps": 8665, "total_steps": 38150, "loss": 0.5997, "lr": 4.7579505223526446e-05, "epoch": 2.27129750982962, "percentage": 22.71, "elapsed_time": "0:14:40", "remaining_time": "0:49:55", "throughput": 2642.9, "total_tokens": 2326808} {"current_steps": 8670, "total_steps": 38150, "loss": 0.2558, "lr": 4.757459327489546e-05, "epoch": 2.272608125819135, "percentage": 22.73, "elapsed_time": "0:14:40", "remaining_time": "0:49:55", "throughput": 2643.22, "total_tokens": 2328344} {"current_steps": 8675, "total_steps": 38150, "loss": 0.3132, "lr": 4.756967660144111e-05, "epoch": 2.27391874180865, "percentage": 22.74, "elapsed_time": "0:14:41", "remaining_time": "0:49:54", "throughput": 2643.31, "total_tokens": 2329560} {"current_steps": 8680, "total_steps": 38150, "loss": 0.5607, "lr": 4.756475520419244e-05, "epoch": 2.2752293577981653, "percentage": 22.75, "elapsed_time": "0:14:41", "remaining_time": "0:49:53", "throughput": 2643.51, "total_tokens": 2330888} {"current_steps": 8685, "total_steps": 38150, "loss": 0.6483, "lr": 4.7559829084179494e-05, "epoch": 2.2765399737876804, "percentage": 22.77, "elapsed_time": "0:14:42", "remaining_time": "0:49:52", "throughput": 2643.71, "total_tokens": 2332232} {"current_steps": 8690, "total_steps": 38150, "loss": 0.7829, "lr": 4.755489824243331e-05, "epoch": 2.2778505897771955, "percentage": 22.78, "elapsed_time": "0:14:42", "remaining_time": "0:49:52", "throughput": 2643.85, "total_tokens": 2333512} {"current_steps": 8695, "total_steps": 38150, "loss": 0.4363, "lr": 4.754996267998589e-05, "epoch": 2.2791612057667106, "percentage": 22.79, "elapsed_time": "0:14:43", "remaining_time": "0:49:51", "throughput": 2643.98, "total_tokens": 2334792} {"current_steps": 8700, "total_steps": 38150, "loss": 0.3812, "lr": 4.754502239787024e-05, "epoch": 2.280471821756225, "percentage": 22.8, "elapsed_time": "0:14:43", "remaining_time": "0:49:50", "throughput": 2644.11, "total_tokens": 2336040} {"current_steps": 8705, "total_steps": 38150, "loss": 0.5371, "lr": 4.7540077397120365e-05, "epoch": 2.2817824377457407, "percentage": 22.82, "elapsed_time": "0:14:43", "remaining_time": "0:49:49", "throughput": 2643.86, "total_tokens": 2336936} {"current_steps": 8710, "total_steps": 38150, "loss": 0.5389, "lr": 4.7535127678771233e-05, "epoch": 2.2830930537352554, "percentage": 22.83, "elapsed_time": "0:14:44", "remaining_time": "0:49:49", "throughput": 2644.27, "total_tokens": 2338664} {"current_steps": 8715, "total_steps": 38150, "loss": 0.4584, "lr": 4.7530173243858814e-05, "epoch": 2.2844036697247705, "percentage": 22.84, "elapsed_time": "0:14:44", "remaining_time": "0:49:48", "throughput": 2644.3, "total_tokens": 2339816} {"current_steps": 8720, "total_steps": 38150, "loss": 0.4336, "lr": 4.7525214093420065e-05, "epoch": 2.2857142857142856, "percentage": 22.86, "elapsed_time": "0:14:45", "remaining_time": "0:49:47", "throughput": 2644.39, "total_tokens": 2341128} {"current_steps": 8725, "total_steps": 38150, "loss": 0.3475, "lr": 4.7520250228492934e-05, "epoch": 2.2870249017038007, "percentage": 22.87, "elapsed_time": "0:14:45", "remaining_time": "0:49:47", "throughput": 2644.31, "total_tokens": 2342184} {"current_steps": 8730, "total_steps": 38150, "loss": 0.3505, "lr": 4.751528165011633e-05, "epoch": 2.288335517693316, "percentage": 22.88, "elapsed_time": "0:14:46", "remaining_time": "0:49:46", "throughput": 2644.7, "total_tokens": 2343960} {"current_steps": 8735, "total_steps": 38150, "loss": 0.3953, "lr": 4.7510308359330194e-05, "epoch": 2.289646133682831, "percentage": 22.9, "elapsed_time": "0:14:46", "remaining_time": "0:49:46", "throughput": 2644.82, "total_tokens": 2345208} {"current_steps": 8740, "total_steps": 38150, "loss": 0.5168, "lr": 4.7505330357175406e-05, "epoch": 2.290956749672346, "percentage": 22.91, "elapsed_time": "0:14:47", "remaining_time": "0:49:45", "throughput": 2645.0, "total_tokens": 2346568} {"current_steps": 8745, "total_steps": 38150, "loss": 0.4923, "lr": 4.750034764469386e-05, "epoch": 2.292267365661861, "percentage": 22.92, "elapsed_time": "0:14:47", "remaining_time": "0:49:44", "throughput": 2644.99, "total_tokens": 2347656} {"current_steps": 8750, "total_steps": 38150, "loss": 0.4047, "lr": 4.749536022292842e-05, "epoch": 2.293577981651376, "percentage": 22.94, "elapsed_time": "0:14:48", "remaining_time": "0:49:43", "throughput": 2645.23, "total_tokens": 2349112} {"current_steps": 8755, "total_steps": 38150, "loss": 0.3139, "lr": 4.7490368092922964e-05, "epoch": 2.2948885976408913, "percentage": 22.95, "elapsed_time": "0:14:48", "remaining_time": "0:49:43", "throughput": 2645.5, "total_tokens": 2350536} {"current_steps": 8760, "total_steps": 38150, "loss": 0.7901, "lr": 4.748537125572233e-05, "epoch": 2.2961992136304064, "percentage": 22.96, "elapsed_time": "0:14:49", "remaining_time": "0:49:42", "throughput": 2645.99, "total_tokens": 2352472} {"current_steps": 8765, "total_steps": 38150, "loss": 0.6527, "lr": 4.748036971237234e-05, "epoch": 2.2975098296199215, "percentage": 22.98, "elapsed_time": "0:14:49", "remaining_time": "0:49:42", "throughput": 2646.17, "total_tokens": 2353784} {"current_steps": 8770, "total_steps": 38150, "loss": 0.3771, "lr": 4.747536346391981e-05, "epoch": 2.2988204456094365, "percentage": 22.99, "elapsed_time": "0:14:49", "remaining_time": "0:49:41", "throughput": 2646.41, "total_tokens": 2355240} {"current_steps": 8775, "total_steps": 38150, "loss": 0.3774, "lr": 4.747035251141254e-05, "epoch": 2.3001310615989516, "percentage": 23.0, "elapsed_time": "0:14:50", "remaining_time": "0:49:40", "throughput": 2646.35, "total_tokens": 2356312} {"current_steps": 8780, "total_steps": 38150, "loss": 0.3588, "lr": 4.746533685589932e-05, "epoch": 2.3014416775884667, "percentage": 23.01, "elapsed_time": "0:14:50", "remaining_time": "0:49:39", "throughput": 2646.51, "total_tokens": 2357624} {"current_steps": 8785, "total_steps": 38150, "loss": 0.4801, "lr": 4.746031649842991e-05, "epoch": 2.302752293577982, "percentage": 23.03, "elapsed_time": "0:14:51", "remaining_time": "0:49:39", "throughput": 2646.67, "total_tokens": 2358984} {"current_steps": 8790, "total_steps": 38150, "loss": 0.3515, "lr": 4.745529144005507e-05, "epoch": 2.304062909567497, "percentage": 23.04, "elapsed_time": "0:14:51", "remaining_time": "0:49:38", "throughput": 2646.61, "total_tokens": 2360056} {"current_steps": 8795, "total_steps": 38150, "loss": 0.7031, "lr": 4.745026168182654e-05, "epoch": 2.3053735255570116, "percentage": 23.05, "elapsed_time": "0:14:52", "remaining_time": "0:49:39", "throughput": 2648.07, "total_tokens": 2363800} {"current_steps": 8800, "total_steps": 38150, "loss": 0.4003, "lr": 4.744522722479701e-05, "epoch": 2.3066841415465267, "percentage": 23.07, "elapsed_time": "0:14:53", "remaining_time": "0:49:38", "throughput": 2648.22, "total_tokens": 2365224} {"current_steps": 8805, "total_steps": 38150, "loss": 0.617, "lr": 4.7440188070020217e-05, "epoch": 2.3079947575360418, "percentage": 23.08, "elapsed_time": "0:14:53", "remaining_time": "0:49:38", "throughput": 2648.56, "total_tokens": 2366840} {"current_steps": 8810, "total_steps": 38150, "loss": 0.3769, "lr": 4.7435144218550834e-05, "epoch": 2.309305373525557, "percentage": 23.09, "elapsed_time": "0:14:54", "remaining_time": "0:49:37", "throughput": 2648.84, "total_tokens": 2368424} {"current_steps": 8815, "total_steps": 38150, "loss": 1.0062, "lr": 4.7430095671444526e-05, "epoch": 2.310615989515072, "percentage": 23.11, "elapsed_time": "0:14:54", "remaining_time": "0:49:37", "throughput": 2649.11, "total_tokens": 2370024} {"current_steps": 8820, "total_steps": 38150, "loss": 0.3014, "lr": 4.742504242975795e-05, "epoch": 2.311926605504587, "percentage": 23.12, "elapsed_time": "0:14:55", "remaining_time": "0:49:36", "throughput": 2649.39, "total_tokens": 2371448} {"current_steps": 8825, "total_steps": 38150, "loss": 0.5676, "lr": 4.7419984494548744e-05, "epoch": 2.313237221494102, "percentage": 23.13, "elapsed_time": "0:14:55", "remaining_time": "0:49:35", "throughput": 2649.8, "total_tokens": 2373080} {"current_steps": 8830, "total_steps": 38150, "loss": 0.5342, "lr": 4.7414921866875524e-05, "epoch": 2.3145478374836173, "percentage": 23.15, "elapsed_time": "0:14:55", "remaining_time": "0:49:35", "throughput": 2649.67, "total_tokens": 2374088} {"current_steps": 8835, "total_steps": 38150, "loss": 0.4104, "lr": 4.740985454779788e-05, "epoch": 2.3158584534731324, "percentage": 23.16, "elapsed_time": "0:14:56", "remaining_time": "0:49:34", "throughput": 2650.12, "total_tokens": 2375848} {"current_steps": 8840, "total_steps": 38150, "loss": 0.3652, "lr": 4.740478253837641e-05, "epoch": 2.3171690694626474, "percentage": 23.17, "elapsed_time": "0:14:56", "remaining_time": "0:49:33", "throughput": 2650.04, "total_tokens": 2376920} {"current_steps": 8845, "total_steps": 38150, "loss": 0.5764, "lr": 4.739970583967266e-05, "epoch": 2.3184796854521625, "percentage": 23.18, "elapsed_time": "0:14:57", "remaining_time": "0:49:33", "throughput": 2650.47, "total_tokens": 2378584} {"current_steps": 8850, "total_steps": 38150, "loss": 0.6584, "lr": 4.739462445274919e-05, "epoch": 2.3197903014416776, "percentage": 23.2, "elapsed_time": "0:14:57", "remaining_time": "0:49:32", "throughput": 2650.58, "total_tokens": 2379848} {"current_steps": 8855, "total_steps": 38150, "loss": 0.418, "lr": 4.738953837866951e-05, "epoch": 2.3211009174311927, "percentage": 23.21, "elapsed_time": "0:14:58", "remaining_time": "0:49:31", "throughput": 2650.64, "total_tokens": 2381048} {"current_steps": 8860, "total_steps": 38150, "loss": 0.3726, "lr": 4.738444761849813e-05, "epoch": 2.322411533420708, "percentage": 23.22, "elapsed_time": "0:14:58", "remaining_time": "0:49:31", "throughput": 2650.7, "total_tokens": 2382232} {"current_steps": 8865, "total_steps": 38150, "loss": 0.5525, "lr": 4.7379352173300553e-05, "epoch": 2.323722149410223, "percentage": 23.24, "elapsed_time": "0:14:59", "remaining_time": "0:49:30", "throughput": 2650.71, "total_tokens": 2383368} {"current_steps": 8870, "total_steps": 38150, "loss": 0.409, "lr": 4.737425204414322e-05, "epoch": 2.325032765399738, "percentage": 23.25, "elapsed_time": "0:14:59", "remaining_time": "0:49:29", "throughput": 2651.14, "total_tokens": 2385032} {"current_steps": 8875, "total_steps": 38150, "loss": 0.2479, "lr": 4.73691472320936e-05, "epoch": 2.326343381389253, "percentage": 23.26, "elapsed_time": "0:15:00", "remaining_time": "0:49:30", "throughput": 2652.3, "total_tokens": 2388264} {"current_steps": 8880, "total_steps": 38150, "loss": 0.4851, "lr": 4.736403773822012e-05, "epoch": 2.327653997378768, "percentage": 23.28, "elapsed_time": "0:15:00", "remaining_time": "0:49:29", "throughput": 2652.35, "total_tokens": 2389464} {"current_steps": 8885, "total_steps": 38150, "loss": 0.4147, "lr": 4.735892356359217e-05, "epoch": 2.3289646133682833, "percentage": 23.29, "elapsed_time": "0:15:01", "remaining_time": "0:49:28", "throughput": 2652.24, "total_tokens": 2390456} {"current_steps": 8890, "total_steps": 38150, "loss": 0.5938, "lr": 4.735380470928017e-05, "epoch": 2.330275229357798, "percentage": 23.3, "elapsed_time": "0:15:01", "remaining_time": "0:49:28", "throughput": 2652.64, "total_tokens": 2392168} {"current_steps": 8895, "total_steps": 38150, "loss": 0.3575, "lr": 4.7348681176355456e-05, "epoch": 2.331585845347313, "percentage": 23.32, "elapsed_time": "0:15:02", "remaining_time": "0:49:27", "throughput": 2652.72, "total_tokens": 2393464} {"current_steps": 8900, "total_steps": 38150, "loss": 0.6183, "lr": 4.734355296589039e-05, "epoch": 2.332896461336828, "percentage": 23.33, "elapsed_time": "0:15:02", "remaining_time": "0:49:26", "throughput": 2653.13, "total_tokens": 2395064} {"current_steps": 8905, "total_steps": 38150, "loss": 0.4551, "lr": 4.73384200789583e-05, "epoch": 2.3342070773263432, "percentage": 23.34, "elapsed_time": "0:15:03", "remaining_time": "0:49:26", "throughput": 2653.07, "total_tokens": 2396232} {"current_steps": 8910, "total_steps": 38150, "loss": 0.4187, "lr": 4.733328251663348e-05, "epoch": 2.3355176933158583, "percentage": 23.36, "elapsed_time": "0:15:03", "remaining_time": "0:49:25", "throughput": 2653.2, "total_tokens": 2397544} {"current_steps": 8915, "total_steps": 38150, "loss": 0.3438, "lr": 4.732814027999122e-05, "epoch": 2.3368283093053734, "percentage": 23.37, "elapsed_time": "0:15:04", "remaining_time": "0:49:24", "throughput": 2653.33, "total_tokens": 2398824} {"current_steps": 8920, "total_steps": 38150, "loss": 0.6503, "lr": 4.7322993370107775e-05, "epoch": 2.3381389252948885, "percentage": 23.38, "elapsed_time": "0:15:04", "remaining_time": "0:49:23", "throughput": 2653.19, "total_tokens": 2399816} {"current_steps": 8925, "total_steps": 38150, "loss": 0.4588, "lr": 4.7317841788060394e-05, "epoch": 2.3394495412844036, "percentage": 23.39, "elapsed_time": "0:15:04", "remaining_time": "0:49:23", "throughput": 2653.17, "total_tokens": 2400952} {"current_steps": 8930, "total_steps": 38150, "loss": 0.3626, "lr": 4.731268553492729e-05, "epoch": 2.3407601572739187, "percentage": 23.41, "elapsed_time": "0:15:05", "remaining_time": "0:49:22", "throughput": 2653.23, "total_tokens": 2402120} {"current_steps": 8935, "total_steps": 38150, "loss": 0.3758, "lr": 4.730752461178766e-05, "epoch": 2.342070773263434, "percentage": 23.42, "elapsed_time": "0:15:05", "remaining_time": "0:49:21", "throughput": 2653.38, "total_tokens": 2403432} {"current_steps": 8940, "total_steps": 38150, "loss": 0.4225, "lr": 4.730235901972166e-05, "epoch": 2.343381389252949, "percentage": 23.43, "elapsed_time": "0:15:06", "remaining_time": "0:49:21", "throughput": 2653.8, "total_tokens": 2405160} {"current_steps": 8945, "total_steps": 38150, "loss": 0.3222, "lr": 4.729718875981046e-05, "epoch": 2.344692005242464, "percentage": 23.45, "elapsed_time": "0:15:06", "remaining_time": "0:49:20", "throughput": 2654.05, "total_tokens": 2406536} {"current_steps": 8950, "total_steps": 38150, "loss": 0.5067, "lr": 4.729201383313618e-05, "epoch": 2.346002621231979, "percentage": 23.46, "elapsed_time": "0:15:07", "remaining_time": "0:49:19", "throughput": 2654.33, "total_tokens": 2407992} {"current_steps": 8955, "total_steps": 38150, "loss": 0.2141, "lr": 4.7286834240781925e-05, "epoch": 2.347313237221494, "percentage": 23.47, "elapsed_time": "0:15:07", "remaining_time": "0:49:18", "throughput": 2654.23, "total_tokens": 2409016} {"current_steps": 8960, "total_steps": 38150, "loss": 0.5025, "lr": 4.728164998383177e-05, "epoch": 2.3486238532110093, "percentage": 23.49, "elapsed_time": "0:15:08", "remaining_time": "0:49:18", "throughput": 2654.52, "total_tokens": 2410472} {"current_steps": 8965, "total_steps": 38150, "loss": 0.3503, "lr": 4.727646106337077e-05, "epoch": 2.3499344692005244, "percentage": 23.5, "elapsed_time": "0:15:08", "remaining_time": "0:49:17", "throughput": 2654.41, "total_tokens": 2411496} {"current_steps": 8970, "total_steps": 38150, "loss": 0.4047, "lr": 4.727126748048496e-05, "epoch": 2.3512450851900395, "percentage": 23.51, "elapsed_time": "0:15:08", "remaining_time": "0:49:16", "throughput": 2654.5, "total_tokens": 2412696} {"current_steps": 8975, "total_steps": 38150, "loss": 0.3564, "lr": 4.726606923626135e-05, "epoch": 2.352555701179554, "percentage": 23.53, "elapsed_time": "0:15:09", "remaining_time": "0:49:15", "throughput": 2654.67, "total_tokens": 2414008} {"current_steps": 8980, "total_steps": 38150, "loss": 0.3402, "lr": 4.726086633178792e-05, "epoch": 2.3538663171690697, "percentage": 23.54, "elapsed_time": "0:15:09", "remaining_time": "0:49:15", "throughput": 2654.8, "total_tokens": 2415272} {"current_steps": 8985, "total_steps": 38150, "loss": 0.5096, "lr": 4.7255658768153635e-05, "epoch": 2.3551769331585843, "percentage": 23.55, "elapsed_time": "0:15:10", "remaining_time": "0:49:14", "throughput": 2655.38, "total_tokens": 2417240} {"current_steps": 8990, "total_steps": 38150, "loss": 0.5479, "lr": 4.725044654644842e-05, "epoch": 2.3564875491480994, "percentage": 23.56, "elapsed_time": "0:15:10", "remaining_time": "0:49:14", "throughput": 2655.4, "total_tokens": 2418376} {"current_steps": 8995, "total_steps": 38150, "loss": 0.4134, "lr": 4.724522966776319e-05, "epoch": 2.3577981651376145, "percentage": 23.58, "elapsed_time": "0:15:11", "remaining_time": "0:49:13", "throughput": 2655.76, "total_tokens": 2420120} {"current_steps": 9000, "total_steps": 38150, "loss": 0.4695, "lr": 4.7240008133189836e-05, "epoch": 2.3591087811271296, "percentage": 23.59, "elapsed_time": "0:15:11", "remaining_time": "0:49:12", "throughput": 2655.69, "total_tokens": 2421160} {"current_steps": 9005, "total_steps": 38150, "loss": 0.3422, "lr": 4.723478194382119e-05, "epoch": 2.3604193971166447, "percentage": 23.6, "elapsed_time": "0:15:12", "remaining_time": "0:49:12", "throughput": 2656.12, "total_tokens": 2423048} {"current_steps": 9010, "total_steps": 38150, "loss": 0.3498, "lr": 4.722955110075112e-05, "epoch": 2.36173001310616, "percentage": 23.62, "elapsed_time": "0:15:12", "remaining_time": "0:49:11", "throughput": 2656.41, "total_tokens": 2424504} {"current_steps": 9015, "total_steps": 38150, "loss": 0.3784, "lr": 4.7224315605074403e-05, "epoch": 2.363040629095675, "percentage": 23.63, "elapsed_time": "0:15:13", "remaining_time": "0:49:11", "throughput": 2656.19, "total_tokens": 2425416} {"current_steps": 9020, "total_steps": 38150, "loss": 0.3864, "lr": 4.7219075457886836e-05, "epoch": 2.36435124508519, "percentage": 23.64, "elapsed_time": "0:15:13", "remaining_time": "0:49:10", "throughput": 2656.58, "total_tokens": 2427176} {"current_steps": 9025, "total_steps": 38150, "loss": 0.5242, "lr": 4.721383066028516e-05, "epoch": 2.365661861074705, "percentage": 23.66, "elapsed_time": "0:15:14", "remaining_time": "0:49:09", "throughput": 2656.64, "total_tokens": 2428360} {"current_steps": 9030, "total_steps": 38150, "loss": 0.3506, "lr": 4.720858121336712e-05, "epoch": 2.36697247706422, "percentage": 23.67, "elapsed_time": "0:15:14", "remaining_time": "0:49:09", "throughput": 2656.82, "total_tokens": 2429688} {"current_steps": 9035, "total_steps": 38150, "loss": 0.4718, "lr": 4.72033271182314e-05, "epoch": 2.3682830930537353, "percentage": 23.68, "elapsed_time": "0:15:14", "remaining_time": "0:49:08", "throughput": 2656.71, "total_tokens": 2430712} {"current_steps": 9040, "total_steps": 38150, "loss": 0.476, "lr": 4.7198068375977675e-05, "epoch": 2.3695937090432504, "percentage": 23.7, "elapsed_time": "0:15:15", "remaining_time": "0:49:07", "throughput": 2656.91, "total_tokens": 2432072} {"current_steps": 9045, "total_steps": 38150, "loss": 0.3583, "lr": 4.71928049877066e-05, "epoch": 2.3709043250327655, "percentage": 23.71, "elapsed_time": "0:15:15", "remaining_time": "0:49:06", "throughput": 2656.99, "total_tokens": 2433288} {"current_steps": 9050, "total_steps": 38150, "loss": 0.3707, "lr": 4.718753695451978e-05, "epoch": 2.3722149410222806, "percentage": 23.72, "elapsed_time": "0:15:16", "remaining_time": "0:49:06", "throughput": 2657.07, "total_tokens": 2434616} {"current_steps": 9055, "total_steps": 38150, "loss": 0.5526, "lr": 4.718226427751982e-05, "epoch": 2.3735255570117957, "percentage": 23.74, "elapsed_time": "0:15:16", "remaining_time": "0:49:05", "throughput": 2657.02, "total_tokens": 2435688} {"current_steps": 9060, "total_steps": 38150, "loss": 0.4818, "lr": 4.7176986957810275e-05, "epoch": 2.374836173001311, "percentage": 23.75, "elapsed_time": "0:15:17", "remaining_time": "0:49:04", "throughput": 2657.49, "total_tokens": 2437416} {"current_steps": 9065, "total_steps": 38150, "loss": 0.4802, "lr": 4.717170499649568e-05, "epoch": 2.376146788990826, "percentage": 23.76, "elapsed_time": "0:15:17", "remaining_time": "0:49:04", "throughput": 2657.23, "total_tokens": 2438280} {"current_steps": 9070, "total_steps": 38150, "loss": 0.5252, "lr": 4.7166418394681526e-05, "epoch": 2.3774574049803405, "percentage": 23.77, "elapsed_time": "0:15:18", "remaining_time": "0:49:03", "throughput": 2657.42, "total_tokens": 2439784} {"current_steps": 9075, "total_steps": 38150, "loss": 0.3802, "lr": 4.716112715347432e-05, "epoch": 2.378768020969856, "percentage": 23.79, "elapsed_time": "0:15:18", "remaining_time": "0:49:02", "throughput": 2657.56, "total_tokens": 2441160} {"current_steps": 9080, "total_steps": 38150, "loss": 0.4147, "lr": 4.715583127398148e-05, "epoch": 2.3800786369593707, "percentage": 23.8, "elapsed_time": "0:15:19", "remaining_time": "0:49:02", "throughput": 2657.53, "total_tokens": 2442328} {"current_steps": 9085, "total_steps": 38150, "loss": 0.2599, "lr": 4.715053075731144e-05, "epoch": 2.381389252948886, "percentage": 23.81, "elapsed_time": "0:15:19", "remaining_time": "0:49:01", "throughput": 2657.48, "total_tokens": 2443432} {"current_steps": 9090, "total_steps": 38150, "loss": 0.4452, "lr": 4.714522560457359e-05, "epoch": 2.382699868938401, "percentage": 23.83, "elapsed_time": "0:15:19", "remaining_time": "0:49:00", "throughput": 2657.33, "total_tokens": 2444488} {"current_steps": 9095, "total_steps": 38150, "loss": 0.5944, "lr": 4.713991581687827e-05, "epoch": 2.384010484927916, "percentage": 23.84, "elapsed_time": "0:15:20", "remaining_time": "0:49:00", "throughput": 2657.3, "total_tokens": 2445592} {"current_steps": 9100, "total_steps": 38150, "loss": 0.399, "lr": 4.7134601395336836e-05, "epoch": 2.385321100917431, "percentage": 23.85, "elapsed_time": "0:15:20", "remaining_time": "0:48:59", "throughput": 2657.63, "total_tokens": 2447256} {"current_steps": 9105, "total_steps": 38150, "loss": 0.3433, "lr": 4.712928234106158e-05, "epoch": 2.386631716906946, "percentage": 23.87, "elapsed_time": "0:15:21", "remaining_time": "0:48:58", "throughput": 2657.73, "total_tokens": 2448472} {"current_steps": 9110, "total_steps": 38150, "loss": 0.435, "lr": 4.712395865516576e-05, "epoch": 2.3879423328964613, "percentage": 23.88, "elapsed_time": "0:15:21", "remaining_time": "0:48:58", "throughput": 2657.89, "total_tokens": 2449880} {"current_steps": 9115, "total_steps": 38150, "loss": 0.3688, "lr": 4.711863033876362e-05, "epoch": 2.3892529488859764, "percentage": 23.89, "elapsed_time": "0:15:22", "remaining_time": "0:48:57", "throughput": 2657.82, "total_tokens": 2450936} {"current_steps": 9120, "total_steps": 38150, "loss": 0.4681, "lr": 4.7113297392970365e-05, "epoch": 2.3905635648754915, "percentage": 23.91, "elapsed_time": "0:15:22", "remaining_time": "0:48:56", "throughput": 2658.1, "total_tokens": 2452488} {"current_steps": 9125, "total_steps": 38150, "loss": 0.4613, "lr": 4.710795981890218e-05, "epoch": 2.3918741808650066, "percentage": 23.92, "elapsed_time": "0:15:23", "remaining_time": "0:48:56", "throughput": 2658.37, "total_tokens": 2453960} {"current_steps": 9130, "total_steps": 38150, "loss": 0.4686, "lr": 4.7102617617676203e-05, "epoch": 2.3931847968545217, "percentage": 23.93, "elapsed_time": "0:15:23", "remaining_time": "0:48:55", "throughput": 2658.42, "total_tokens": 2455208} {"current_steps": 9135, "total_steps": 38150, "loss": 0.3053, "lr": 4.7097270790410555e-05, "epoch": 2.3944954128440368, "percentage": 23.94, "elapsed_time": "0:15:23", "remaining_time": "0:48:54", "throughput": 2658.25, "total_tokens": 2456152} {"current_steps": 9140, "total_steps": 38150, "loss": 0.5273, "lr": 4.709191933822431e-05, "epoch": 2.395806028833552, "percentage": 23.96, "elapsed_time": "0:15:24", "remaining_time": "0:48:54", "throughput": 2658.4, "total_tokens": 2457528} {"current_steps": 9145, "total_steps": 38150, "loss": 0.2617, "lr": 4.7086563262237514e-05, "epoch": 2.397116644823067, "percentage": 23.97, "elapsed_time": "0:15:24", "remaining_time": "0:48:53", "throughput": 2658.43, "total_tokens": 2458792} {"current_steps": 9150, "total_steps": 38150, "loss": 0.3587, "lr": 4.7081202563571194e-05, "epoch": 2.398427260812582, "percentage": 23.98, "elapsed_time": "0:15:25", "remaining_time": "0:48:52", "throughput": 2658.44, "total_tokens": 2459928} {"current_steps": 9155, "total_steps": 38150, "loss": 0.4943, "lr": 4.707583724334732e-05, "epoch": 2.399737876802097, "percentage": 24.0, "elapsed_time": "0:15:25", "remaining_time": "0:48:52", "throughput": 2658.62, "total_tokens": 2461304} {"current_steps": 9160, "total_steps": 38150, "loss": 0.5568, "lr": 4.707046730268887e-05, "epoch": 2.4010484927916123, "percentage": 24.01, "elapsed_time": "0:15:26", "remaining_time": "0:48:51", "throughput": 2658.53, "total_tokens": 2462440} {"current_steps": 9165, "total_steps": 38150, "loss": 0.5643, "lr": 4.706509274271974e-05, "epoch": 2.402359108781127, "percentage": 24.02, "elapsed_time": "0:15:26", "remaining_time": "0:48:50", "throughput": 2658.72, "total_tokens": 2463864} {"current_steps": 9170, "total_steps": 38150, "loss": 0.6742, "lr": 4.705971356456483e-05, "epoch": 2.4036697247706424, "percentage": 24.04, "elapsed_time": "0:15:27", "remaining_time": "0:48:50", "throughput": 2659.21, "total_tokens": 2465688} {"current_steps": 9175, "total_steps": 38150, "loss": 0.4598, "lr": 4.7054329769349984e-05, "epoch": 2.404980340760157, "percentage": 24.05, "elapsed_time": "0:15:27", "remaining_time": "0:48:49", "throughput": 2659.52, "total_tokens": 2467320} {"current_steps": 9180, "total_steps": 38150, "loss": 0.3214, "lr": 4.704894135820202e-05, "epoch": 2.406290956749672, "percentage": 24.06, "elapsed_time": "0:15:28", "remaining_time": "0:48:49", "throughput": 2659.66, "total_tokens": 2468680} {"current_steps": 9185, "total_steps": 38150, "loss": 0.6257, "lr": 4.704354833224873e-05, "epoch": 2.4076015727391873, "percentage": 24.08, "elapsed_time": "0:15:28", "remaining_time": "0:48:48", "throughput": 2659.9, "total_tokens": 2470088} {"current_steps": 9190, "total_steps": 38150, "loss": 0.5112, "lr": 4.7038150692618864e-05, "epoch": 2.4089121887287024, "percentage": 24.09, "elapsed_time": "0:15:29", "remaining_time": "0:48:47", "throughput": 2660.07, "total_tokens": 2471416} {"current_steps": 9195, "total_steps": 38150, "loss": 0.4801, "lr": 4.703274844044214e-05, "epoch": 2.4102228047182175, "percentage": 24.1, "elapsed_time": "0:15:29", "remaining_time": "0:48:46", "throughput": 2659.98, "total_tokens": 2472456} {"current_steps": 9200, "total_steps": 38150, "loss": 0.5217, "lr": 4.702734157684924e-05, "epoch": 2.4115334207077326, "percentage": 24.12, "elapsed_time": "0:15:29", "remaining_time": "0:48:46", "throughput": 2659.78, "total_tokens": 2473400} {"current_steps": 9205, "total_steps": 38150, "loss": 0.3236, "lr": 4.7021930102971796e-05, "epoch": 2.4128440366972477, "percentage": 24.13, "elapsed_time": "0:15:30", "remaining_time": "0:48:45", "throughput": 2659.86, "total_tokens": 2474616} {"current_steps": 9210, "total_steps": 38150, "loss": 0.4183, "lr": 4.701651401994244e-05, "epoch": 2.4141546526867628, "percentage": 24.14, "elapsed_time": "0:15:30", "remaining_time": "0:48:44", "throughput": 2659.86, "total_tokens": 2475752} {"current_steps": 9215, "total_steps": 38150, "loss": 0.3715, "lr": 4.701109332889474e-05, "epoch": 2.415465268676278, "percentage": 24.15, "elapsed_time": "0:15:31", "remaining_time": "0:48:44", "throughput": 2660.04, "total_tokens": 2477064} {"current_steps": 9220, "total_steps": 38150, "loss": 0.4336, "lr": 4.700566803096324e-05, "epoch": 2.416775884665793, "percentage": 24.17, "elapsed_time": "0:15:31", "remaining_time": "0:48:43", "throughput": 2660.22, "total_tokens": 2478472} {"current_steps": 9225, "total_steps": 38150, "loss": 0.2746, "lr": 4.700023812728344e-05, "epoch": 2.418086500655308, "percentage": 24.18, "elapsed_time": "0:15:32", "remaining_time": "0:48:42", "throughput": 2660.74, "total_tokens": 2480408} {"current_steps": 9230, "total_steps": 38150, "loss": 0.5306, "lr": 4.699480361899181e-05, "epoch": 2.419397116644823, "percentage": 24.19, "elapsed_time": "0:15:32", "remaining_time": "0:48:42", "throughput": 2660.88, "total_tokens": 2481704} {"current_steps": 9235, "total_steps": 38150, "loss": 0.2422, "lr": 4.6989364507225795e-05, "epoch": 2.4207077326343382, "percentage": 24.21, "elapsed_time": "0:15:33", "remaining_time": "0:48:41", "throughput": 2660.82, "total_tokens": 2482776} {"current_steps": 9240, "total_steps": 38150, "loss": 0.4053, "lr": 4.698392079312378e-05, "epoch": 2.4220183486238533, "percentage": 24.22, "elapsed_time": "0:15:33", "remaining_time": "0:48:40", "throughput": 2661.12, "total_tokens": 2484376} {"current_steps": 9245, "total_steps": 38150, "loss": 0.4653, "lr": 4.697847247782513e-05, "epoch": 2.4233289646133684, "percentage": 24.23, "elapsed_time": "0:15:34", "remaining_time": "0:48:40", "throughput": 2661.51, "total_tokens": 2486088} {"current_steps": 9250, "total_steps": 38150, "loss": 0.5628, "lr": 4.6973019562470166e-05, "epoch": 2.4246395806028835, "percentage": 24.25, "elapsed_time": "0:15:34", "remaining_time": "0:48:39", "throughput": 2661.57, "total_tokens": 2487320} {"current_steps": 9255, "total_steps": 38150, "loss": 0.4731, "lr": 4.6967562048200176e-05, "epoch": 2.4259501965923986, "percentage": 24.26, "elapsed_time": "0:15:34", "remaining_time": "0:48:39", "throughput": 2661.54, "total_tokens": 2488424} {"current_steps": 9260, "total_steps": 38150, "loss": 0.3803, "lr": 4.69620999361574e-05, "epoch": 2.4272608125819133, "percentage": 24.27, "elapsed_time": "0:15:35", "remaining_time": "0:48:38", "throughput": 2661.47, "total_tokens": 2489480} {"current_steps": 9265, "total_steps": 38150, "loss": 0.5882, "lr": 4.695663322748506e-05, "epoch": 2.4285714285714284, "percentage": 24.29, "elapsed_time": "0:15:35", "remaining_time": "0:48:37", "throughput": 2661.72, "total_tokens": 2490872} {"current_steps": 9270, "total_steps": 38150, "loss": 0.3992, "lr": 4.6951161923327324e-05, "epoch": 2.4298820445609435, "percentage": 24.3, "elapsed_time": "0:15:36", "remaining_time": "0:48:36", "throughput": 2661.84, "total_tokens": 2492152} {"current_steps": 9275, "total_steps": 38150, "loss": 0.3816, "lr": 4.694568602482933e-05, "epoch": 2.4311926605504586, "percentage": 24.31, "elapsed_time": "0:15:36", "remaining_time": "0:48:36", "throughput": 2662.1, "total_tokens": 2493640} {"current_steps": 9280, "total_steps": 38150, "loss": 0.3267, "lr": 4.694020553313716e-05, "epoch": 2.4325032765399737, "percentage": 24.33, "elapsed_time": "0:15:37", "remaining_time": "0:48:35", "throughput": 2662.12, "total_tokens": 2494792} {"current_steps": 9285, "total_steps": 38150, "loss": 0.3722, "lr": 4.693472044939788e-05, "epoch": 2.4338138925294888, "percentage": 24.34, "elapsed_time": "0:15:37", "remaining_time": "0:48:34", "throughput": 2662.21, "total_tokens": 2496200} {"current_steps": 9290, "total_steps": 38150, "loss": 0.4431, "lr": 4.692923077475952e-05, "epoch": 2.435124508519004, "percentage": 24.35, "elapsed_time": "0:15:38", "remaining_time": "0:48:34", "throughput": 2662.37, "total_tokens": 2497544} {"current_steps": 9295, "total_steps": 38150, "loss": 0.5119, "lr": 4.6923736510371054e-05, "epoch": 2.436435124508519, "percentage": 24.36, "elapsed_time": "0:15:38", "remaining_time": "0:48:33", "throughput": 2662.48, "total_tokens": 2498856} {"current_steps": 9300, "total_steps": 38150, "loss": 0.4525, "lr": 4.69182376573824e-05, "epoch": 2.437745740498034, "percentage": 24.38, "elapsed_time": "0:15:39", "remaining_time": "0:48:32", "throughput": 2662.54, "total_tokens": 2500136} {"current_steps": 9305, "total_steps": 38150, "loss": 0.4249, "lr": 4.6912734216944486e-05, "epoch": 2.439056356487549, "percentage": 24.39, "elapsed_time": "0:15:39", "remaining_time": "0:48:32", "throughput": 2662.59, "total_tokens": 2501304} {"current_steps": 9310, "total_steps": 38150, "loss": 0.4001, "lr": 4.6907226190209165e-05, "epoch": 2.4403669724770642, "percentage": 24.4, "elapsed_time": "0:15:39", "remaining_time": "0:48:31", "throughput": 2662.83, "total_tokens": 2502792} {"current_steps": 9315, "total_steps": 38150, "loss": 0.3139, "lr": 4.6901713578329255e-05, "epoch": 2.4416775884665793, "percentage": 24.42, "elapsed_time": "0:15:40", "remaining_time": "0:48:30", "throughput": 2662.83, "total_tokens": 2503944} {"current_steps": 9320, "total_steps": 38150, "loss": 0.5171, "lr": 4.689619638245853e-05, "epoch": 2.4429882044560944, "percentage": 24.43, "elapsed_time": "0:15:40", "remaining_time": "0:48:30", "throughput": 2663.52, "total_tokens": 2505960} {"current_steps": 9325, "total_steps": 38150, "loss": 0.4452, "lr": 4.6890674603751746e-05, "epoch": 2.4442988204456095, "percentage": 24.44, "elapsed_time": "0:15:41", "remaining_time": "0:48:29", "throughput": 2663.87, "total_tokens": 2507480} {"current_steps": 9330, "total_steps": 38150, "loss": 0.5639, "lr": 4.688514824336459e-05, "epoch": 2.4456094364351246, "percentage": 24.46, "elapsed_time": "0:15:41", "remaining_time": "0:48:29", "throughput": 2664.7, "total_tokens": 2509928} {"current_steps": 9335, "total_steps": 38150, "loss": 0.5563, "lr": 4.687961730245371e-05, "epoch": 2.4469200524246397, "percentage": 24.47, "elapsed_time": "0:15:42", "remaining_time": "0:48:29", "throughput": 2664.87, "total_tokens": 2511496} {"current_steps": 9340, "total_steps": 38150, "loss": 0.3665, "lr": 4.687408178217674e-05, "epoch": 2.448230668414155, "percentage": 24.48, "elapsed_time": "0:15:42", "remaining_time": "0:48:28", "throughput": 2665.11, "total_tokens": 2512984} {"current_steps": 9345, "total_steps": 38150, "loss": 0.4214, "lr": 4.6868541683692244e-05, "epoch": 2.44954128440367, "percentage": 24.5, "elapsed_time": "0:15:43", "remaining_time": "0:48:27", "throughput": 2665.38, "total_tokens": 2514536} {"current_steps": 9350, "total_steps": 38150, "loss": 0.3716, "lr": 4.6862997008159774e-05, "epoch": 2.450851900393185, "percentage": 24.51, "elapsed_time": "0:15:43", "remaining_time": "0:48:27", "throughput": 2665.37, "total_tokens": 2515656} {"current_steps": 9355, "total_steps": 38150, "loss": 0.5093, "lr": 4.685744775673979e-05, "epoch": 2.4521625163826997, "percentage": 24.52, "elapsed_time": "0:15:44", "remaining_time": "0:48:26", "throughput": 2665.59, "total_tokens": 2517096} {"current_steps": 9360, "total_steps": 38150, "loss": 0.5214, "lr": 4.685189393059377e-05, "epoch": 2.4534731323722148, "percentage": 24.53, "elapsed_time": "0:15:44", "remaining_time": "0:48:25", "throughput": 2665.73, "total_tokens": 2518408} {"current_steps": 9365, "total_steps": 38150, "loss": 0.3649, "lr": 4.68463355308841e-05, "epoch": 2.45478374836173, "percentage": 24.55, "elapsed_time": "0:15:45", "remaining_time": "0:48:25", "throughput": 2665.63, "total_tokens": 2519512} {"current_steps": 9370, "total_steps": 38150, "loss": 0.3981, "lr": 4.684077255877415e-05, "epoch": 2.456094364351245, "percentage": 24.56, "elapsed_time": "0:15:45", "remaining_time": "0:48:24", "throughput": 2665.76, "total_tokens": 2520808} {"current_steps": 9375, "total_steps": 38150, "loss": 0.5966, "lr": 4.6835205015428246e-05, "epoch": 2.45740498034076, "percentage": 24.57, "elapsed_time": "0:15:46", "remaining_time": "0:48:23", "throughput": 2665.86, "total_tokens": 2522120} {"current_steps": 9380, "total_steps": 38150, "loss": 0.4801, "lr": 4.682963290201166e-05, "epoch": 2.458715596330275, "percentage": 24.59, "elapsed_time": "0:15:46", "remaining_time": "0:48:23", "throughput": 2665.97, "total_tokens": 2523384} {"current_steps": 9385, "total_steps": 38150, "loss": 0.4658, "lr": 4.682405621969062e-05, "epoch": 2.4600262123197902, "percentage": 24.6, "elapsed_time": "0:15:47", "remaining_time": "0:48:22", "throughput": 2666.25, "total_tokens": 2525144} {"current_steps": 9390, "total_steps": 38150, "loss": 0.4349, "lr": 4.681847496963233e-05, "epoch": 2.4613368283093053, "percentage": 24.61, "elapsed_time": "0:15:47", "remaining_time": "0:48:22", "throughput": 2666.17, "total_tokens": 2526168} {"current_steps": 9395, "total_steps": 38150, "loss": 0.6039, "lr": 4.6812889153004925e-05, "epoch": 2.4626474442988204, "percentage": 24.63, "elapsed_time": "0:15:47", "remaining_time": "0:48:21", "throughput": 2666.41, "total_tokens": 2527560} {"current_steps": 9400, "total_steps": 38150, "loss": 0.4109, "lr": 4.6807298770977516e-05, "epoch": 2.4639580602883355, "percentage": 24.64, "elapsed_time": "0:15:48", "remaining_time": "0:48:20", "throughput": 2666.72, "total_tokens": 2529176} {"current_steps": 9405, "total_steps": 38150, "loss": 0.5164, "lr": 4.6801703824720146e-05, "epoch": 2.4652686762778506, "percentage": 24.65, "elapsed_time": "0:15:48", "remaining_time": "0:48:19", "throughput": 2666.53, "total_tokens": 2530088} {"current_steps": 9410, "total_steps": 38150, "loss": 0.3906, "lr": 4.679610431540384e-05, "epoch": 2.4665792922673657, "percentage": 24.67, "elapsed_time": "0:15:49", "remaining_time": "0:48:19", "throughput": 2666.55, "total_tokens": 2531272} {"current_steps": 9415, "total_steps": 38150, "loss": 0.5097, "lr": 4.679050024420056e-05, "epoch": 2.467889908256881, "percentage": 24.68, "elapsed_time": "0:15:49", "remaining_time": "0:48:18", "throughput": 2666.74, "total_tokens": 2532696} {"current_steps": 9420, "total_steps": 38150, "loss": 0.4403, "lr": 4.678489161228323e-05, "epoch": 2.469200524246396, "percentage": 24.69, "elapsed_time": "0:15:50", "remaining_time": "0:48:17", "throughput": 2666.58, "total_tokens": 2533640} {"current_steps": 9425, "total_steps": 38150, "loss": 0.3883, "lr": 4.677927842082572e-05, "epoch": 2.470511140235911, "percentage": 24.71, "elapsed_time": "0:15:50", "remaining_time": "0:48:17", "throughput": 2666.65, "total_tokens": 2534856} {"current_steps": 9430, "total_steps": 38150, "loss": 0.3576, "lr": 4.6773660671002885e-05, "epoch": 2.471821756225426, "percentage": 24.72, "elapsed_time": "0:15:51", "remaining_time": "0:48:16", "throughput": 2666.75, "total_tokens": 2536152} {"current_steps": 9435, "total_steps": 38150, "loss": 0.5674, "lr": 4.676803836399048e-05, "epoch": 2.473132372214941, "percentage": 24.73, "elapsed_time": "0:15:51", "remaining_time": "0:48:15", "throughput": 2666.89, "total_tokens": 2537560} {"current_steps": 9440, "total_steps": 38150, "loss": 0.3399, "lr": 4.6762411500965265e-05, "epoch": 2.474442988204456, "percentage": 24.74, "elapsed_time": "0:15:51", "remaining_time": "0:48:15", "throughput": 2666.99, "total_tokens": 2538792} {"current_steps": 9445, "total_steps": 38150, "loss": 0.5611, "lr": 4.675678008310492e-05, "epoch": 2.4757536041939714, "percentage": 24.76, "elapsed_time": "0:15:52", "remaining_time": "0:48:14", "throughput": 2666.96, "total_tokens": 2539896} {"current_steps": 9450, "total_steps": 38150, "loss": 0.4399, "lr": 4.6751144111588094e-05, "epoch": 2.477064220183486, "percentage": 24.77, "elapsed_time": "0:15:52", "remaining_time": "0:48:13", "throughput": 2666.97, "total_tokens": 2541032} {"current_steps": 9455, "total_steps": 38150, "loss": 0.3441, "lr": 4.6745503587594396e-05, "epoch": 2.478374836173001, "percentage": 24.78, "elapsed_time": "0:15:53", "remaining_time": "0:48:12", "throughput": 2666.94, "total_tokens": 2542120} {"current_steps": 9460, "total_steps": 38150, "loss": 0.5922, "lr": 4.6739858512304366e-05, "epoch": 2.4796854521625162, "percentage": 24.8, "elapsed_time": "0:15:53", "remaining_time": "0:48:12", "throughput": 2666.77, "total_tokens": 2543096} {"current_steps": 9465, "total_steps": 38150, "loss": 0.3405, "lr": 4.673420888689952e-05, "epoch": 2.4809960681520313, "percentage": 24.81, "elapsed_time": "0:15:54", "remaining_time": "0:48:11", "throughput": 2666.78, "total_tokens": 2544328} {"current_steps": 9470, "total_steps": 38150, "loss": 0.4576, "lr": 4.67285547125623e-05, "epoch": 2.4823066841415464, "percentage": 24.82, "elapsed_time": "0:15:54", "remaining_time": "0:48:10", "throughput": 2666.78, "total_tokens": 2545448} {"current_steps": 9475, "total_steps": 38150, "loss": 0.4073, "lr": 4.6722895990476126e-05, "epoch": 2.4836173001310615, "percentage": 24.84, "elapsed_time": "0:15:54", "remaining_time": "0:48:09", "throughput": 2666.79, "total_tokens": 2546584} {"current_steps": 9480, "total_steps": 38150, "loss": 0.3813, "lr": 4.671723272182535e-05, "epoch": 2.4849279161205766, "percentage": 24.85, "elapsed_time": "0:15:55", "remaining_time": "0:48:09", "throughput": 2666.88, "total_tokens": 2547832} {"current_steps": 9485, "total_steps": 38150, "loss": 0.5927, "lr": 4.67115649077953e-05, "epoch": 2.4862385321100917, "percentage": 24.86, "elapsed_time": "0:15:55", "remaining_time": "0:48:08", "throughput": 2666.91, "total_tokens": 2549016} {"current_steps": 9490, "total_steps": 38150, "loss": 0.3309, "lr": 4.670589254957222e-05, "epoch": 2.487549148099607, "percentage": 24.88, "elapsed_time": "0:15:56", "remaining_time": "0:48:07", "throughput": 2667.11, "total_tokens": 2550392} {"current_steps": 9495, "total_steps": 38150, "loss": 0.3627, "lr": 4.6700215648343336e-05, "epoch": 2.488859764089122, "percentage": 24.89, "elapsed_time": "0:15:56", "remaining_time": "0:48:07", "throughput": 2667.42, "total_tokens": 2551992} {"current_steps": 9500, "total_steps": 38150, "loss": 0.3466, "lr": 4.669453420529682e-05, "epoch": 2.490170380078637, "percentage": 24.9, "elapsed_time": "0:15:57", "remaining_time": "0:48:06", "throughput": 2667.83, "total_tokens": 2553736} {"current_steps": 9505, "total_steps": 38150, "loss": 0.503, "lr": 4.668884822162177e-05, "epoch": 2.491480996068152, "percentage": 24.91, "elapsed_time": "0:15:57", "remaining_time": "0:48:06", "throughput": 2667.94, "total_tokens": 2554968} {"current_steps": 9510, "total_steps": 38150, "loss": 0.3246, "lr": 4.668315769850827e-05, "epoch": 2.492791612057667, "percentage": 24.93, "elapsed_time": "0:15:58", "remaining_time": "0:48:05", "throughput": 2667.96, "total_tokens": 2556120} {"current_steps": 9515, "total_steps": 38150, "loss": 0.4275, "lr": 4.667746263714733e-05, "epoch": 2.4941022280471823, "percentage": 24.94, "elapsed_time": "0:15:58", "remaining_time": "0:48:04", "throughput": 2668.16, "total_tokens": 2557560} {"current_steps": 9520, "total_steps": 38150, "loss": 0.4757, "lr": 4.667176303873091e-05, "epoch": 2.4954128440366974, "percentage": 24.95, "elapsed_time": "0:15:59", "remaining_time": "0:48:04", "throughput": 2668.28, "total_tokens": 2558888} {"current_steps": 9525, "total_steps": 38150, "loss": 0.3123, "lr": 4.666605890445193e-05, "epoch": 2.4967234600262125, "percentage": 24.97, "elapsed_time": "0:15:59", "remaining_time": "0:48:03", "throughput": 2668.29, "total_tokens": 2560024} {"current_steps": 9530, "total_steps": 38150, "loss": 0.4953, "lr": 4.6660350235504265e-05, "epoch": 2.4980340760157276, "percentage": 24.98, "elapsed_time": "0:15:59", "remaining_time": "0:48:02", "throughput": 2668.3, "total_tokens": 2561192} {"current_steps": 9535, "total_steps": 38150, "loss": 0.4147, "lr": 4.6654637033082715e-05, "epoch": 2.4993446920052422, "percentage": 24.99, "elapsed_time": "0:16:00", "remaining_time": "0:48:01", "throughput": 2668.58, "total_tokens": 2562648} {"current_steps": 9540, "total_steps": 38150, "loss": 0.6815, "lr": 4.6648919298383055e-05, "epoch": 2.5006553079947578, "percentage": 25.01, "elapsed_time": "0:16:00", "remaining_time": "0:48:01", "throughput": 2668.44, "total_tokens": 2563624} {"current_steps": 9540, "total_steps": 38150, "eval_loss": 0.5050681829452515, "epoch": 2.5006553079947578, "percentage": 25.01, "elapsed_time": "0:16:17", "remaining_time": "0:48:51", "throughput": 2622.41, "total_tokens": 2563624} {"current_steps": 9545, "total_steps": 38150, "loss": 0.5692, "lr": 4.664319703260199e-05, "epoch": 2.5019659239842724, "percentage": 25.02, "elapsed_time": "0:16:19", "remaining_time": "0:48:55", "throughput": 2619.19, "total_tokens": 2565160} {"current_steps": 9550, "total_steps": 38150, "loss": 0.5569, "lr": 4.6637470236937186e-05, "epoch": 2.5032765399737875, "percentage": 25.03, "elapsed_time": "0:16:19", "remaining_time": "0:48:54", "throughput": 2619.14, "total_tokens": 2566232} {"current_steps": 9555, "total_steps": 38150, "loss": 0.2908, "lr": 4.663173891258724e-05, "epoch": 2.5045871559633026, "percentage": 25.05, "elapsed_time": "0:16:20", "remaining_time": "0:48:53", "throughput": 2619.18, "total_tokens": 2567400} {"current_steps": 9560, "total_steps": 38150, "loss": 0.2949, "lr": 4.662600306075172e-05, "epoch": 2.5058977719528177, "percentage": 25.06, "elapsed_time": "0:16:20", "remaining_time": "0:48:52", "throughput": 2619.46, "total_tokens": 2568840} {"current_steps": 9565, "total_steps": 38150, "loss": 0.6695, "lr": 4.662026268263113e-05, "epoch": 2.507208387942333, "percentage": 25.07, "elapsed_time": "0:16:21", "remaining_time": "0:48:52", "throughput": 2619.63, "total_tokens": 2570392} {"current_steps": 9570, "total_steps": 38150, "loss": 0.5657, "lr": 4.6614517779426917e-05, "epoch": 2.508519003931848, "percentage": 25.09, "elapsed_time": "0:16:21", "remaining_time": "0:48:51", "throughput": 2619.97, "total_tokens": 2572072} {"current_steps": 9575, "total_steps": 38150, "loss": 0.6318, "lr": 4.660876835234148e-05, "epoch": 2.509829619921363, "percentage": 25.1, "elapsed_time": "0:16:22", "remaining_time": "0:48:51", "throughput": 2619.88, "total_tokens": 2573096} {"current_steps": 9580, "total_steps": 38150, "loss": 0.5966, "lr": 4.660301440257816e-05, "epoch": 2.511140235910878, "percentage": 25.11, "elapsed_time": "0:16:22", "remaining_time": "0:48:50", "throughput": 2620.06, "total_tokens": 2574424} {"current_steps": 9585, "total_steps": 38150, "loss": 0.3285, "lr": 4.659725593134125e-05, "epoch": 2.512450851900393, "percentage": 25.12, "elapsed_time": "0:16:23", "remaining_time": "0:48:49", "throughput": 2620.16, "total_tokens": 2575688} {"current_steps": 9590, "total_steps": 38150, "loss": 0.5266, "lr": 4.6591492939836e-05, "epoch": 2.5137614678899083, "percentage": 25.14, "elapsed_time": "0:16:23", "remaining_time": "0:48:49", "throughput": 2620.4, "total_tokens": 2577240} {"current_steps": 9595, "total_steps": 38150, "loss": 0.5294, "lr": 4.6585725429268585e-05, "epoch": 2.5150720838794234, "percentage": 25.15, "elapsed_time": "0:16:24", "remaining_time": "0:48:48", "throughput": 2620.67, "total_tokens": 2578760} {"current_steps": 9600, "total_steps": 38150, "loss": 0.4552, "lr": 4.657995340084613e-05, "epoch": 2.5163826998689385, "percentage": 25.16, "elapsed_time": "0:16:24", "remaining_time": "0:48:47", "throughput": 2621.02, "total_tokens": 2580328} {"current_steps": 9605, "total_steps": 38150, "loss": 0.5462, "lr": 4.657417685577671e-05, "epoch": 2.5176933158584536, "percentage": 25.18, "elapsed_time": "0:16:24", "remaining_time": "0:48:47", "throughput": 2620.96, "total_tokens": 2581400} {"current_steps": 9610, "total_steps": 38150, "loss": 0.4296, "lr": 4.656839579526936e-05, "epoch": 2.5190039318479687, "percentage": 25.19, "elapsed_time": "0:16:25", "remaining_time": "0:48:46", "throughput": 2621.02, "total_tokens": 2582568} {"current_steps": 9615, "total_steps": 38150, "loss": 0.4198, "lr": 4.6562610220534035e-05, "epoch": 2.5203145478374838, "percentage": 25.2, "elapsed_time": "0:16:25", "remaining_time": "0:48:45", "throughput": 2621.13, "total_tokens": 2583816} {"current_steps": 9620, "total_steps": 38150, "loss": 0.359, "lr": 4.6556820132781646e-05, "epoch": 2.5216251638269984, "percentage": 25.22, "elapsed_time": "0:16:26", "remaining_time": "0:48:44", "throughput": 2621.31, "total_tokens": 2585128} {"current_steps": 9625, "total_steps": 38150, "loss": 0.3314, "lr": 4.6551025533224056e-05, "epoch": 2.522935779816514, "percentage": 25.23, "elapsed_time": "0:16:26", "remaining_time": "0:48:43", "throughput": 2621.22, "total_tokens": 2586120} {"current_steps": 9630, "total_steps": 38150, "loss": 0.4678, "lr": 4.654522642307405e-05, "epoch": 2.5242463958060286, "percentage": 25.24, "elapsed_time": "0:16:27", "remaining_time": "0:48:43", "throughput": 2621.3, "total_tokens": 2587352} {"current_steps": 9635, "total_steps": 38150, "loss": 0.4005, "lr": 4.653942280354539e-05, "epoch": 2.525557011795544, "percentage": 25.26, "elapsed_time": "0:16:27", "remaining_time": "0:48:42", "throughput": 2621.54, "total_tokens": 2588840} {"current_steps": 9640, "total_steps": 38150, "loss": 0.3503, "lr": 4.6533614675852755e-05, "epoch": 2.526867627785059, "percentage": 25.27, "elapsed_time": "0:16:28", "remaining_time": "0:48:42", "throughput": 2621.66, "total_tokens": 2590232} {"current_steps": 9645, "total_steps": 38150, "loss": 0.5377, "lr": 4.652780204121177e-05, "epoch": 2.528178243774574, "percentage": 25.28, "elapsed_time": "0:16:28", "remaining_time": "0:48:41", "throughput": 2621.7, "total_tokens": 2591400} {"current_steps": 9650, "total_steps": 38150, "loss": 0.374, "lr": 4.652198490083901e-05, "epoch": 2.529488859764089, "percentage": 25.29, "elapsed_time": "0:16:28", "remaining_time": "0:48:40", "throughput": 2621.67, "total_tokens": 2592488} {"current_steps": 9655, "total_steps": 38150, "loss": 0.3477, "lr": 4.6516163255952004e-05, "epoch": 2.530799475753604, "percentage": 25.31, "elapsed_time": "0:16:29", "remaining_time": "0:48:39", "throughput": 2621.62, "total_tokens": 2593544} {"current_steps": 9660, "total_steps": 38150, "loss": 0.3644, "lr": 4.651033710776921e-05, "epoch": 2.532110091743119, "percentage": 25.32, "elapsed_time": "0:16:29", "remaining_time": "0:48:38", "throughput": 2621.64, "total_tokens": 2594696} {"current_steps": 9665, "total_steps": 38150, "loss": 0.5314, "lr": 4.6504506457510025e-05, "epoch": 2.5334207077326343, "percentage": 25.33, "elapsed_time": "0:16:30", "remaining_time": "0:48:38", "throughput": 2621.68, "total_tokens": 2595864} {"current_steps": 9670, "total_steps": 38150, "loss": 0.6784, "lr": 4.649867130639479e-05, "epoch": 2.5347313237221494, "percentage": 25.35, "elapsed_time": "0:16:30", "remaining_time": "0:48:37", "throughput": 2621.76, "total_tokens": 2597080} {"current_steps": 9675, "total_steps": 38150, "loss": 0.3739, "lr": 4.64928316556448e-05, "epoch": 2.5360419397116645, "percentage": 25.36, "elapsed_time": "0:16:31", "remaining_time": "0:48:36", "throughput": 2621.75, "total_tokens": 2598200} {"current_steps": 9680, "total_steps": 38150, "loss": 0.4584, "lr": 4.648698750648228e-05, "epoch": 2.5373525557011796, "percentage": 25.37, "elapsed_time": "0:16:31", "remaining_time": "0:48:36", "throughput": 2621.87, "total_tokens": 2599512} {"current_steps": 9685, "total_steps": 38150, "loss": 0.4413, "lr": 4.64811388601304e-05, "epoch": 2.5386631716906947, "percentage": 25.39, "elapsed_time": "0:16:31", "remaining_time": "0:48:35", "throughput": 2622.07, "total_tokens": 2600984} {"current_steps": 9690, "total_steps": 38150, "loss": 0.4793, "lr": 4.647528571781328e-05, "epoch": 2.5399737876802098, "percentage": 25.4, "elapsed_time": "0:16:32", "remaining_time": "0:48:34", "throughput": 2622.0, "total_tokens": 2602024} {"current_steps": 9695, "total_steps": 38150, "loss": 0.6566, "lr": 4.646942808075596e-05, "epoch": 2.541284403669725, "percentage": 25.41, "elapsed_time": "0:16:32", "remaining_time": "0:48:34", "throughput": 2622.42, "total_tokens": 2603848} {"current_steps": 9700, "total_steps": 38150, "loss": 0.3064, "lr": 4.646356595018444e-05, "epoch": 2.54259501965924, "percentage": 25.43, "elapsed_time": "0:16:33", "remaining_time": "0:48:33", "throughput": 2622.67, "total_tokens": 2605384} {"current_steps": 9705, "total_steps": 38150, "loss": 0.5232, "lr": 4.6457699327325655e-05, "epoch": 2.543905635648755, "percentage": 25.44, "elapsed_time": "0:16:33", "remaining_time": "0:48:32", "throughput": 2622.75, "total_tokens": 2606600} {"current_steps": 9710, "total_steps": 38150, "loss": 0.4464, "lr": 4.645182821340747e-05, "epoch": 2.54521625163827, "percentage": 25.45, "elapsed_time": "0:16:34", "remaining_time": "0:48:32", "throughput": 2623.04, "total_tokens": 2608072} {"current_steps": 9715, "total_steps": 38150, "loss": 0.344, "lr": 4.644595260965872e-05, "epoch": 2.546526867627785, "percentage": 25.47, "elapsed_time": "0:16:34", "remaining_time": "0:48:31", "throughput": 2623.23, "total_tokens": 2609400} {"current_steps": 9720, "total_steps": 38150, "loss": 0.5349, "lr": 4.644007251730913e-05, "epoch": 2.5478374836173003, "percentage": 25.48, "elapsed_time": "0:16:35", "remaining_time": "0:48:30", "throughput": 2623.34, "total_tokens": 2610648} {"current_steps": 9725, "total_steps": 38150, "loss": 0.4658, "lr": 4.643418793758941e-05, "epoch": 2.549148099606815, "percentage": 25.49, "elapsed_time": "0:16:35", "remaining_time": "0:48:30", "throughput": 2623.72, "total_tokens": 2612392} {"current_steps": 9730, "total_steps": 38150, "loss": 0.4238, "lr": 4.642829887173119e-05, "epoch": 2.5504587155963305, "percentage": 25.5, "elapsed_time": "0:16:36", "remaining_time": "0:48:29", "throughput": 2624.14, "total_tokens": 2614088} {"current_steps": 9735, "total_steps": 38150, "loss": 0.3854, "lr": 4.642240532096705e-05, "epoch": 2.551769331585845, "percentage": 25.52, "elapsed_time": "0:16:36", "remaining_time": "0:48:28", "throughput": 2624.2, "total_tokens": 2615256} {"current_steps": 9740, "total_steps": 38150, "loss": 0.5256, "lr": 4.641650728653049e-05, "epoch": 2.5530799475753603, "percentage": 25.53, "elapsed_time": "0:16:37", "remaining_time": "0:48:28", "throughput": 2624.31, "total_tokens": 2616568} {"current_steps": 9745, "total_steps": 38150, "loss": 0.2882, "lr": 4.641060476965595e-05, "epoch": 2.5543905635648754, "percentage": 25.54, "elapsed_time": "0:16:37", "remaining_time": "0:48:27", "throughput": 2624.43, "total_tokens": 2617896} {"current_steps": 9750, "total_steps": 38150, "loss": 0.4395, "lr": 4.640469777157883e-05, "epoch": 2.5557011795543905, "percentage": 25.56, "elapsed_time": "0:16:37", "remaining_time": "0:48:26", "throughput": 2624.39, "total_tokens": 2618968} {"current_steps": 9755, "total_steps": 38150, "loss": 0.6892, "lr": 4.6398786293535455e-05, "epoch": 2.5570117955439056, "percentage": 25.57, "elapsed_time": "0:16:38", "remaining_time": "0:48:26", "throughput": 2624.27, "total_tokens": 2619928} {"current_steps": 9760, "total_steps": 38150, "loss": 0.4248, "lr": 4.639287033676308e-05, "epoch": 2.5583224115334207, "percentage": 25.58, "elapsed_time": "0:16:38", "remaining_time": "0:48:25", "throughput": 2624.27, "total_tokens": 2621048} {"current_steps": 9765, "total_steps": 38150, "loss": 0.4194, "lr": 4.638694990249991e-05, "epoch": 2.5596330275229358, "percentage": 25.6, "elapsed_time": "0:16:39", "remaining_time": "0:48:24", "throughput": 2624.26, "total_tokens": 2622152} {"current_steps": 9770, "total_steps": 38150, "loss": 0.439, "lr": 4.638102499198508e-05, "epoch": 2.560943643512451, "percentage": 25.61, "elapsed_time": "0:16:39", "remaining_time": "0:48:24", "throughput": 2624.82, "total_tokens": 2624104} {"current_steps": 9775, "total_steps": 38150, "loss": 0.4915, "lr": 4.637509560645865e-05, "epoch": 2.562254259501966, "percentage": 25.62, "elapsed_time": "0:16:40", "remaining_time": "0:48:23", "throughput": 2624.99, "total_tokens": 2625416} {"current_steps": 9780, "total_steps": 38150, "loss": 0.7944, "lr": 4.636916174716166e-05, "epoch": 2.563564875491481, "percentage": 25.64, "elapsed_time": "0:16:40", "remaining_time": "0:48:22", "throughput": 2625.01, "total_tokens": 2626600} {"current_steps": 9785, "total_steps": 38150, "loss": 0.5528, "lr": 4.636322341533603e-05, "epoch": 2.564875491480996, "percentage": 25.65, "elapsed_time": "0:16:41", "remaining_time": "0:48:21", "throughput": 2625.14, "total_tokens": 2627864} {"current_steps": 9790, "total_steps": 38150, "loss": 0.7865, "lr": 4.6357280612224656e-05, "epoch": 2.5661861074705112, "percentage": 25.66, "elapsed_time": "0:16:41", "remaining_time": "0:48:21", "throughput": 2625.12, "total_tokens": 2628984} {"current_steps": 9795, "total_steps": 38150, "loss": 0.4205, "lr": 4.635133333907135e-05, "epoch": 2.5674967234600263, "percentage": 25.67, "elapsed_time": "0:16:41", "remaining_time": "0:48:20", "throughput": 2625.3, "total_tokens": 2630376} {"current_steps": 9800, "total_steps": 38150, "loss": 0.2772, "lr": 4.634538159712088e-05, "epoch": 2.5688073394495414, "percentage": 25.69, "elapsed_time": "0:16:42", "remaining_time": "0:48:19", "throughput": 2625.26, "total_tokens": 2631448} {"current_steps": 9805, "total_steps": 38150, "loss": 0.329, "lr": 4.6339425387618906e-05, "epoch": 2.5701179554390565, "percentage": 25.7, "elapsed_time": "0:16:42", "remaining_time": "0:48:18", "throughput": 2625.34, "total_tokens": 2632664} {"current_steps": 9810, "total_steps": 38150, "loss": 0.4213, "lr": 4.633346471181207e-05, "epoch": 2.571428571428571, "percentage": 25.71, "elapsed_time": "0:16:43", "remaining_time": "0:48:18", "throughput": 2625.39, "total_tokens": 2633896} {"current_steps": 9815, "total_steps": 38150, "loss": 0.4111, "lr": 4.632749957094794e-05, "epoch": 2.5727391874180867, "percentage": 25.73, "elapsed_time": "0:16:43", "remaining_time": "0:48:17", "throughput": 2625.63, "total_tokens": 2635416} {"current_steps": 9820, "total_steps": 38150, "loss": 0.4024, "lr": 4.6321529966275e-05, "epoch": 2.5740498034076014, "percentage": 25.74, "elapsed_time": "0:16:44", "remaining_time": "0:48:16", "throughput": 2625.72, "total_tokens": 2636632} {"current_steps": 9825, "total_steps": 38150, "loss": 0.6242, "lr": 4.6315555899042686e-05, "epoch": 2.575360419397117, "percentage": 25.75, "elapsed_time": "0:16:44", "remaining_time": "0:48:16", "throughput": 2625.67, "total_tokens": 2637672} {"current_steps": 9830, "total_steps": 38150, "loss": 0.5375, "lr": 4.630957737050134e-05, "epoch": 2.5766710353866316, "percentage": 25.77, "elapsed_time": "0:16:45", "remaining_time": "0:48:15", "throughput": 2625.85, "total_tokens": 2639064} {"current_steps": 9835, "total_steps": 38150, "loss": 0.4342, "lr": 4.630359438190227e-05, "epoch": 2.5779816513761467, "percentage": 25.78, "elapsed_time": "0:16:45", "remaining_time": "0:48:14", "throughput": 2625.86, "total_tokens": 2640184} {"current_steps": 9840, "total_steps": 38150, "loss": 0.4967, "lr": 4.629760693449772e-05, "epoch": 2.5792922673656618, "percentage": 25.79, "elapsed_time": "0:16:45", "remaining_time": "0:48:13", "throughput": 2625.94, "total_tokens": 2641400} {"current_steps": 9845, "total_steps": 38150, "loss": 0.4355, "lr": 4.6291615029540826e-05, "epoch": 2.580602883355177, "percentage": 25.81, "elapsed_time": "0:16:46", "remaining_time": "0:48:13", "throughput": 2626.14, "total_tokens": 2642792} {"current_steps": 9850, "total_steps": 38150, "loss": 0.4068, "lr": 4.62856186682857e-05, "epoch": 2.581913499344692, "percentage": 25.82, "elapsed_time": "0:16:46", "remaining_time": "0:48:12", "throughput": 2626.21, "total_tokens": 2643992} {"current_steps": 9855, "total_steps": 38150, "loss": 0.4328, "lr": 4.627961785198736e-05, "epoch": 2.583224115334207, "percentage": 25.83, "elapsed_time": "0:16:47", "remaining_time": "0:48:11", "throughput": 2625.95, "total_tokens": 2644808} {"current_steps": 9860, "total_steps": 38150, "loss": 0.4022, "lr": 4.627361258190178e-05, "epoch": 2.584534731323722, "percentage": 25.85, "elapsed_time": "0:16:47", "remaining_time": "0:48:11", "throughput": 2626.11, "total_tokens": 2646168} {"current_steps": 9865, "total_steps": 38150, "loss": 0.4511, "lr": 4.626760285928584e-05, "epoch": 2.5858453473132372, "percentage": 25.86, "elapsed_time": "0:16:48", "remaining_time": "0:48:10", "throughput": 2626.25, "total_tokens": 2647512} {"current_steps": 9870, "total_steps": 38150, "loss": 0.2714, "lr": 4.626158868539737e-05, "epoch": 2.5871559633027523, "percentage": 25.87, "elapsed_time": "0:16:48", "remaining_time": "0:48:09", "throughput": 2626.2, "total_tokens": 2648584} {"current_steps": 9875, "total_steps": 38150, "loss": 0.4856, "lr": 4.625557006149512e-05, "epoch": 2.5884665792922674, "percentage": 25.88, "elapsed_time": "0:16:49", "remaining_time": "0:48:09", "throughput": 2626.48, "total_tokens": 2650120} {"current_steps": 9880, "total_steps": 38150, "loss": 0.581, "lr": 4.624954698883879e-05, "epoch": 2.5897771952817825, "percentage": 25.9, "elapsed_time": "0:16:49", "remaining_time": "0:48:08", "throughput": 2626.75, "total_tokens": 2651624} {"current_steps": 9885, "total_steps": 38150, "loss": 0.5313, "lr": 4.624351946868899e-05, "epoch": 2.5910878112712976, "percentage": 25.91, "elapsed_time": "0:16:49", "remaining_time": "0:48:07", "throughput": 2626.81, "total_tokens": 2652888} {"current_steps": 9890, "total_steps": 38150, "loss": 0.4677, "lr": 4.6237487502307265e-05, "epoch": 2.5923984272608127, "percentage": 25.92, "elapsed_time": "0:16:50", "remaining_time": "0:48:07", "throughput": 2626.87, "total_tokens": 2654184} {"current_steps": 9895, "total_steps": 38150, "loss": 0.3713, "lr": 4.623145109095611e-05, "epoch": 2.593709043250328, "percentage": 25.94, "elapsed_time": "0:16:50", "remaining_time": "0:48:06", "throughput": 2627.24, "total_tokens": 2655832} {"current_steps": 9900, "total_steps": 38150, "loss": 0.6268, "lr": 4.622541023589893e-05, "epoch": 2.595019659239843, "percentage": 25.95, "elapsed_time": "0:16:51", "remaining_time": "0:48:05", "throughput": 2627.48, "total_tokens": 2657288} {"current_steps": 9905, "total_steps": 38150, "loss": 0.6626, "lr": 4.621936493840005e-05, "epoch": 2.5963302752293576, "percentage": 25.96, "elapsed_time": "0:16:51", "remaining_time": "0:48:05", "throughput": 2627.72, "total_tokens": 2658760} {"current_steps": 9910, "total_steps": 38150, "loss": 0.7849, "lr": 4.621331519972476e-05, "epoch": 2.597640891218873, "percentage": 25.98, "elapsed_time": "0:16:52", "remaining_time": "0:48:04", "throughput": 2627.77, "total_tokens": 2659928} {"current_steps": 9915, "total_steps": 38150, "loss": 0.3692, "lr": 4.6207261021139246e-05, "epoch": 2.5989515072083877, "percentage": 25.99, "elapsed_time": "0:16:52", "remaining_time": "0:48:03", "throughput": 2627.86, "total_tokens": 2661160} {"current_steps": 9920, "total_steps": 38150, "loss": 0.4008, "lr": 4.620120240391065e-05, "epoch": 2.6002621231979033, "percentage": 26.0, "elapsed_time": "0:16:53", "remaining_time": "0:48:03", "throughput": 2627.9, "total_tokens": 2662328} {"current_steps": 9925, "total_steps": 38150, "loss": 0.3099, "lr": 4.6195139349307024e-05, "epoch": 2.601572739187418, "percentage": 26.02, "elapsed_time": "0:16:53", "remaining_time": "0:48:02", "throughput": 2627.99, "total_tokens": 2663672} {"current_steps": 9930, "total_steps": 38150, "loss": 0.4407, "lr": 4.6189071858597355e-05, "epoch": 2.602883355176933, "percentage": 26.03, "elapsed_time": "0:16:54", "remaining_time": "0:48:01", "throughput": 2628.14, "total_tokens": 2665000} {"current_steps": 9935, "total_steps": 38150, "loss": 0.3869, "lr": 4.6182999933051554e-05, "epoch": 2.604193971166448, "percentage": 26.04, "elapsed_time": "0:16:54", "remaining_time": "0:48:01", "throughput": 2628.42, "total_tokens": 2666632} {"current_steps": 9940, "total_steps": 38150, "loss": 0.3716, "lr": 4.617692357394047e-05, "epoch": 2.6055045871559632, "percentage": 26.06, "elapsed_time": "0:16:55", "remaining_time": "0:48:00", "throughput": 2628.89, "total_tokens": 2668392} {"current_steps": 9945, "total_steps": 38150, "loss": 0.3868, "lr": 4.617084278253587e-05, "epoch": 2.6068152031454783, "percentage": 26.07, "elapsed_time": "0:16:55", "remaining_time": "0:48:00", "throughput": 2629.01, "total_tokens": 2669736} {"current_steps": 9950, "total_steps": 38150, "loss": 0.508, "lr": 4.616475756011046e-05, "epoch": 2.6081258191349934, "percentage": 26.08, "elapsed_time": "0:16:55", "remaining_time": "0:47:59", "throughput": 2629.21, "total_tokens": 2671112} {"current_steps": 9955, "total_steps": 38150, "loss": 0.4306, "lr": 4.615866790793786e-05, "epoch": 2.6094364351245085, "percentage": 26.09, "elapsed_time": "0:16:56", "remaining_time": "0:47:58", "throughput": 2629.67, "total_tokens": 2672856} {"current_steps": 9960, "total_steps": 38150, "loss": 0.5392, "lr": 4.6152573827292636e-05, "epoch": 2.6107470511140236, "percentage": 26.11, "elapsed_time": "0:16:56", "remaining_time": "0:47:57", "throughput": 2629.71, "total_tokens": 2674008} {"current_steps": 9965, "total_steps": 38150, "loss": 0.7406, "lr": 4.6146475319450244e-05, "epoch": 2.6120576671035387, "percentage": 26.12, "elapsed_time": "0:16:57", "remaining_time": "0:47:57", "throughput": 2629.73, "total_tokens": 2675176} {"current_steps": 9970, "total_steps": 38150, "loss": 0.4467, "lr": 4.6140372385687114e-05, "epoch": 2.613368283093054, "percentage": 26.13, "elapsed_time": "0:16:57", "remaining_time": "0:47:56", "throughput": 2629.97, "total_tokens": 2676664} {"current_steps": 9975, "total_steps": 38150, "loss": 0.5381, "lr": 4.6134265027280574e-05, "epoch": 2.614678899082569, "percentage": 26.15, "elapsed_time": "0:16:58", "remaining_time": "0:47:56", "throughput": 2630.16, "total_tokens": 2678104} {"current_steps": 9980, "total_steps": 38150, "loss": 0.471, "lr": 4.6128153245508876e-05, "epoch": 2.615989515072084, "percentage": 26.16, "elapsed_time": "0:16:58", "remaining_time": "0:47:55", "throughput": 2630.08, "total_tokens": 2679112} {"current_steps": 9985, "total_steps": 38150, "loss": 0.3432, "lr": 4.612203704165121e-05, "epoch": 2.617300131061599, "percentage": 26.17, "elapsed_time": "0:16:59", "remaining_time": "0:47:54", "throughput": 2630.34, "total_tokens": 2680600} {"current_steps": 9990, "total_steps": 38150, "loss": 0.6246, "lr": 4.6115916416987686e-05, "epoch": 2.618610747051114, "percentage": 26.19, "elapsed_time": "0:16:59", "remaining_time": "0:47:53", "throughput": 2630.3, "total_tokens": 2681672} {"current_steps": 9995, "total_steps": 38150, "loss": 0.324, "lr": 4.610979137279935e-05, "epoch": 2.6199213630406293, "percentage": 26.2, "elapsed_time": "0:16:59", "remaining_time": "0:47:53", "throughput": 2630.29, "total_tokens": 2682792} {"current_steps": 10000, "total_steps": 38150, "loss": 0.4565, "lr": 4.6103661910368146e-05, "epoch": 2.621231979030144, "percentage": 26.21, "elapsed_time": "0:17:00", "remaining_time": "0:47:52", "throughput": 2630.39, "total_tokens": 2684088} {"current_steps": 10005, "total_steps": 38150, "loss": 0.2685, "lr": 4.6097528030976964e-05, "epoch": 2.6225425950196595, "percentage": 26.23, "elapsed_time": "0:17:00", "remaining_time": "0:47:51", "throughput": 2630.67, "total_tokens": 2685624} {"current_steps": 10010, "total_steps": 38150, "loss": 0.5173, "lr": 4.609138973590963e-05, "epoch": 2.623853211009174, "percentage": 26.24, "elapsed_time": "0:17:01", "remaining_time": "0:47:51", "throughput": 2630.72, "total_tokens": 2686808} {"current_steps": 10015, "total_steps": 38150, "loss": 0.4452, "lr": 4.6085247026450866e-05, "epoch": 2.625163826998689, "percentage": 26.25, "elapsed_time": "0:17:01", "remaining_time": "0:47:50", "throughput": 2630.76, "total_tokens": 2687976} {"current_steps": 10020, "total_steps": 38150, "loss": 0.506, "lr": 4.607909990388632e-05, "epoch": 2.6264744429882043, "percentage": 26.26, "elapsed_time": "0:17:02", "remaining_time": "0:47:49", "throughput": 2630.94, "total_tokens": 2689400} {"current_steps": 10025, "total_steps": 38150, "loss": 0.435, "lr": 4.607294836950261e-05, "epoch": 2.6277850589777194, "percentage": 26.28, "elapsed_time": "0:17:02", "remaining_time": "0:47:49", "throughput": 2631.0, "total_tokens": 2690664} {"current_steps": 10030, "total_steps": 38150, "loss": 0.4291, "lr": 4.606679242458719e-05, "epoch": 2.6290956749672345, "percentage": 26.29, "elapsed_time": "0:17:03", "remaining_time": "0:47:48", "throughput": 2631.07, "total_tokens": 2691848} {"current_steps": 10035, "total_steps": 38150, "loss": 0.3754, "lr": 4.606063207042853e-05, "epoch": 2.6304062909567496, "percentage": 26.3, "elapsed_time": "0:17:03", "remaining_time": "0:47:47", "throughput": 2631.12, "total_tokens": 2693128} {"current_steps": 10040, "total_steps": 38150, "loss": 0.4434, "lr": 4.6054467308315975e-05, "epoch": 2.6317169069462647, "percentage": 26.32, "elapsed_time": "0:17:04", "remaining_time": "0:47:46", "throughput": 2631.24, "total_tokens": 2694392} {"current_steps": 10045, "total_steps": 38150, "loss": 0.5752, "lr": 4.604829813953978e-05, "epoch": 2.63302752293578, "percentage": 26.33, "elapsed_time": "0:17:04", "remaining_time": "0:47:46", "throughput": 2631.29, "total_tokens": 2695560} {"current_steps": 10050, "total_steps": 38150, "loss": 0.4206, "lr": 4.6042124565391155e-05, "epoch": 2.634338138925295, "percentage": 26.34, "elapsed_time": "0:17:04", "remaining_time": "0:47:45", "throughput": 2631.43, "total_tokens": 2696872} {"current_steps": 10055, "total_steps": 38150, "loss": 0.8657, "lr": 4.603594658716221e-05, "epoch": 2.63564875491481, "percentage": 26.36, "elapsed_time": "0:17:05", "remaining_time": "0:47:44", "throughput": 2631.52, "total_tokens": 2698104} {"current_steps": 10060, "total_steps": 38150, "loss": 0.2645, "lr": 4.6029764206146006e-05, "epoch": 2.636959370904325, "percentage": 26.37, "elapsed_time": "0:17:05", "remaining_time": "0:47:44", "throughput": 2631.88, "total_tokens": 2699800} {"current_steps": 10065, "total_steps": 38150, "loss": 0.2466, "lr": 4.602357742363649e-05, "epoch": 2.63826998689384, "percentage": 26.38, "elapsed_time": "0:17:06", "remaining_time": "0:47:43", "throughput": 2632.19, "total_tokens": 2701400} {"current_steps": 10070, "total_steps": 38150, "loss": 0.4039, "lr": 4.601738624092853e-05, "epoch": 2.6395806028833553, "percentage": 26.4, "elapsed_time": "0:17:06", "remaining_time": "0:47:43", "throughput": 2632.31, "total_tokens": 2702744} {"current_steps": 10075, "total_steps": 38150, "loss": 0.2803, "lr": 4.601119065931796e-05, "epoch": 2.6408912188728704, "percentage": 26.41, "elapsed_time": "0:17:07", "remaining_time": "0:47:42", "throughput": 2632.61, "total_tokens": 2704296} {"current_steps": 10080, "total_steps": 38150, "loss": 0.484, "lr": 4.600499068010148e-05, "epoch": 2.6422018348623855, "percentage": 26.42, "elapsed_time": "0:17:07", "remaining_time": "0:47:41", "throughput": 2632.95, "total_tokens": 2705992} {"current_steps": 10085, "total_steps": 38150, "loss": 0.4983, "lr": 4.599878630457674e-05, "epoch": 2.6435124508519, "percentage": 26.44, "elapsed_time": "0:17:08", "remaining_time": "0:47:41", "throughput": 2633.39, "total_tokens": 2707816} {"current_steps": 10090, "total_steps": 38150, "loss": 0.5145, "lr": 4.599257753404233e-05, "epoch": 2.6448230668414157, "percentage": 26.45, "elapsed_time": "0:17:08", "remaining_time": "0:47:40", "throughput": 2633.47, "total_tokens": 2709144} {"current_steps": 10095, "total_steps": 38150, "loss": 0.5396, "lr": 4.59863643697977e-05, "epoch": 2.6461336828309303, "percentage": 26.46, "elapsed_time": "0:17:09", "remaining_time": "0:47:40", "throughput": 2633.39, "total_tokens": 2710152} {"current_steps": 10100, "total_steps": 38150, "loss": 0.6607, "lr": 4.5980146813143264e-05, "epoch": 2.647444298820446, "percentage": 26.47, "elapsed_time": "0:17:09", "remaining_time": "0:47:39", "throughput": 2633.41, "total_tokens": 2711304} {"current_steps": 10105, "total_steps": 38150, "loss": 0.5502, "lr": 4.597392486538036e-05, "epoch": 2.6487549148099605, "percentage": 26.49, "elapsed_time": "0:17:09", "remaining_time": "0:47:38", "throughput": 2633.34, "total_tokens": 2712328} {"current_steps": 10110, "total_steps": 38150, "loss": 0.5064, "lr": 4.596769852781122e-05, "epoch": 2.6500655307994756, "percentage": 26.5, "elapsed_time": "0:17:10", "remaining_time": "0:47:38", "throughput": 2633.81, "total_tokens": 2714120} {"current_steps": 10115, "total_steps": 38150, "loss": 0.5362, "lr": 4.596146780173901e-05, "epoch": 2.6513761467889907, "percentage": 26.51, "elapsed_time": "0:17:10", "remaining_time": "0:47:37", "throughput": 2634.17, "total_tokens": 2715800} {"current_steps": 10120, "total_steps": 38150, "loss": 0.5368, "lr": 4.59552326884678e-05, "epoch": 2.652686762778506, "percentage": 26.53, "elapsed_time": "0:17:11", "remaining_time": "0:47:36", "throughput": 2634.24, "total_tokens": 2717016} {"current_steps": 10125, "total_steps": 38150, "loss": 0.6015, "lr": 4.5948993189302605e-05, "epoch": 2.653997378768021, "percentage": 26.54, "elapsed_time": "0:17:12", "remaining_time": "0:47:36", "throughput": 2634.71, "total_tokens": 2719176} {"current_steps": 10130, "total_steps": 38150, "loss": 0.3876, "lr": 4.5942749305549325e-05, "epoch": 2.655307994757536, "percentage": 26.55, "elapsed_time": "0:17:12", "remaining_time": "0:47:35", "throughput": 2634.8, "total_tokens": 2720456} {"current_steps": 10135, "total_steps": 38150, "loss": 0.3088, "lr": 4.593650103851481e-05, "epoch": 2.656618610747051, "percentage": 26.57, "elapsed_time": "0:17:12", "remaining_time": "0:47:35", "throughput": 2634.8, "total_tokens": 2721576} {"current_steps": 10140, "total_steps": 38150, "loss": 0.7981, "lr": 4.5930248389506794e-05, "epoch": 2.657929226736566, "percentage": 26.58, "elapsed_time": "0:17:13", "remaining_time": "0:47:34", "throughput": 2634.71, "total_tokens": 2722680} {"current_steps": 10145, "total_steps": 38150, "loss": 0.3838, "lr": 4.592399135983396e-05, "epoch": 2.6592398427260813, "percentage": 26.59, "elapsed_time": "0:17:13", "remaining_time": "0:47:33", "throughput": 2634.96, "total_tokens": 2724104} {"current_steps": 10150, "total_steps": 38150, "loss": 0.3664, "lr": 4.591772995080589e-05, "epoch": 2.6605504587155964, "percentage": 26.61, "elapsed_time": "0:17:14", "remaining_time": "0:47:33", "throughput": 2635.14, "total_tokens": 2725432} {"current_steps": 10155, "total_steps": 38150, "loss": 0.5431, "lr": 4.591146416373308e-05, "epoch": 2.6618610747051115, "percentage": 26.62, "elapsed_time": "0:17:14", "remaining_time": "0:47:32", "throughput": 2635.23, "total_tokens": 2726712} {"current_steps": 10160, "total_steps": 38150, "loss": 0.4842, "lr": 4.590519399992695e-05, "epoch": 2.6631716906946266, "percentage": 26.63, "elapsed_time": "0:17:15", "remaining_time": "0:47:31", "throughput": 2635.26, "total_tokens": 2727880} {"current_steps": 10165, "total_steps": 38150, "loss": 0.4633, "lr": 4.5898919460699845e-05, "epoch": 2.6644823066841417, "percentage": 26.64, "elapsed_time": "0:17:15", "remaining_time": "0:47:31", "throughput": 2635.35, "total_tokens": 2729096} {"current_steps": 10170, "total_steps": 38150, "loss": 0.4841, "lr": 4.589264054736501e-05, "epoch": 2.6657929226736568, "percentage": 26.66, "elapsed_time": "0:17:16", "remaining_time": "0:47:30", "throughput": 2635.37, "total_tokens": 2730264} {"current_steps": 10175, "total_steps": 38150, "loss": 0.3895, "lr": 4.58863572612366e-05, "epoch": 2.667103538663172, "percentage": 26.67, "elapsed_time": "0:17:16", "remaining_time": "0:47:29", "throughput": 2635.35, "total_tokens": 2731352} {"current_steps": 10180, "total_steps": 38150, "loss": 0.4891, "lr": 4.5880069603629705e-05, "epoch": 2.6684141546526865, "percentage": 26.68, "elapsed_time": "0:17:16", "remaining_time": "0:47:28", "throughput": 2635.36, "total_tokens": 2732552} {"current_steps": 10185, "total_steps": 38150, "loss": 0.516, "lr": 4.587377757586032e-05, "epoch": 2.669724770642202, "percentage": 26.7, "elapsed_time": "0:17:17", "remaining_time": "0:47:28", "throughput": 2635.7, "total_tokens": 2734232} {"current_steps": 10190, "total_steps": 38150, "loss": 0.4562, "lr": 4.586748117924536e-05, "epoch": 2.6710353866317167, "percentage": 26.71, "elapsed_time": "0:17:17", "remaining_time": "0:47:27", "throughput": 2635.8, "total_tokens": 2735480} {"current_steps": 10195, "total_steps": 38150, "loss": 0.5471, "lr": 4.586118041510264e-05, "epoch": 2.6723460026212322, "percentage": 26.72, "elapsed_time": "0:17:18", "remaining_time": "0:47:26", "throughput": 2635.99, "total_tokens": 2736824} {"current_steps": 10200, "total_steps": 38150, "loss": 0.3381, "lr": 4.585487528475091e-05, "epoch": 2.673656618610747, "percentage": 26.74, "elapsed_time": "0:17:18", "remaining_time": "0:47:26", "throughput": 2636.02, "total_tokens": 2737992} {"current_steps": 10205, "total_steps": 38150, "loss": 0.4401, "lr": 4.584856578950981e-05, "epoch": 2.674967234600262, "percentage": 26.75, "elapsed_time": "0:17:19", "remaining_time": "0:47:25", "throughput": 2636.14, "total_tokens": 2739272} {"current_steps": 10210, "total_steps": 38150, "loss": 0.4005, "lr": 4.584225193069992e-05, "epoch": 2.676277850589777, "percentage": 26.76, "elapsed_time": "0:17:19", "remaining_time": "0:47:24", "throughput": 2636.43, "total_tokens": 2740840} {"current_steps": 10215, "total_steps": 38150, "loss": 0.4715, "lr": 4.583593370964271e-05, "epoch": 2.677588466579292, "percentage": 26.78, "elapsed_time": "0:17:20", "remaining_time": "0:47:24", "throughput": 2636.91, "total_tokens": 2742632} {"current_steps": 10220, "total_steps": 38150, "loss": 0.4595, "lr": 4.582961112766058e-05, "epoch": 2.6788990825688073, "percentage": 26.79, "elapsed_time": "0:17:20", "remaining_time": "0:47:23", "throughput": 2636.99, "total_tokens": 2743944} {"current_steps": 10225, "total_steps": 38150, "loss": 0.4414, "lr": 4.582328418607682e-05, "epoch": 2.6802096985583224, "percentage": 26.8, "elapsed_time": "0:17:20", "remaining_time": "0:47:23", "throughput": 2636.97, "total_tokens": 2745064} {"current_steps": 10230, "total_steps": 38150, "loss": 0.5779, "lr": 4.581695288621568e-05, "epoch": 2.6815203145478375, "percentage": 26.82, "elapsed_time": "0:17:21", "remaining_time": "0:47:22", "throughput": 2637.02, "total_tokens": 2746312} {"current_steps": 10235, "total_steps": 38150, "loss": 0.4849, "lr": 4.581061722940225e-05, "epoch": 2.6828309305373526, "percentage": 26.83, "elapsed_time": "0:17:21", "remaining_time": "0:47:21", "throughput": 2637.21, "total_tokens": 2747672} {"current_steps": 10240, "total_steps": 38150, "loss": 0.5557, "lr": 4.580427721696261e-05, "epoch": 2.6841415465268676, "percentage": 26.84, "elapsed_time": "0:17:22", "remaining_time": "0:47:20", "throughput": 2637.1, "total_tokens": 2748680} {"current_steps": 10245, "total_steps": 38150, "loss": 0.3893, "lr": 4.579793285022368e-05, "epoch": 2.6854521625163827, "percentage": 26.85, "elapsed_time": "0:17:22", "remaining_time": "0:47:20", "throughput": 2637.16, "total_tokens": 2749944} {"current_steps": 10250, "total_steps": 38150, "loss": 0.4983, "lr": 4.579158413051335e-05, "epoch": 2.686762778505898, "percentage": 26.87, "elapsed_time": "0:17:23", "remaining_time": "0:47:19", "throughput": 2637.31, "total_tokens": 2751320} {"current_steps": 10255, "total_steps": 38150, "loss": 0.3491, "lr": 4.578523105916038e-05, "epoch": 2.688073394495413, "percentage": 26.88, "elapsed_time": "0:17:23", "remaining_time": "0:47:19", "throughput": 2637.69, "total_tokens": 2753064} {"current_steps": 10260, "total_steps": 38150, "loss": 0.6213, "lr": 4.577887363749447e-05, "epoch": 2.689384010484928, "percentage": 26.89, "elapsed_time": "0:17:24", "remaining_time": "0:47:18", "throughput": 2637.54, "total_tokens": 2754024} {"current_steps": 10265, "total_steps": 38150, "loss": 0.6495, "lr": 4.57725118668462e-05, "epoch": 2.690694626474443, "percentage": 26.91, "elapsed_time": "0:17:24", "remaining_time": "0:47:17", "throughput": 2638.01, "total_tokens": 2755800} {"current_steps": 10270, "total_steps": 38150, "loss": 0.3653, "lr": 4.5766145748547104e-05, "epoch": 2.6920052424639582, "percentage": 26.92, "elapsed_time": "0:17:25", "remaining_time": "0:47:17", "throughput": 2637.98, "total_tokens": 2756872} {"current_steps": 10275, "total_steps": 38150, "loss": 0.4177, "lr": 4.575977528392957e-05, "epoch": 2.693315858453473, "percentage": 26.93, "elapsed_time": "0:17:25", "remaining_time": "0:47:16", "throughput": 2638.27, "total_tokens": 2758440} {"current_steps": 10280, "total_steps": 38150, "loss": 0.3065, "lr": 4.5753400474326946e-05, "epoch": 2.6946264744429884, "percentage": 26.95, "elapsed_time": "0:17:26", "remaining_time": "0:47:15", "throughput": 2638.42, "total_tokens": 2759816} {"current_steps": 10285, "total_steps": 38150, "loss": 0.5045, "lr": 4.574702132107346e-05, "epoch": 2.695937090432503, "percentage": 26.96, "elapsed_time": "0:17:26", "remaining_time": "0:47:15", "throughput": 2638.75, "total_tokens": 2761400} {"current_steps": 10290, "total_steps": 38150, "loss": 0.4377, "lr": 4.5740637825504265e-05, "epoch": 2.6972477064220186, "percentage": 26.97, "elapsed_time": "0:17:26", "remaining_time": "0:47:14", "throughput": 2638.63, "total_tokens": 2762392} {"current_steps": 10295, "total_steps": 38150, "loss": 0.3996, "lr": 4.5734249988955405e-05, "epoch": 2.6985583224115333, "percentage": 26.99, "elapsed_time": "0:17:27", "remaining_time": "0:47:13", "throughput": 2638.85, "total_tokens": 2763864} {"current_steps": 10300, "total_steps": 38150, "loss": 0.4463, "lr": 4.572785781276385e-05, "epoch": 2.6998689384010484, "percentage": 27.0, "elapsed_time": "0:17:27", "remaining_time": "0:47:13", "throughput": 2638.73, "total_tokens": 2764856} {"current_steps": 10305, "total_steps": 38150, "loss": 0.5552, "lr": 4.5721461298267466e-05, "epoch": 2.7011795543905635, "percentage": 27.01, "elapsed_time": "0:17:28", "remaining_time": "0:47:12", "throughput": 2638.73, "total_tokens": 2765944} {"current_steps": 10310, "total_steps": 38150, "loss": 0.3079, "lr": 4.5715060446805044e-05, "epoch": 2.7024901703800785, "percentage": 27.02, "elapsed_time": "0:17:28", "remaining_time": "0:47:11", "throughput": 2638.57, "total_tokens": 2766888} {"current_steps": 10315, "total_steps": 38150, "loss": 0.3607, "lr": 4.570865525971626e-05, "epoch": 2.7038007863695936, "percentage": 27.04, "elapsed_time": "0:17:29", "remaining_time": "0:47:11", "throughput": 2638.74, "total_tokens": 2768328} {"current_steps": 10320, "total_steps": 38150, "loss": 0.3476, "lr": 4.570224573834171e-05, "epoch": 2.7051114023591087, "percentage": 27.05, "elapsed_time": "0:17:29", "remaining_time": "0:47:10", "throughput": 2638.59, "total_tokens": 2769256} {"current_steps": 10325, "total_steps": 38150, "loss": 0.4212, "lr": 4.569583188402289e-05, "epoch": 2.706422018348624, "percentage": 27.06, "elapsed_time": "0:17:29", "remaining_time": "0:47:09", "throughput": 2638.84, "total_tokens": 2770744} {"current_steps": 10330, "total_steps": 38150, "loss": 0.4677, "lr": 4.5689413698102226e-05, "epoch": 2.707732634338139, "percentage": 27.08, "elapsed_time": "0:17:30", "remaining_time": "0:47:08", "throughput": 2639.12, "total_tokens": 2772200} {"current_steps": 10335, "total_steps": 38150, "loss": 0.3446, "lr": 4.5682991181923024e-05, "epoch": 2.709043250327654, "percentage": 27.09, "elapsed_time": "0:17:30", "remaining_time": "0:47:08", "throughput": 2639.36, "total_tokens": 2773752} {"current_steps": 10340, "total_steps": 38150, "loss": 0.5616, "lr": 4.56765643368295e-05, "epoch": 2.710353866317169, "percentage": 27.1, "elapsed_time": "0:17:31", "remaining_time": "0:47:07", "throughput": 2639.35, "total_tokens": 2774952} {"current_steps": 10345, "total_steps": 38150, "loss": 0.3965, "lr": 4.5670133164166795e-05, "epoch": 2.711664482306684, "percentage": 27.12, "elapsed_time": "0:17:31", "remaining_time": "0:47:06", "throughput": 2639.36, "total_tokens": 2776072} {"current_steps": 10350, "total_steps": 38150, "loss": 0.3625, "lr": 4.566369766528093e-05, "epoch": 2.7129750982961993, "percentage": 27.13, "elapsed_time": "0:17:32", "remaining_time": "0:47:06", "throughput": 2639.58, "total_tokens": 2777560} {"current_steps": 10355, "total_steps": 38150, "loss": 0.581, "lr": 4.565725784151884e-05, "epoch": 2.7142857142857144, "percentage": 27.14, "elapsed_time": "0:17:32", "remaining_time": "0:47:05", "throughput": 2639.37, "total_tokens": 2778456} {"current_steps": 10360, "total_steps": 38150, "loss": 0.4191, "lr": 4.565081369422839e-05, "epoch": 2.7155963302752295, "percentage": 27.16, "elapsed_time": "0:17:33", "remaining_time": "0:47:04", "throughput": 2639.43, "total_tokens": 2779672} {"current_steps": 10365, "total_steps": 38150, "loss": 0.3994, "lr": 4.56443652247583e-05, "epoch": 2.7169069462647446, "percentage": 27.17, "elapsed_time": "0:17:33", "remaining_time": "0:47:04", "throughput": 2639.47, "total_tokens": 2780824} {"current_steps": 10370, "total_steps": 38150, "loss": 0.944, "lr": 4.5637912434458254e-05, "epoch": 2.7182175622542593, "percentage": 27.18, "elapsed_time": "0:17:34", "remaining_time": "0:47:03", "throughput": 2639.42, "total_tokens": 2781960} {"current_steps": 10375, "total_steps": 38150, "loss": 0.4834, "lr": 4.563145532467878e-05, "epoch": 2.719528178243775, "percentage": 27.2, "elapsed_time": "0:17:34", "remaining_time": "0:47:02", "throughput": 2639.41, "total_tokens": 2783064} {"current_steps": 10380, "total_steps": 38150, "loss": 0.612, "lr": 4.562499389677137e-05, "epoch": 2.7208387942332894, "percentage": 27.21, "elapsed_time": "0:17:34", "remaining_time": "0:47:02", "throughput": 2639.5, "total_tokens": 2784280} {"current_steps": 10385, "total_steps": 38150, "loss": 0.7265, "lr": 4.561852815208837e-05, "epoch": 2.722149410222805, "percentage": 27.22, "elapsed_time": "0:17:35", "remaining_time": "0:47:01", "throughput": 2639.71, "total_tokens": 2785736} {"current_steps": 10390, "total_steps": 38150, "loss": 0.4172, "lr": 4.561205809198305e-05, "epoch": 2.7234600262123196, "percentage": 27.23, "elapsed_time": "0:17:35", "remaining_time": "0:47:00", "throughput": 2639.87, "total_tokens": 2787064} {"current_steps": 10395, "total_steps": 38150, "loss": 0.482, "lr": 4.560558371780959e-05, "epoch": 2.7247706422018347, "percentage": 27.25, "elapsed_time": "0:17:36", "remaining_time": "0:47:00", "throughput": 2639.81, "total_tokens": 2788120} {"current_steps": 10400, "total_steps": 38150, "loss": 0.4257, "lr": 4.559910503092306e-05, "epoch": 2.72608125819135, "percentage": 27.26, "elapsed_time": "0:17:36", "remaining_time": "0:46:59", "throughput": 2639.83, "total_tokens": 2789288} {"current_steps": 10405, "total_steps": 38150, "loss": 0.5317, "lr": 4.559262203267945e-05, "epoch": 2.727391874180865, "percentage": 27.27, "elapsed_time": "0:17:37", "remaining_time": "0:46:58", "throughput": 2639.74, "total_tokens": 2790280} {"current_steps": 10410, "total_steps": 38150, "loss": 0.265, "lr": 4.5586134724435614e-05, "epoch": 2.72870249017038, "percentage": 27.29, "elapsed_time": "0:17:37", "remaining_time": "0:46:57", "throughput": 2639.68, "total_tokens": 2791320} {"current_steps": 10415, "total_steps": 38150, "loss": 0.4466, "lr": 4.557964310754935e-05, "epoch": 2.730013106159895, "percentage": 27.3, "elapsed_time": "0:17:37", "remaining_time": "0:46:57", "throughput": 2639.95, "total_tokens": 2792856} {"current_steps": 10420, "total_steps": 38150, "loss": 0.4862, "lr": 4.557314718337935e-05, "epoch": 2.73132372214941, "percentage": 27.31, "elapsed_time": "0:17:38", "remaining_time": "0:46:56", "throughput": 2640.12, "total_tokens": 2794200} {"current_steps": 10425, "total_steps": 38150, "loss": 0.3957, "lr": 4.556664695328519e-05, "epoch": 2.7326343381389253, "percentage": 27.33, "elapsed_time": "0:17:38", "remaining_time": "0:46:55", "throughput": 2640.0, "total_tokens": 2795192} {"current_steps": 10430, "total_steps": 38150, "loss": 0.3202, "lr": 4.556014241862736e-05, "epoch": 2.7339449541284404, "percentage": 27.34, "elapsed_time": "0:17:39", "remaining_time": "0:46:55", "throughput": 2639.99, "total_tokens": 2796296} {"current_steps": 10435, "total_steps": 38150, "loss": 0.3949, "lr": 4.555363358076725e-05, "epoch": 2.7352555701179555, "percentage": 27.35, "elapsed_time": "0:17:39", "remaining_time": "0:46:54", "throughput": 2640.01, "total_tokens": 2797512} {"current_steps": 10440, "total_steps": 38150, "loss": 0.5276, "lr": 4.5547120441067136e-05, "epoch": 2.7365661861074706, "percentage": 27.37, "elapsed_time": "0:17:40", "remaining_time": "0:46:53", "throughput": 2639.9, "total_tokens": 2798504} {"current_steps": 10445, "total_steps": 38150, "loss": 0.3932, "lr": 4.554060300089022e-05, "epoch": 2.7378768020969857, "percentage": 27.38, "elapsed_time": "0:17:40", "remaining_time": "0:46:53", "throughput": 2640.04, "total_tokens": 2799832} {"current_steps": 10450, "total_steps": 38150, "loss": 0.3827, "lr": 4.553408126160059e-05, "epoch": 2.739187418086501, "percentage": 27.39, "elapsed_time": "0:17:40", "remaining_time": "0:46:52", "throughput": 2640.13, "total_tokens": 2801048} {"current_steps": 10455, "total_steps": 38150, "loss": 0.4713, "lr": 4.552755522456324e-05, "epoch": 2.740498034076016, "percentage": 27.4, "elapsed_time": "0:17:41", "remaining_time": "0:46:51", "throughput": 2640.39, "total_tokens": 2802568} {"current_steps": 10460, "total_steps": 38150, "loss": 0.5176, "lr": 4.552102489114404e-05, "epoch": 2.741808650065531, "percentage": 27.42, "elapsed_time": "0:17:41", "remaining_time": "0:46:51", "throughput": 2640.71, "total_tokens": 2804184} {"current_steps": 10465, "total_steps": 38150, "loss": 0.3866, "lr": 4.551449026270979e-05, "epoch": 2.7431192660550456, "percentage": 27.43, "elapsed_time": "0:17:42", "remaining_time": "0:46:50", "throughput": 2640.81, "total_tokens": 2805512} {"current_steps": 10470, "total_steps": 38150, "loss": 0.5029, "lr": 4.550795134062817e-05, "epoch": 2.744429882044561, "percentage": 27.44, "elapsed_time": "0:17:42", "remaining_time": "0:46:49", "throughput": 2640.82, "total_tokens": 2806664} {"current_steps": 10475, "total_steps": 38150, "loss": 0.4511, "lr": 4.5501408126267784e-05, "epoch": 2.745740498034076, "percentage": 27.46, "elapsed_time": "0:17:43", "remaining_time": "0:46:49", "throughput": 2641.08, "total_tokens": 2808200} {"current_steps": 10480, "total_steps": 38150, "loss": 0.3884, "lr": 4.5494860620998086e-05, "epoch": 2.747051114023591, "percentage": 27.47, "elapsed_time": "0:17:43", "remaining_time": "0:46:48", "throughput": 2641.26, "total_tokens": 2809528} {"current_steps": 10485, "total_steps": 38150, "loss": 0.5136, "lr": 4.548830882618948e-05, "epoch": 2.748361730013106, "percentage": 27.48, "elapsed_time": "0:17:44", "remaining_time": "0:46:47", "throughput": 2641.48, "total_tokens": 2810984} {"current_steps": 10490, "total_steps": 38150, "loss": 0.3959, "lr": 4.5481752743213234e-05, "epoch": 2.749672346002621, "percentage": 27.5, "elapsed_time": "0:17:44", "remaining_time": "0:46:47", "throughput": 2641.78, "total_tokens": 2812600} {"current_steps": 10495, "total_steps": 38150, "loss": 0.4235, "lr": 4.5475192373441525e-05, "epoch": 2.750982961992136, "percentage": 27.51, "elapsed_time": "0:17:45", "remaining_time": "0:46:46", "throughput": 2642.18, "total_tokens": 2814568} {"current_steps": 10500, "total_steps": 38150, "loss": 0.6947, "lr": 4.5468627718247436e-05, "epoch": 2.7522935779816513, "percentage": 27.52, "elapsed_time": "0:17:45", "remaining_time": "0:46:46", "throughput": 2642.53, "total_tokens": 2816216} {"current_steps": 10505, "total_steps": 38150, "loss": 0.521, "lr": 4.546205877900494e-05, "epoch": 2.7536041939711664, "percentage": 27.54, "elapsed_time": "0:17:46", "remaining_time": "0:46:45", "throughput": 2642.7, "total_tokens": 2817560} {"current_steps": 10510, "total_steps": 38150, "loss": 0.5897, "lr": 4.5455485557088885e-05, "epoch": 2.7549148099606815, "percentage": 27.55, "elapsed_time": "0:17:46", "remaining_time": "0:46:45", "throughput": 2642.64, "total_tokens": 2818616} {"current_steps": 10515, "total_steps": 38150, "loss": 0.4069, "lr": 4.544890805387505e-05, "epoch": 2.7562254259501966, "percentage": 27.56, "elapsed_time": "0:17:47", "remaining_time": "0:46:44", "throughput": 2642.84, "total_tokens": 2819976} {"current_steps": 10520, "total_steps": 38150, "loss": 0.4999, "lr": 4.544232627074009e-05, "epoch": 2.7575360419397117, "percentage": 27.58, "elapsed_time": "0:17:47", "remaining_time": "0:46:43", "throughput": 2643.12, "total_tokens": 2821464} {"current_steps": 10525, "total_steps": 38150, "loss": 0.4374, "lr": 4.5435740209061574e-05, "epoch": 2.758846657929227, "percentage": 27.59, "elapsed_time": "0:17:47", "remaining_time": "0:46:42", "throughput": 2643.23, "total_tokens": 2822744} {"current_steps": 10530, "total_steps": 38150, "loss": 0.7152, "lr": 4.5429149870217936e-05, "epoch": 2.760157273918742, "percentage": 27.6, "elapsed_time": "0:17:48", "remaining_time": "0:46:42", "throughput": 2643.33, "total_tokens": 2823992} {"current_steps": 10535, "total_steps": 38150, "loss": 0.3585, "lr": 4.5422555255588524e-05, "epoch": 2.761467889908257, "percentage": 27.61, "elapsed_time": "0:17:48", "remaining_time": "0:46:41", "throughput": 2643.4, "total_tokens": 2825256} {"current_steps": 10540, "total_steps": 38150, "loss": 0.4345, "lr": 4.541595636655359e-05, "epoch": 2.762778505897772, "percentage": 27.63, "elapsed_time": "0:17:49", "remaining_time": "0:46:40", "throughput": 2643.31, "total_tokens": 2826312} {"current_steps": 10545, "total_steps": 38150, "loss": 0.3674, "lr": 4.540935320449426e-05, "epoch": 2.764089121887287, "percentage": 27.64, "elapsed_time": "0:17:49", "remaining_time": "0:46:40", "throughput": 2643.56, "total_tokens": 2827816} {"current_steps": 10550, "total_steps": 38150, "loss": 0.552, "lr": 4.540274577079258e-05, "epoch": 2.765399737876802, "percentage": 27.65, "elapsed_time": "0:17:50", "remaining_time": "0:46:39", "throughput": 2643.78, "total_tokens": 2829272} {"current_steps": 10555, "total_steps": 38150, "loss": 0.5816, "lr": 4.539613406683145e-05, "epoch": 2.7667103538663174, "percentage": 27.67, "elapsed_time": "0:17:50", "remaining_time": "0:46:39", "throughput": 2643.93, "total_tokens": 2830648} {"current_steps": 10560, "total_steps": 38150, "loss": 0.6404, "lr": 4.538951809399471e-05, "epoch": 2.768020969855832, "percentage": 27.68, "elapsed_time": "0:17:51", "remaining_time": "0:46:38", "throughput": 2644.12, "total_tokens": 2832088} {"current_steps": 10565, "total_steps": 38150, "loss": 0.3271, "lr": 4.538289785366706e-05, "epoch": 2.7693315858453476, "percentage": 27.69, "elapsed_time": "0:17:51", "remaining_time": "0:46:37", "throughput": 2644.41, "total_tokens": 2833720} {"current_steps": 10570, "total_steps": 38150, "loss": 0.5498, "lr": 4.53762733472341e-05, "epoch": 2.770642201834862, "percentage": 27.71, "elapsed_time": "0:17:52", "remaining_time": "0:46:37", "throughput": 2644.45, "total_tokens": 2834888} {"current_steps": 10575, "total_steps": 38150, "loss": 0.3686, "lr": 4.536964457608235e-05, "epoch": 2.7719528178243773, "percentage": 27.72, "elapsed_time": "0:17:52", "remaining_time": "0:46:36", "throughput": 2644.55, "total_tokens": 2836232} {"current_steps": 10580, "total_steps": 38150, "loss": 0.5454, "lr": 4.5363011541599185e-05, "epoch": 2.7732634338138924, "percentage": 27.73, "elapsed_time": "0:17:52", "remaining_time": "0:46:35", "throughput": 2644.77, "total_tokens": 2837720} {"current_steps": 10585, "total_steps": 38150, "loss": 0.589, "lr": 4.535637424517288e-05, "epoch": 2.7745740498034075, "percentage": 27.75, "elapsed_time": "0:17:53", "remaining_time": "0:46:35", "throughput": 2644.82, "total_tokens": 2839000} {"current_steps": 10590, "total_steps": 38150, "loss": 0.4453, "lr": 4.5349732688192624e-05, "epoch": 2.7758846657929226, "percentage": 27.76, "elapsed_time": "0:17:53", "remaining_time": "0:46:34", "throughput": 2644.94, "total_tokens": 2840360} {"current_steps": 10595, "total_steps": 38150, "loss": 0.4681, "lr": 4.534308687204848e-05, "epoch": 2.7771952817824377, "percentage": 27.77, "elapsed_time": "0:17:54", "remaining_time": "0:46:34", "throughput": 2644.96, "total_tokens": 2841576} {"current_steps": 10600, "total_steps": 38150, "loss": 0.5985, "lr": 4.53364367981314e-05, "epoch": 2.778505897771953, "percentage": 27.79, "elapsed_time": "0:17:54", "remaining_time": "0:46:33", "throughput": 2645.05, "total_tokens": 2842888} {"current_steps": 10605, "total_steps": 38150, "loss": 0.328, "lr": 4.5329782467833236e-05, "epoch": 2.779816513761468, "percentage": 27.8, "elapsed_time": "0:17:55", "remaining_time": "0:46:32", "throughput": 2645.0, "total_tokens": 2844040} {"current_steps": 10610, "total_steps": 38150, "loss": 0.4162, "lr": 4.532312388254674e-05, "epoch": 2.781127129750983, "percentage": 27.81, "elapsed_time": "0:17:55", "remaining_time": "0:46:32", "throughput": 2645.04, "total_tokens": 2845208} {"current_steps": 10615, "total_steps": 38150, "loss": 0.5642, "lr": 4.5316461043665516e-05, "epoch": 2.782437745740498, "percentage": 27.82, "elapsed_time": "0:17:56", "remaining_time": "0:46:31", "throughput": 2645.29, "total_tokens": 2846792} {"current_steps": 10620, "total_steps": 38150, "loss": 0.3334, "lr": 4.53097939525841e-05, "epoch": 2.783748361730013, "percentage": 27.84, "elapsed_time": "0:17:56", "remaining_time": "0:46:30", "throughput": 2645.47, "total_tokens": 2848120} {"current_steps": 10625, "total_steps": 38150, "loss": 0.4653, "lr": 4.530312261069791e-05, "epoch": 2.7850589777195283, "percentage": 27.85, "elapsed_time": "0:17:57", "remaining_time": "0:46:30", "throughput": 2645.64, "total_tokens": 2849544} {"current_steps": 10630, "total_steps": 38150, "loss": 0.5307, "lr": 4.5296447019403245e-05, "epoch": 2.7863695937090434, "percentage": 27.86, "elapsed_time": "0:17:57", "remaining_time": "0:46:29", "throughput": 2645.6, "total_tokens": 2850648} {"current_steps": 10635, "total_steps": 38150, "loss": 0.5779, "lr": 4.5289767180097275e-05, "epoch": 2.7876802096985585, "percentage": 27.88, "elapsed_time": "0:17:57", "remaining_time": "0:46:28", "throughput": 2645.61, "total_tokens": 2851864} {"current_steps": 10640, "total_steps": 38150, "loss": 0.3657, "lr": 4.528308309417809e-05, "epoch": 2.7889908256880735, "percentage": 27.89, "elapsed_time": "0:17:58", "remaining_time": "0:46:28", "throughput": 2645.61, "total_tokens": 2852984} {"current_steps": 10645, "total_steps": 38150, "loss": 0.4504, "lr": 4.527639476304467e-05, "epoch": 2.790301441677588, "percentage": 27.9, "elapsed_time": "0:17:58", "remaining_time": "0:46:27", "throughput": 2645.63, "total_tokens": 2854152} {"current_steps": 10650, "total_steps": 38150, "loss": 0.3793, "lr": 4.526970218809686e-05, "epoch": 2.7916120576671037, "percentage": 27.92, "elapsed_time": "0:17:59", "remaining_time": "0:46:27", "throughput": 2646.04, "total_tokens": 2856104} {"current_steps": 10655, "total_steps": 38150, "loss": 0.5374, "lr": 4.52630053707354e-05, "epoch": 2.7929226736566184, "percentage": 27.93, "elapsed_time": "0:17:59", "remaining_time": "0:46:26", "throughput": 2646.0, "total_tokens": 2857176} {"current_steps": 10660, "total_steps": 38150, "loss": 0.3588, "lr": 4.525630431236193e-05, "epoch": 2.794233289646134, "percentage": 27.94, "elapsed_time": "0:18:00", "remaining_time": "0:46:25", "throughput": 2646.19, "total_tokens": 2858632} {"current_steps": 10665, "total_steps": 38150, "loss": 0.4613, "lr": 4.524959901437897e-05, "epoch": 2.7955439056356486, "percentage": 27.96, "elapsed_time": "0:18:00", "remaining_time": "0:46:25", "throughput": 2646.55, "total_tokens": 2860312} {"current_steps": 10670, "total_steps": 38150, "loss": 0.4443, "lr": 4.5242889478189926e-05, "epoch": 2.7968545216251637, "percentage": 27.97, "elapsed_time": "0:18:01", "remaining_time": "0:46:24", "throughput": 2646.55, "total_tokens": 2861512} {"current_steps": 10675, "total_steps": 38150, "loss": 0.4729, "lr": 4.5236175705199094e-05, "epoch": 2.7981651376146788, "percentage": 27.98, "elapsed_time": "0:18:01", "remaining_time": "0:46:23", "throughput": 2646.75, "total_tokens": 2862904} {"current_steps": 10680, "total_steps": 38150, "loss": 0.4538, "lr": 4.522945769681164e-05, "epoch": 2.799475753604194, "percentage": 27.99, "elapsed_time": "0:18:02", "remaining_time": "0:46:23", "throughput": 2646.85, "total_tokens": 2864232} {"current_steps": 10685, "total_steps": 38150, "loss": 0.2642, "lr": 4.522273545443365e-05, "epoch": 2.800786369593709, "percentage": 28.01, "elapsed_time": "0:18:02", "remaining_time": "0:46:22", "throughput": 2646.99, "total_tokens": 2865608} {"current_steps": 10690, "total_steps": 38150, "loss": 0.4864, "lr": 4.521600897947208e-05, "epoch": 2.802096985583224, "percentage": 28.02, "elapsed_time": "0:18:03", "remaining_time": "0:46:22", "throughput": 2647.28, "total_tokens": 2867224} {"current_steps": 10695, "total_steps": 38150, "loss": 0.4801, "lr": 4.520927827333475e-05, "epoch": 2.803407601572739, "percentage": 28.03, "elapsed_time": "0:18:03", "remaining_time": "0:46:21", "throughput": 2647.27, "total_tokens": 2868344} {"current_steps": 10700, "total_steps": 38150, "loss": 0.3929, "lr": 4.5202543337430405e-05, "epoch": 2.8047182175622543, "percentage": 28.05, "elapsed_time": "0:18:03", "remaining_time": "0:46:20", "throughput": 2647.3, "total_tokens": 2869528} {"current_steps": 10705, "total_steps": 38150, "loss": 0.2381, "lr": 4.519580417316863e-05, "epoch": 2.8060288335517694, "percentage": 28.06, "elapsed_time": "0:18:04", "remaining_time": "0:46:20", "throughput": 2647.58, "total_tokens": 2871112} {"current_steps": 10710, "total_steps": 38150, "loss": 0.4471, "lr": 4.518906078195996e-05, "epoch": 2.8073394495412844, "percentage": 28.07, "elapsed_time": "0:18:04", "remaining_time": "0:46:19", "throughput": 2647.55, "total_tokens": 2872184} {"current_steps": 10715, "total_steps": 38150, "loss": 0.4297, "lr": 4.518231316521574e-05, "epoch": 2.8086500655307995, "percentage": 28.09, "elapsed_time": "0:18:05", "remaining_time": "0:46:18", "throughput": 2647.59, "total_tokens": 2873448} {"current_steps": 10720, "total_steps": 38150, "loss": 0.3554, "lr": 4.517556132434825e-05, "epoch": 2.8099606815203146, "percentage": 28.1, "elapsed_time": "0:18:05", "remaining_time": "0:46:18", "throughput": 2647.61, "total_tokens": 2874664} {"current_steps": 10725, "total_steps": 38150, "loss": 0.499, "lr": 4.5168805260770633e-05, "epoch": 2.8112712975098297, "percentage": 28.11, "elapsed_time": "0:18:06", "remaining_time": "0:46:17", "throughput": 2647.77, "total_tokens": 2876072} {"current_steps": 10730, "total_steps": 38150, "loss": 0.4057, "lr": 4.516204497589692e-05, "epoch": 2.812581913499345, "percentage": 28.13, "elapsed_time": "0:18:06", "remaining_time": "0:46:16", "throughput": 2647.73, "total_tokens": 2877144} {"current_steps": 10735, "total_steps": 38150, "loss": 0.4213, "lr": 4.5155280471142036e-05, "epoch": 2.81389252948886, "percentage": 28.14, "elapsed_time": "0:18:07", "remaining_time": "0:46:16", "throughput": 2647.98, "total_tokens": 2878680} {"current_steps": 10740, "total_steps": 38150, "loss": 0.4944, "lr": 4.514851174792177e-05, "epoch": 2.8152031454783746, "percentage": 28.15, "elapsed_time": "0:18:07", "remaining_time": "0:46:15", "throughput": 2647.86, "total_tokens": 2879640} {"current_steps": 10745, "total_steps": 38150, "loss": 0.5437, "lr": 4.514173880765282e-05, "epoch": 2.81651376146789, "percentage": 28.17, "elapsed_time": "0:18:07", "remaining_time": "0:46:14", "throughput": 2647.97, "total_tokens": 2880904} {"current_steps": 10750, "total_steps": 38150, "loss": 0.5003, "lr": 4.513496165175273e-05, "epoch": 2.8178243774574048, "percentage": 28.18, "elapsed_time": "0:18:08", "remaining_time": "0:46:14", "throughput": 2648.16, "total_tokens": 2882312} {"current_steps": 10755, "total_steps": 38150, "loss": 0.361, "lr": 4.512818028163996e-05, "epoch": 2.8191349934469203, "percentage": 28.19, "elapsed_time": "0:18:08", "remaining_time": "0:46:13", "throughput": 2648.27, "total_tokens": 2883624} {"current_steps": 10760, "total_steps": 38150, "loss": 0.3979, "lr": 4.512139469873384e-05, "epoch": 2.820445609436435, "percentage": 28.2, "elapsed_time": "0:18:09", "remaining_time": "0:46:12", "throughput": 2648.19, "total_tokens": 2884680} {"current_steps": 10765, "total_steps": 38150, "loss": 0.3262, "lr": 4.511460490445457e-05, "epoch": 2.82175622542595, "percentage": 28.22, "elapsed_time": "0:18:09", "remaining_time": "0:46:12", "throughput": 2648.16, "total_tokens": 2885800} {"current_steps": 10770, "total_steps": 38150, "loss": 0.3678, "lr": 4.510781090022325e-05, "epoch": 2.823066841415465, "percentage": 28.23, "elapsed_time": "0:18:10", "remaining_time": "0:46:11", "throughput": 2648.4, "total_tokens": 2887352} {"current_steps": 10775, "total_steps": 38150, "loss": 0.4346, "lr": 4.5101012687461854e-05, "epoch": 2.8243774574049803, "percentage": 28.24, "elapsed_time": "0:18:10", "remaining_time": "0:46:10", "throughput": 2648.48, "total_tokens": 2888632} {"current_steps": 10780, "total_steps": 38150, "loss": 0.3862, "lr": 4.509421026759323e-05, "epoch": 2.8256880733944953, "percentage": 28.26, "elapsed_time": "0:18:11", "remaining_time": "0:46:10", "throughput": 2648.34, "total_tokens": 2889576} {"current_steps": 10785, "total_steps": 38150, "loss": 0.3761, "lr": 4.508740364204113e-05, "epoch": 2.8269986893840104, "percentage": 28.27, "elapsed_time": "0:18:11", "remaining_time": "0:46:09", "throughput": 2648.65, "total_tokens": 2891320} {"current_steps": 10790, "total_steps": 38150, "loss": 0.4267, "lr": 4.508059281223015e-05, "epoch": 2.8283093053735255, "percentage": 28.28, "elapsed_time": "0:18:12", "remaining_time": "0:46:09", "throughput": 2648.95, "total_tokens": 2892984} {"current_steps": 10795, "total_steps": 38150, "loss": 0.4885, "lr": 4.507377777958578e-05, "epoch": 2.8296199213630406, "percentage": 28.3, "elapsed_time": "0:18:12", "remaining_time": "0:46:08", "throughput": 2648.98, "total_tokens": 2894232} {"current_steps": 10800, "total_steps": 38150, "loss": 0.3749, "lr": 4.5066958545534415e-05, "epoch": 2.8309305373525557, "percentage": 28.31, "elapsed_time": "0:18:12", "remaining_time": "0:46:07", "throughput": 2648.89, "total_tokens": 2895224} {"current_steps": 10805, "total_steps": 38150, "loss": 0.4454, "lr": 4.50601351115033e-05, "epoch": 2.832241153342071, "percentage": 28.32, "elapsed_time": "0:18:13", "remaining_time": "0:46:07", "throughput": 2648.95, "total_tokens": 2896536} {"current_steps": 10810, "total_steps": 38150, "loss": 0.4718, "lr": 4.5053307478920564e-05, "epoch": 2.833551769331586, "percentage": 28.34, "elapsed_time": "0:18:13", "remaining_time": "0:46:06", "throughput": 2649.19, "total_tokens": 2897992} {"current_steps": 10815, "total_steps": 38150, "loss": 0.4173, "lr": 4.504647564921523e-05, "epoch": 2.834862385321101, "percentage": 28.35, "elapsed_time": "0:18:14", "remaining_time": "0:46:06", "throughput": 2649.41, "total_tokens": 2899496} {"current_steps": 10820, "total_steps": 38150, "loss": 0.4792, "lr": 4.503963962381717e-05, "epoch": 2.836173001310616, "percentage": 28.36, "elapsed_time": "0:18:14", "remaining_time": "0:46:05", "throughput": 2649.45, "total_tokens": 2900696} {"current_steps": 10825, "total_steps": 38150, "loss": 0.3424, "lr": 4.503279940415717e-05, "epoch": 2.837483617300131, "percentage": 28.37, "elapsed_time": "0:18:15", "remaining_time": "0:46:04", "throughput": 2649.65, "total_tokens": 2902072} {"current_steps": 10830, "total_steps": 38150, "loss": 0.4219, "lr": 4.5025954991666865e-05, "epoch": 2.8387942332896463, "percentage": 28.39, "elapsed_time": "0:18:15", "remaining_time": "0:46:04", "throughput": 2649.68, "total_tokens": 2903256} {"current_steps": 10835, "total_steps": 38150, "loss": 0.4682, "lr": 4.501910638777878e-05, "epoch": 2.840104849279161, "percentage": 28.4, "elapsed_time": "0:18:16", "remaining_time": "0:46:03", "throughput": 2649.81, "total_tokens": 2904632} {"current_steps": 10840, "total_steps": 38150, "loss": 0.3468, "lr": 4.5012253593926324e-05, "epoch": 2.8414154652686765, "percentage": 28.41, "elapsed_time": "0:18:16", "remaining_time": "0:46:02", "throughput": 2649.87, "total_tokens": 2905848} {"current_steps": 10845, "total_steps": 38150, "loss": 0.3642, "lr": 4.5005396611543765e-05, "epoch": 2.842726081258191, "percentage": 28.43, "elapsed_time": "0:18:17", "remaining_time": "0:46:02", "throughput": 2649.99, "total_tokens": 2907208} {"current_steps": 10850, "total_steps": 38150, "loss": 0.441, "lr": 4.499853544206626e-05, "epoch": 2.8440366972477067, "percentage": 28.44, "elapsed_time": "0:18:17", "remaining_time": "0:46:01", "throughput": 2650.01, "total_tokens": 2908424} {"current_steps": 10855, "total_steps": 38150, "loss": 0.5106, "lr": 4.499167008692985e-05, "epoch": 2.8453473132372213, "percentage": 28.45, "elapsed_time": "0:18:17", "remaining_time": "0:46:00", "throughput": 2649.99, "total_tokens": 2909496} {"current_steps": 10860, "total_steps": 38150, "loss": 0.3329, "lr": 4.4984800547571425e-05, "epoch": 2.8466579292267364, "percentage": 28.47, "elapsed_time": "0:18:18", "remaining_time": "0:46:00", "throughput": 2650.32, "total_tokens": 2911144} {"current_steps": 10865, "total_steps": 38150, "loss": 0.359, "lr": 4.497792682542878e-05, "epoch": 2.8479685452162515, "percentage": 28.48, "elapsed_time": "0:18:18", "remaining_time": "0:45:59", "throughput": 2650.5, "total_tokens": 2912536} {"current_steps": 10870, "total_steps": 38150, "loss": 0.4173, "lr": 4.4971048921940575e-05, "epoch": 2.8492791612057666, "percentage": 28.49, "elapsed_time": "0:18:19", "remaining_time": "0:45:58", "throughput": 2650.51, "total_tokens": 2913672} {"current_steps": 10875, "total_steps": 38150, "loss": 0.5925, "lr": 4.496416683854633e-05, "epoch": 2.8505897771952817, "percentage": 28.51, "elapsed_time": "0:18:19", "remaining_time": "0:45:58", "throughput": 2650.36, "total_tokens": 2914616} {"current_steps": 10880, "total_steps": 38150, "loss": 0.5661, "lr": 4.495728057668647e-05, "epoch": 2.851900393184797, "percentage": 28.52, "elapsed_time": "0:18:20", "remaining_time": "0:45:57", "throughput": 2650.49, "total_tokens": 2915912} {"current_steps": 10885, "total_steps": 38150, "loss": 0.5452, "lr": 4.4950390137802254e-05, "epoch": 2.853211009174312, "percentage": 28.53, "elapsed_time": "0:18:20", "remaining_time": "0:45:56", "throughput": 2650.73, "total_tokens": 2917336} {"current_steps": 10890, "total_steps": 38150, "loss": 0.6085, "lr": 4.4943495523335865e-05, "epoch": 2.854521625163827, "percentage": 28.55, "elapsed_time": "0:18:21", "remaining_time": "0:45:56", "throughput": 2650.9, "total_tokens": 2918776} {"current_steps": 10895, "total_steps": 38150, "loss": 0.4389, "lr": 4.493659673473032e-05, "epoch": 2.855832241153342, "percentage": 28.56, "elapsed_time": "0:18:21", "remaining_time": "0:45:55", "throughput": 2651.52, "total_tokens": 2921144} {"current_steps": 10900, "total_steps": 38150, "loss": 0.2832, "lr": 4.492969377342952e-05, "epoch": 2.857142857142857, "percentage": 28.57, "elapsed_time": "0:18:22", "remaining_time": "0:45:55", "throughput": 2651.82, "total_tokens": 2922776} {"current_steps": 10905, "total_steps": 38150, "loss": 0.4084, "lr": 4.4922786640878265e-05, "epoch": 2.8584534731323723, "percentage": 28.58, "elapsed_time": "0:18:22", "remaining_time": "0:45:54", "throughput": 2651.88, "total_tokens": 2923992} {"current_steps": 10910, "total_steps": 38150, "loss": 0.3447, "lr": 4.491587533852218e-05, "epoch": 2.8597640891218874, "percentage": 28.6, "elapsed_time": "0:18:23", "remaining_time": "0:45:54", "throughput": 2652.12, "total_tokens": 2925432} {"current_steps": 10915, "total_steps": 38150, "loss": 0.4495, "lr": 4.49089598678078e-05, "epoch": 2.8610747051114025, "percentage": 28.61, "elapsed_time": "0:18:23", "remaining_time": "0:45:53", "throughput": 2652.28, "total_tokens": 2926776} {"current_steps": 10920, "total_steps": 38150, "loss": 0.4077, "lr": 4.490204023018252e-05, "epoch": 2.8623853211009176, "percentage": 28.62, "elapsed_time": "0:18:23", "remaining_time": "0:45:52", "throughput": 2652.09, "total_tokens": 2927656} {"current_steps": 10925, "total_steps": 38150, "loss": 0.5122, "lr": 4.4895116427094605e-05, "epoch": 2.8636959370904327, "percentage": 28.64, "elapsed_time": "0:18:24", "remaining_time": "0:45:52", "throughput": 2652.09, "total_tokens": 2928808} {"current_steps": 10930, "total_steps": 38150, "loss": 0.4024, "lr": 4.48881884599932e-05, "epoch": 2.8650065530799473, "percentage": 28.65, "elapsed_time": "0:18:24", "remaining_time": "0:45:51", "throughput": 2652.46, "total_tokens": 2930472} {"current_steps": 10935, "total_steps": 38150, "loss": 0.3917, "lr": 4.4881256330328314e-05, "epoch": 2.866317169069463, "percentage": 28.66, "elapsed_time": "0:18:25", "remaining_time": "0:45:50", "throughput": 2652.66, "total_tokens": 2931976} {"current_steps": 10940, "total_steps": 38150, "loss": 0.4214, "lr": 4.4874320039550834e-05, "epoch": 2.8676277850589775, "percentage": 28.68, "elapsed_time": "0:18:25", "remaining_time": "0:45:50", "throughput": 2652.57, "total_tokens": 2932968} {"current_steps": 10945, "total_steps": 38150, "loss": 0.4417, "lr": 4.48673795891125e-05, "epoch": 2.8689384010484926, "percentage": 28.69, "elapsed_time": "0:18:26", "remaining_time": "0:45:49", "throughput": 2652.55, "total_tokens": 2934072} {"current_steps": 10950, "total_steps": 38150, "loss": 0.5831, "lr": 4.4860434980465954e-05, "epoch": 2.8702490170380077, "percentage": 28.7, "elapsed_time": "0:18:26", "remaining_time": "0:45:48", "throughput": 2652.76, "total_tokens": 2935560} {"current_steps": 10955, "total_steps": 38150, "loss": 0.3504, "lr": 4.485348621506468e-05, "epoch": 2.871559633027523, "percentage": 28.72, "elapsed_time": "0:18:27", "remaining_time": "0:45:48", "throughput": 2652.99, "total_tokens": 2937112} {"current_steps": 10960, "total_steps": 38150, "loss": 0.4683, "lr": 4.484653329436305e-05, "epoch": 2.872870249017038, "percentage": 28.73, "elapsed_time": "0:18:27", "remaining_time": "0:45:47", "throughput": 2653.04, "total_tokens": 2938360} {"current_steps": 10965, "total_steps": 38150, "loss": 0.5955, "lr": 4.483957621981629e-05, "epoch": 2.874180865006553, "percentage": 28.74, "elapsed_time": "0:18:27", "remaining_time": "0:45:46", "throughput": 2653.15, "total_tokens": 2939624} {"current_steps": 10970, "total_steps": 38150, "loss": 0.3089, "lr": 4.483261499288051e-05, "epoch": 2.875491480996068, "percentage": 28.75, "elapsed_time": "0:18:28", "remaining_time": "0:45:46", "throughput": 2653.33, "total_tokens": 2941032} {"current_steps": 10975, "total_steps": 38150, "loss": 0.719, "lr": 4.482564961501268e-05, "epoch": 2.876802096985583, "percentage": 28.77, "elapsed_time": "0:18:28", "remaining_time": "0:45:45", "throughput": 2653.34, "total_tokens": 2942200} {"current_steps": 10980, "total_steps": 38150, "loss": 0.3612, "lr": 4.481868008767063e-05, "epoch": 2.8781127129750983, "percentage": 28.78, "elapsed_time": "0:18:29", "remaining_time": "0:45:45", "throughput": 2654.03, "total_tokens": 2945208} {"current_steps": 10985, "total_steps": 38150, "loss": 0.4045, "lr": 4.4811706412313094e-05, "epoch": 2.8794233289646134, "percentage": 28.79, "elapsed_time": "0:18:30", "remaining_time": "0:45:45", "throughput": 2653.96, "total_tokens": 2946248} {"current_steps": 10990, "total_steps": 38150, "loss": 0.4159, "lr": 4.4804728590399635e-05, "epoch": 2.8807339449541285, "percentage": 28.81, "elapsed_time": "0:18:30", "remaining_time": "0:45:44", "throughput": 2654.36, "total_tokens": 2948088} {"current_steps": 10995, "total_steps": 38150, "loss": 0.3017, "lr": 4.47977466233907e-05, "epoch": 2.8820445609436436, "percentage": 28.82, "elapsed_time": "0:18:31", "remaining_time": "0:45:44", "throughput": 2654.37, "total_tokens": 2949240} {"current_steps": 11000, "total_steps": 38150, "loss": 0.5508, "lr": 4.479076051274761e-05, "epoch": 2.8833551769331587, "percentage": 28.83, "elapsed_time": "0:18:31", "remaining_time": "0:45:43", "throughput": 2654.33, "total_tokens": 2950328} {"current_steps": 11005, "total_steps": 38150, "loss": 0.362, "lr": 4.478377025993254e-05, "epoch": 2.8846657929226738, "percentage": 28.85, "elapsed_time": "0:18:31", "remaining_time": "0:45:42", "throughput": 2654.56, "total_tokens": 2951848} {"current_steps": 11010, "total_steps": 38150, "loss": 0.4997, "lr": 4.477677586640854e-05, "epoch": 2.885976408912189, "percentage": 28.86, "elapsed_time": "0:18:32", "remaining_time": "0:45:42", "throughput": 2654.48, "total_tokens": 2952888} {"current_steps": 11015, "total_steps": 38150, "loss": 0.5136, "lr": 4.476977733363951e-05, "epoch": 2.8872870249017035, "percentage": 28.87, "elapsed_time": "0:18:32", "remaining_time": "0:45:41", "throughput": 2654.41, "total_tokens": 2953912} {"current_steps": 11020, "total_steps": 38150, "loss": 0.4842, "lr": 4.4762774663090256e-05, "epoch": 2.888597640891219, "percentage": 28.89, "elapsed_time": "0:18:33", "remaining_time": "0:45:40", "throughput": 2654.61, "total_tokens": 2955288} {"current_steps": 11025, "total_steps": 38150, "loss": 0.34, "lr": 4.4755767856226405e-05, "epoch": 2.8899082568807337, "percentage": 28.9, "elapsed_time": "0:18:33", "remaining_time": "0:45:40", "throughput": 2654.71, "total_tokens": 2956536} {"current_steps": 11030, "total_steps": 38150, "loss": 0.4028, "lr": 4.474875691451448e-05, "epoch": 2.8912188728702493, "percentage": 28.91, "elapsed_time": "0:18:34", "remaining_time": "0:45:39", "throughput": 2654.61, "total_tokens": 2957528} {"current_steps": 11035, "total_steps": 38150, "loss": 0.3844, "lr": 4.474174183942186e-05, "epoch": 2.892529488859764, "percentage": 28.93, "elapsed_time": "0:18:34", "remaining_time": "0:45:38", "throughput": 2654.52, "total_tokens": 2958520} {"current_steps": 11040, "total_steps": 38150, "loss": 0.6704, "lr": 4.473472263241678e-05, "epoch": 2.893840104849279, "percentage": 28.94, "elapsed_time": "0:18:34", "remaining_time": "0:45:37", "throughput": 2654.6, "total_tokens": 2959752} {"current_steps": 11045, "total_steps": 38150, "loss": 0.424, "lr": 4.472769929496835e-05, "epoch": 2.895150720838794, "percentage": 28.95, "elapsed_time": "0:18:35", "remaining_time": "0:45:37", "throughput": 2654.86, "total_tokens": 2961352} {"current_steps": 11050, "total_steps": 38150, "loss": 0.5798, "lr": 4.472067182854654e-05, "epoch": 2.896461336828309, "percentage": 28.96, "elapsed_time": "0:18:35", "remaining_time": "0:45:36", "throughput": 2654.93, "total_tokens": 2962568} {"current_steps": 11055, "total_steps": 38150, "loss": 0.4802, "lr": 4.4713640234622205e-05, "epoch": 2.8977719528178243, "percentage": 28.98, "elapsed_time": "0:18:36", "remaining_time": "0:45:35", "throughput": 2655.03, "total_tokens": 2963816} {"current_steps": 11060, "total_steps": 38150, "loss": 0.4347, "lr": 4.4706604514667025e-05, "epoch": 2.8990825688073394, "percentage": 28.99, "elapsed_time": "0:18:36", "remaining_time": "0:45:35", "throughput": 2655.09, "total_tokens": 2965096} {"current_steps": 11065, "total_steps": 38150, "loss": 0.603, "lr": 4.469956467015357e-05, "epoch": 2.9003931847968545, "percentage": 29.0, "elapsed_time": "0:18:37", "remaining_time": "0:45:34", "throughput": 2655.41, "total_tokens": 2966744} {"current_steps": 11070, "total_steps": 38150, "loss": 0.4973, "lr": 4.469252070255527e-05, "epoch": 2.9017038007863696, "percentage": 29.02, "elapsed_time": "0:18:37", "remaining_time": "0:45:34", "throughput": 2655.32, "total_tokens": 2967768} {"current_steps": 11075, "total_steps": 38150, "loss": 0.5217, "lr": 4.4685472613346404e-05, "epoch": 2.9030144167758847, "percentage": 29.03, "elapsed_time": "0:18:38", "remaining_time": "0:45:33", "throughput": 2655.52, "total_tokens": 2969240} {"current_steps": 11080, "total_steps": 38150, "loss": 0.4945, "lr": 4.467842040400214e-05, "epoch": 2.9043250327653998, "percentage": 29.04, "elapsed_time": "0:18:38", "remaining_time": "0:45:32", "throughput": 2655.85, "total_tokens": 2970872} {"current_steps": 11085, "total_steps": 38150, "loss": 0.4036, "lr": 4.467136407599849e-05, "epoch": 2.905635648754915, "percentage": 29.06, "elapsed_time": "0:18:39", "remaining_time": "0:45:32", "throughput": 2656.05, "total_tokens": 2972296} {"current_steps": 11090, "total_steps": 38150, "loss": 0.3666, "lr": 4.466430363081233e-05, "epoch": 2.90694626474443, "percentage": 29.07, "elapsed_time": "0:18:39", "remaining_time": "0:45:32", "throughput": 2656.51, "total_tokens": 2974408} {"current_steps": 11095, "total_steps": 38150, "loss": 0.5346, "lr": 4.465723906992139e-05, "epoch": 2.908256880733945, "percentage": 29.08, "elapsed_time": "0:18:40", "remaining_time": "0:45:31", "throughput": 2656.43, "total_tokens": 2975448} {"current_steps": 11100, "total_steps": 38150, "loss": 0.5189, "lr": 4.465017039480428e-05, "epoch": 2.90956749672346, "percentage": 29.1, "elapsed_time": "0:18:40", "remaining_time": "0:45:30", "throughput": 2656.49, "total_tokens": 2976648} {"current_steps": 11105, "total_steps": 38150, "loss": 0.449, "lr": 4.464309760694047e-05, "epoch": 2.9108781127129753, "percentage": 29.11, "elapsed_time": "0:18:41", "remaining_time": "0:45:30", "throughput": 2656.71, "total_tokens": 2978216} {"current_steps": 11110, "total_steps": 38150, "loss": 0.4235, "lr": 4.4636020707810254e-05, "epoch": 2.91218872870249, "percentage": 29.12, "elapsed_time": "0:18:41", "remaining_time": "0:45:29", "throughput": 2656.67, "total_tokens": 2979368} {"current_steps": 11115, "total_steps": 38150, "loss": 0.3697, "lr": 4.462893969889484e-05, "epoch": 2.9134993446920054, "percentage": 29.13, "elapsed_time": "0:18:41", "remaining_time": "0:45:28", "throughput": 2656.83, "total_tokens": 2980760} {"current_steps": 11120, "total_steps": 38150, "loss": 0.4055, "lr": 4.462185458167626e-05, "epoch": 2.91480996068152, "percentage": 29.15, "elapsed_time": "0:18:42", "remaining_time": "0:45:28", "throughput": 2657.06, "total_tokens": 2982280} {"current_steps": 11125, "total_steps": 38150, "loss": 0.3858, "lr": 4.4614765357637425e-05, "epoch": 2.9161205766710356, "percentage": 29.16, "elapsed_time": "0:18:42", "remaining_time": "0:45:27", "throughput": 2657.21, "total_tokens": 2983624} {"current_steps": 11130, "total_steps": 38150, "loss": 0.4453, "lr": 4.4607672028262094e-05, "epoch": 2.9174311926605503, "percentage": 29.17, "elapsed_time": "0:18:43", "remaining_time": "0:45:26", "throughput": 2657.36, "total_tokens": 2984936} {"current_steps": 11135, "total_steps": 38150, "loss": 0.5424, "lr": 4.460057459503488e-05, "epoch": 2.9187418086500654, "percentage": 29.19, "elapsed_time": "0:18:43", "remaining_time": "0:45:26", "throughput": 2657.21, "total_tokens": 2985864} {"current_steps": 11140, "total_steps": 38150, "loss": 0.6238, "lr": 4.4593473059441274e-05, "epoch": 2.9200524246395805, "percentage": 29.2, "elapsed_time": "0:18:44", "remaining_time": "0:45:25", "throughput": 2657.38, "total_tokens": 2987336} {"current_steps": 11145, "total_steps": 38150, "loss": 0.3971, "lr": 4.458636742296761e-05, "epoch": 2.9213630406290956, "percentage": 29.21, "elapsed_time": "0:18:44", "remaining_time": "0:45:25", "throughput": 2657.51, "total_tokens": 2988712} {"current_steps": 11150, "total_steps": 38150, "loss": 0.4692, "lr": 4.4579257687101097e-05, "epoch": 2.9226736566186107, "percentage": 29.23, "elapsed_time": "0:18:45", "remaining_time": "0:45:24", "throughput": 2657.68, "total_tokens": 2990184} {"current_steps": 11155, "total_steps": 38150, "loss": 0.4076, "lr": 4.457214385332977e-05, "epoch": 2.9239842726081258, "percentage": 29.24, "elapsed_time": "0:18:45", "remaining_time": "0:45:23", "throughput": 2657.92, "total_tokens": 2991720} {"current_steps": 11160, "total_steps": 38150, "loss": 0.4066, "lr": 4.456502592314256e-05, "epoch": 2.925294888597641, "percentage": 29.25, "elapsed_time": "0:18:46", "remaining_time": "0:45:23", "throughput": 2658.25, "total_tokens": 2993352} {"current_steps": 11165, "total_steps": 38150, "loss": 0.4218, "lr": 4.455790389802922e-05, "epoch": 2.926605504587156, "percentage": 29.27, "elapsed_time": "0:18:46", "remaining_time": "0:45:22", "throughput": 2658.56, "total_tokens": 2995048} {"current_steps": 11170, "total_steps": 38150, "loss": 0.3076, "lr": 4.4550777779480393e-05, "epoch": 2.927916120576671, "percentage": 29.28, "elapsed_time": "0:18:47", "remaining_time": "0:45:22", "throughput": 2658.64, "total_tokens": 2996296} {"current_steps": 11175, "total_steps": 38150, "loss": 0.37, "lr": 4.454364756898756e-05, "epoch": 2.929226736566186, "percentage": 29.29, "elapsed_time": "0:18:47", "remaining_time": "0:45:21", "throughput": 2658.51, "total_tokens": 2997240} {"current_steps": 11180, "total_steps": 38150, "loss": 0.4256, "lr": 4.453651326804305e-05, "epoch": 2.9305373525557012, "percentage": 29.31, "elapsed_time": "0:18:47", "remaining_time": "0:45:20", "throughput": 2658.49, "total_tokens": 2998328} {"current_steps": 11185, "total_steps": 38150, "loss": 0.3606, "lr": 4.452937487814007e-05, "epoch": 2.9318479685452163, "percentage": 29.32, "elapsed_time": "0:18:48", "remaining_time": "0:45:20", "throughput": 2658.59, "total_tokens": 2999656} {"current_steps": 11190, "total_steps": 38150, "loss": 0.2999, "lr": 4.452223240077269e-05, "epoch": 2.9331585845347314, "percentage": 29.33, "elapsed_time": "0:18:48", "remaining_time": "0:45:19", "throughput": 2658.66, "total_tokens": 3000968} {"current_steps": 11195, "total_steps": 38150, "loss": 0.5905, "lr": 4.451508583743578e-05, "epoch": 2.9344692005242465, "percentage": 29.34, "elapsed_time": "0:18:49", "remaining_time": "0:45:18", "throughput": 2659.01, "total_tokens": 3002696} {"current_steps": 11200, "total_steps": 38150, "loss": 0.6629, "lr": 4.450793518962514e-05, "epoch": 2.9357798165137616, "percentage": 29.36, "elapsed_time": "0:18:49", "remaining_time": "0:45:18", "throughput": 2659.01, "total_tokens": 3003832} {"current_steps": 11205, "total_steps": 38150, "loss": 0.4392, "lr": 4.450078045883736e-05, "epoch": 2.9370904325032763, "percentage": 29.37, "elapsed_time": "0:18:50", "remaining_time": "0:45:17", "throughput": 2659.03, "total_tokens": 3004984} {"current_steps": 11210, "total_steps": 38150, "loss": 0.5339, "lr": 4.449362164656993e-05, "epoch": 2.938401048492792, "percentage": 29.38, "elapsed_time": "0:18:50", "remaining_time": "0:45:16", "throughput": 2658.97, "total_tokens": 3006040} {"current_steps": 11215, "total_steps": 38150, "loss": 0.4557, "lr": 4.448645875432117e-05, "epoch": 2.9397116644823065, "percentage": 29.4, "elapsed_time": "0:18:50", "remaining_time": "0:45:16", "throughput": 2659.18, "total_tokens": 3007448} {"current_steps": 11220, "total_steps": 38150, "loss": 0.4614, "lr": 4.447929178359026e-05, "epoch": 2.941022280471822, "percentage": 29.41, "elapsed_time": "0:18:51", "remaining_time": "0:45:15", "throughput": 2659.33, "total_tokens": 3008776} {"current_steps": 11225, "total_steps": 38150, "loss": 0.4676, "lr": 4.4472120735877246e-05, "epoch": 2.9423328964613367, "percentage": 29.42, "elapsed_time": "0:18:51", "remaining_time": "0:45:14", "throughput": 2659.3, "total_tokens": 3009864} {"current_steps": 11230, "total_steps": 38150, "loss": 0.5615, "lr": 4.4464945612683005e-05, "epoch": 2.9436435124508518, "percentage": 29.44, "elapsed_time": "0:18:52", "remaining_time": "0:45:14", "throughput": 2659.42, "total_tokens": 3011176} {"current_steps": 11235, "total_steps": 38150, "loss": 0.3726, "lr": 4.4457766415509275e-05, "epoch": 2.944954128440367, "percentage": 29.45, "elapsed_time": "0:18:52", "remaining_time": "0:45:13", "throughput": 2659.69, "total_tokens": 3012664} {"current_steps": 11240, "total_steps": 38150, "loss": 0.4599, "lr": 4.445058314585866e-05, "epoch": 2.946264744429882, "percentage": 29.46, "elapsed_time": "0:18:53", "remaining_time": "0:45:12", "throughput": 2659.61, "total_tokens": 3013704} {"current_steps": 11245, "total_steps": 38150, "loss": 0.4777, "lr": 4.44433958052346e-05, "epoch": 2.947575360419397, "percentage": 29.48, "elapsed_time": "0:18:53", "remaining_time": "0:45:12", "throughput": 2659.85, "total_tokens": 3015224} {"current_steps": 11250, "total_steps": 38150, "loss": 0.5097, "lr": 4.443620439514138e-05, "epoch": 2.948885976408912, "percentage": 29.49, "elapsed_time": "0:18:54", "remaining_time": "0:45:11", "throughput": 2660.07, "total_tokens": 3016776} {"current_steps": 11255, "total_steps": 38150, "loss": 0.5463, "lr": 4.442900891708418e-05, "epoch": 2.9501965923984272, "percentage": 29.5, "elapsed_time": "0:18:54", "remaining_time": "0:45:11", "throughput": 2660.1, "total_tokens": 3017960} {"current_steps": 11260, "total_steps": 38150, "loss": 0.3822, "lr": 4.442180937256898e-05, "epoch": 2.9515072083879423, "percentage": 29.52, "elapsed_time": "0:18:54", "remaining_time": "0:45:10", "throughput": 2660.17, "total_tokens": 3019176} {"current_steps": 11265, "total_steps": 38150, "loss": 0.4823, "lr": 4.4414605763102635e-05, "epoch": 2.9528178243774574, "percentage": 29.53, "elapsed_time": "0:18:55", "remaining_time": "0:45:09", "throughput": 2660.19, "total_tokens": 3020392} {"current_steps": 11270, "total_steps": 38150, "loss": 0.3543, "lr": 4.4407398090192846e-05, "epoch": 2.9541284403669725, "percentage": 29.54, "elapsed_time": "0:18:55", "remaining_time": "0:45:09", "throughput": 2660.15, "total_tokens": 3021496} {"current_steps": 11275, "total_steps": 38150, "loss": 0.5694, "lr": 4.440018635534818e-05, "epoch": 2.9554390563564876, "percentage": 29.55, "elapsed_time": "0:18:56", "remaining_time": "0:45:08", "throughput": 2660.08, "total_tokens": 3022536} {"current_steps": 11280, "total_steps": 38150, "loss": 0.6251, "lr": 4.439297056007802e-05, "epoch": 2.9567496723460027, "percentage": 29.57, "elapsed_time": "0:18:56", "remaining_time": "0:45:07", "throughput": 2660.26, "total_tokens": 3024024} {"current_steps": 11285, "total_steps": 38150, "loss": 0.4259, "lr": 4.4385750705892634e-05, "epoch": 2.958060288335518, "percentage": 29.58, "elapsed_time": "0:18:57", "remaining_time": "0:45:07", "throughput": 2660.35, "total_tokens": 3025256} {"current_steps": 11290, "total_steps": 38150, "loss": 0.3884, "lr": 4.437852679430313e-05, "epoch": 2.959370904325033, "percentage": 29.59, "elapsed_time": "0:18:57", "remaining_time": "0:45:06", "throughput": 2660.55, "total_tokens": 3026792} {"current_steps": 11295, "total_steps": 38150, "loss": 0.4688, "lr": 4.437129882682144e-05, "epoch": 2.960681520314548, "percentage": 29.61, "elapsed_time": "0:18:58", "remaining_time": "0:45:06", "throughput": 2660.87, "total_tokens": 3028424} {"current_steps": 11300, "total_steps": 38150, "loss": 0.4044, "lr": 4.436406680496038e-05, "epoch": 2.9619921363040627, "percentage": 29.62, "elapsed_time": "0:18:58", "remaining_time": "0:45:05", "throughput": 2660.75, "total_tokens": 3029416} {"current_steps": 11305, "total_steps": 38150, "loss": 0.4301, "lr": 4.43568307302336e-05, "epoch": 2.963302752293578, "percentage": 29.63, "elapsed_time": "0:18:59", "remaining_time": "0:45:04", "throughput": 2660.89, "total_tokens": 3030776} {"current_steps": 11310, "total_steps": 38150, "loss": 0.4353, "lr": 4.4349590604155586e-05, "epoch": 2.964613368283093, "percentage": 29.65, "elapsed_time": "0:18:59", "remaining_time": "0:45:04", "throughput": 2660.89, "total_tokens": 3031896} {"current_steps": 11315, "total_steps": 38150, "loss": 0.59, "lr": 4.43423464282417e-05, "epoch": 2.9659239842726084, "percentage": 29.66, "elapsed_time": "0:18:59", "remaining_time": "0:45:03", "throughput": 2660.84, "total_tokens": 3032952} {"current_steps": 11320, "total_steps": 38150, "loss": 0.5264, "lr": 4.4335098204008126e-05, "epoch": 2.967234600262123, "percentage": 29.67, "elapsed_time": "0:19:00", "remaining_time": "0:45:02", "throughput": 2661.21, "total_tokens": 3034760} {"current_steps": 11325, "total_steps": 38150, "loss": 0.572, "lr": 4.43278459329719e-05, "epoch": 2.968545216251638, "percentage": 29.69, "elapsed_time": "0:19:00", "remaining_time": "0:45:02", "throughput": 2661.27, "total_tokens": 3035976} {"current_steps": 11330, "total_steps": 38150, "loss": 0.5973, "lr": 4.432058961665092e-05, "epoch": 2.9698558322411532, "percentage": 29.7, "elapsed_time": "0:19:01", "remaining_time": "0:45:01", "throughput": 2661.37, "total_tokens": 3037304} {"current_steps": 11335, "total_steps": 38150, "loss": 0.3219, "lr": 4.4313329256563916e-05, "epoch": 2.9711664482306683, "percentage": 29.71, "elapsed_time": "0:19:01", "remaining_time": "0:45:00", "throughput": 2661.51, "total_tokens": 3038664} {"current_steps": 11340, "total_steps": 38150, "loss": 0.3878, "lr": 4.430606485423048e-05, "epoch": 2.9724770642201834, "percentage": 29.72, "elapsed_time": "0:19:02", "remaining_time": "0:45:00", "throughput": 2661.65, "total_tokens": 3040024} {"current_steps": 11345, "total_steps": 38150, "loss": 0.5517, "lr": 4.4298796411171015e-05, "epoch": 2.9737876802096985, "percentage": 29.74, "elapsed_time": "0:19:02", "remaining_time": "0:44:59", "throughput": 2661.79, "total_tokens": 3041320} {"current_steps": 11350, "total_steps": 38150, "loss": 0.4018, "lr": 4.429152392890681e-05, "epoch": 2.9750982961992136, "percentage": 29.75, "elapsed_time": "0:19:03", "remaining_time": "0:44:58", "throughput": 2661.75, "total_tokens": 3042408} {"current_steps": 11355, "total_steps": 38150, "loss": 0.4687, "lr": 4.428424740895998e-05, "epoch": 2.9764089121887287, "percentage": 29.76, "elapsed_time": "0:19:03", "remaining_time": "0:44:58", "throughput": 2661.82, "total_tokens": 3043640} {"current_steps": 11360, "total_steps": 38150, "loss": 0.4836, "lr": 4.427696685285349e-05, "epoch": 2.977719528178244, "percentage": 29.78, "elapsed_time": "0:19:03", "remaining_time": "0:44:57", "throughput": 2662.06, "total_tokens": 3045176} {"current_steps": 11365, "total_steps": 38150, "loss": 0.3748, "lr": 4.4269682262111145e-05, "epoch": 2.979030144167759, "percentage": 29.79, "elapsed_time": "0:19:04", "remaining_time": "0:44:57", "throughput": 2662.15, "total_tokens": 3046504} {"current_steps": 11370, "total_steps": 38150, "loss": 0.3986, "lr": 4.42623936382576e-05, "epoch": 2.980340760157274, "percentage": 29.8, "elapsed_time": "0:19:04", "remaining_time": "0:44:56", "throughput": 2662.23, "total_tokens": 3047752} {"current_steps": 11375, "total_steps": 38150, "loss": 0.6448, "lr": 4.425510098281835e-05, "epoch": 2.981651376146789, "percentage": 29.82, "elapsed_time": "0:19:05", "remaining_time": "0:44:55", "throughput": 2662.49, "total_tokens": 3049368} {"current_steps": 11380, "total_steps": 38150, "loss": 0.4639, "lr": 4.424780429731973e-05, "epoch": 2.982961992136304, "percentage": 29.83, "elapsed_time": "0:19:05", "remaining_time": "0:44:55", "throughput": 2662.65, "total_tokens": 3050712} {"current_steps": 11385, "total_steps": 38150, "loss": 0.5218, "lr": 4.424050358328893e-05, "epoch": 2.9842726081258193, "percentage": 29.84, "elapsed_time": "0:19:06", "remaining_time": "0:44:54", "throughput": 2662.95, "total_tokens": 3052488} {"current_steps": 11390, "total_steps": 38150, "loss": 0.4873, "lr": 4.423319884225398e-05, "epoch": 2.9855832241153344, "percentage": 29.86, "elapsed_time": "0:19:06", "remaining_time": "0:44:54", "throughput": 2663.0, "total_tokens": 3053736} {"current_steps": 11395, "total_steps": 38150, "loss": 0.331, "lr": 4.422589007574374e-05, "epoch": 2.986893840104849, "percentage": 29.87, "elapsed_time": "0:19:07", "remaining_time": "0:44:53", "throughput": 2663.0, "total_tokens": 3054856} {"current_steps": 11400, "total_steps": 38150, "loss": 0.3954, "lr": 4.421857728528792e-05, "epoch": 2.9882044560943646, "percentage": 29.88, "elapsed_time": "0:19:07", "remaining_time": "0:44:52", "throughput": 2662.89, "total_tokens": 3055848} {"current_steps": 11405, "total_steps": 38150, "loss": 0.4025, "lr": 4.421126047241709e-05, "epoch": 2.9895150720838792, "percentage": 29.9, "elapsed_time": "0:19:08", "remaining_time": "0:44:52", "throughput": 2662.91, "total_tokens": 3057112} {"current_steps": 11410, "total_steps": 38150, "loss": 0.5234, "lr": 4.420393963866263e-05, "epoch": 2.9908256880733948, "percentage": 29.91, "elapsed_time": "0:19:08", "remaining_time": "0:44:51", "throughput": 2662.96, "total_tokens": 3058312} {"current_steps": 11415, "total_steps": 38150, "loss": 0.4033, "lr": 4.4196614785556795e-05, "epoch": 2.9921363040629094, "percentage": 29.92, "elapsed_time": "0:19:08", "remaining_time": "0:44:50", "throughput": 2663.26, "total_tokens": 3060008} {"current_steps": 11420, "total_steps": 38150, "loss": 0.4826, "lr": 4.418928591463265e-05, "epoch": 2.9934469200524245, "percentage": 29.93, "elapsed_time": "0:19:09", "remaining_time": "0:44:50", "throughput": 2663.17, "total_tokens": 3061016} {"current_steps": 11425, "total_steps": 38150, "loss": 0.2875, "lr": 4.418195302742412e-05, "epoch": 2.9947575360419396, "percentage": 29.95, "elapsed_time": "0:19:09", "remaining_time": "0:44:49", "throughput": 2663.42, "total_tokens": 3062632} {"current_steps": 11430, "total_steps": 38150, "loss": 0.4884, "lr": 4.417461612546596e-05, "epoch": 2.9960681520314547, "percentage": 29.96, "elapsed_time": "0:19:10", "remaining_time": "0:44:49", "throughput": 2663.59, "total_tokens": 3064008} {"current_steps": 11435, "total_steps": 38150, "loss": 0.4887, "lr": 4.416727521029379e-05, "epoch": 2.99737876802097, "percentage": 29.97, "elapsed_time": "0:19:10", "remaining_time": "0:44:48", "throughput": 2663.65, "total_tokens": 3065256} {"current_steps": 11440, "total_steps": 38150, "loss": 0.393, "lr": 4.415993028344403e-05, "epoch": 2.998689384010485, "percentage": 29.99, "elapsed_time": "0:19:11", "remaining_time": "0:44:47", "throughput": 2663.71, "total_tokens": 3066456} {"current_steps": 11445, "total_steps": 38150, "loss": 0.3892, "lr": 4.415258134645396e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:19:11", "remaining_time": "0:44:47", "throughput": 2663.5, "total_tokens": 3067768} {"current_steps": 11448, "total_steps": 38150, "eval_loss": 0.4982500374317169, "epoch": 3.000786369593709, "percentage": 30.01, "elapsed_time": "0:19:29", "remaining_time": "0:45:26", "throughput": 2624.68, "total_tokens": 3068424} {"current_steps": 11450, "total_steps": 38150, "loss": 0.5965, "lr": 4.414522840086172e-05, "epoch": 3.001310615989515, "percentage": 30.01, "elapsed_time": "0:19:30", "remaining_time": "0:45:29", "throughput": 2621.7, "total_tokens": 3068920} {"current_steps": 11455, "total_steps": 38150, "loss": 0.4483, "lr": 4.413787144820625e-05, "epoch": 3.00262123197903, "percentage": 30.03, "elapsed_time": "0:19:31", "remaining_time": "0:45:29", "throughput": 2621.87, "total_tokens": 3070328} {"current_steps": 11460, "total_steps": 38150, "loss": 0.3816, "lr": 4.413051049002735e-05, "epoch": 3.0039318479685453, "percentage": 30.04, "elapsed_time": "0:19:31", "remaining_time": "0:45:28", "throughput": 2621.8, "total_tokens": 3071368} {"current_steps": 11465, "total_steps": 38150, "loss": 0.4642, "lr": 4.412314552786566e-05, "epoch": 3.0052424639580604, "percentage": 30.05, "elapsed_time": "0:19:31", "remaining_time": "0:45:27", "throughput": 2622.0, "total_tokens": 3072840} {"current_steps": 11470, "total_steps": 38150, "loss": 0.3447, "lr": 4.4115776563262656e-05, "epoch": 3.0065530799475755, "percentage": 30.07, "elapsed_time": "0:19:32", "remaining_time": "0:45:27", "throughput": 2622.25, "total_tokens": 3074440} {"current_steps": 11475, "total_steps": 38150, "loss": 0.3527, "lr": 4.410840359776065e-05, "epoch": 3.0078636959370906, "percentage": 30.08, "elapsed_time": "0:19:32", "remaining_time": "0:45:26", "throughput": 2622.26, "total_tokens": 3075592} {"current_steps": 11480, "total_steps": 38150, "loss": 0.4124, "lr": 4.410102663290278e-05, "epoch": 3.0091743119266057, "percentage": 30.09, "elapsed_time": "0:19:33", "remaining_time": "0:45:25", "throughput": 2622.2, "total_tokens": 3076616} {"current_steps": 11485, "total_steps": 38150, "loss": 0.3767, "lr": 4.4093645670233045e-05, "epoch": 3.0104849279161208, "percentage": 30.1, "elapsed_time": "0:19:33", "remaining_time": "0:45:25", "throughput": 2622.4, "total_tokens": 3078088} {"current_steps": 11490, "total_steps": 38150, "loss": 0.4629, "lr": 4.4086260711296265e-05, "epoch": 3.011795543905636, "percentage": 30.12, "elapsed_time": "0:19:34", "remaining_time": "0:45:24", "throughput": 2622.3, "total_tokens": 3079064} {"current_steps": 11495, "total_steps": 38150, "loss": 0.3462, "lr": 4.407887175763809e-05, "epoch": 3.0131061598951505, "percentage": 30.13, "elapsed_time": "0:19:34", "remaining_time": "0:45:23", "throughput": 2622.32, "total_tokens": 3080184} {"current_steps": 11500, "total_steps": 38150, "loss": 0.3782, "lr": 4.407147881080503e-05, "epoch": 3.0144167758846656, "percentage": 30.14, "elapsed_time": "0:19:35", "remaining_time": "0:45:23", "throughput": 2622.73, "total_tokens": 3082008} {"current_steps": 11505, "total_steps": 38150, "loss": 0.4333, "lr": 4.40640818723444e-05, "epoch": 3.0157273918741807, "percentage": 30.16, "elapsed_time": "0:19:35", "remaining_time": "0:45:22", "throughput": 2622.84, "total_tokens": 3083352} {"current_steps": 11510, "total_steps": 38150, "loss": 0.3723, "lr": 4.4056680943804374e-05, "epoch": 3.017038007863696, "percentage": 30.17, "elapsed_time": "0:19:35", "remaining_time": "0:45:21", "throughput": 2622.68, "total_tokens": 3084248} {"current_steps": 11515, "total_steps": 38150, "loss": 0.4296, "lr": 4.404927602673396e-05, "epoch": 3.018348623853211, "percentage": 30.18, "elapsed_time": "0:19:36", "remaining_time": "0:45:21", "throughput": 2622.97, "total_tokens": 3085864} {"current_steps": 11520, "total_steps": 38150, "loss": 0.4765, "lr": 4.404186712268299e-05, "epoch": 3.019659239842726, "percentage": 30.2, "elapsed_time": "0:19:36", "remaining_time": "0:45:20", "throughput": 2623.03, "total_tokens": 3087112} {"current_steps": 11525, "total_steps": 38150, "loss": 0.2866, "lr": 4.4034454233202124e-05, "epoch": 3.020969855832241, "percentage": 30.21, "elapsed_time": "0:19:37", "remaining_time": "0:45:19", "throughput": 2623.3, "total_tokens": 3088632} {"current_steps": 11530, "total_steps": 38150, "loss": 0.393, "lr": 4.4027037359842884e-05, "epoch": 3.022280471821756, "percentage": 30.22, "elapsed_time": "0:19:37", "remaining_time": "0:45:19", "throughput": 2623.15, "total_tokens": 3089560} {"current_steps": 11535, "total_steps": 38150, "loss": 0.3265, "lr": 4.401961650415759e-05, "epoch": 3.0235910878112713, "percentage": 30.24, "elapsed_time": "0:19:38", "remaining_time": "0:45:18", "throughput": 2623.11, "total_tokens": 3090600} {"current_steps": 11540, "total_steps": 38150, "loss": 0.3968, "lr": 4.401219166769943e-05, "epoch": 3.0249017038007864, "percentage": 30.25, "elapsed_time": "0:19:38", "remaining_time": "0:45:17", "throughput": 2623.1, "total_tokens": 3091704} {"current_steps": 11545, "total_steps": 38150, "loss": 0.4352, "lr": 4.400476285202241e-05, "epoch": 3.0262123197903015, "percentage": 30.26, "elapsed_time": "0:19:39", "remaining_time": "0:45:17", "throughput": 2623.06, "total_tokens": 3092744} {"current_steps": 11550, "total_steps": 38150, "loss": 0.506, "lr": 4.399733005868136e-05, "epoch": 3.0275229357798166, "percentage": 30.28, "elapsed_time": "0:19:39", "remaining_time": "0:45:16", "throughput": 2623.3, "total_tokens": 3094408} {"current_steps": 11555, "total_steps": 38150, "loss": 0.3539, "lr": 4.3989893289231954e-05, "epoch": 3.0288335517693317, "percentage": 30.29, "elapsed_time": "0:19:40", "remaining_time": "0:45:16", "throughput": 2623.41, "total_tokens": 3095800} {"current_steps": 11560, "total_steps": 38150, "loss": 0.5597, "lr": 4.398245254523069e-05, "epoch": 3.0301441677588468, "percentage": 30.3, "elapsed_time": "0:19:40", "remaining_time": "0:45:15", "throughput": 2623.38, "total_tokens": 3096888} {"current_steps": 11565, "total_steps": 38150, "loss": 0.6472, "lr": 4.397500782823492e-05, "epoch": 3.031454783748362, "percentage": 30.31, "elapsed_time": "0:19:41", "remaining_time": "0:45:14", "throughput": 2623.8, "total_tokens": 3098856} {"current_steps": 11570, "total_steps": 38150, "loss": 0.3778, "lr": 4.3967559139802785e-05, "epoch": 3.032765399737877, "percentage": 30.33, "elapsed_time": "0:19:41", "remaining_time": "0:45:14", "throughput": 2623.91, "total_tokens": 3100184} {"current_steps": 11575, "total_steps": 38150, "loss": 0.4073, "lr": 4.39601064814933e-05, "epoch": 3.034076015727392, "percentage": 30.34, "elapsed_time": "0:19:41", "remaining_time": "0:45:13", "throughput": 2624.12, "total_tokens": 3101688} {"current_steps": 11580, "total_steps": 38150, "loss": 0.3867, "lr": 4.395264985486629e-05, "epoch": 3.035386631716907, "percentage": 30.35, "elapsed_time": "0:19:42", "remaining_time": "0:45:13", "throughput": 2624.31, "total_tokens": 3103048} {"current_steps": 11585, "total_steps": 38150, "loss": 0.3238, "lr": 4.394518926148241e-05, "epoch": 3.036697247706422, "percentage": 30.37, "elapsed_time": "0:19:42", "remaining_time": "0:45:12", "throughput": 2624.45, "total_tokens": 3104376} {"current_steps": 11590, "total_steps": 38150, "loss": 0.4289, "lr": 4.393772470290315e-05, "epoch": 3.038007863695937, "percentage": 30.38, "elapsed_time": "0:19:43", "remaining_time": "0:45:11", "throughput": 2624.6, "total_tokens": 3105720} {"current_steps": 11595, "total_steps": 38150, "loss": 0.4933, "lr": 4.393025618069084e-05, "epoch": 3.039318479685452, "percentage": 30.39, "elapsed_time": "0:19:43", "remaining_time": "0:45:11", "throughput": 2624.74, "total_tokens": 3107080} {"current_steps": 11600, "total_steps": 38150, "loss": 0.3588, "lr": 4.3922783696408615e-05, "epoch": 3.040629095674967, "percentage": 30.41, "elapsed_time": "0:19:44", "remaining_time": "0:45:10", "throughput": 2625.01, "total_tokens": 3108648} {"current_steps": 11605, "total_steps": 38150, "loss": 0.4388, "lr": 4.3915307251620456e-05, "epoch": 3.041939711664482, "percentage": 30.42, "elapsed_time": "0:19:44", "remaining_time": "0:45:09", "throughput": 2625.16, "total_tokens": 3110040} {"current_steps": 11610, "total_steps": 38150, "loss": 0.4702, "lr": 4.390782684789118e-05, "epoch": 3.0432503276539973, "percentage": 30.43, "elapsed_time": "0:19:45", "remaining_time": "0:45:09", "throughput": 2625.42, "total_tokens": 3111672} {"current_steps": 11615, "total_steps": 38150, "loss": 0.4637, "lr": 4.3900342486786405e-05, "epoch": 3.0445609436435124, "percentage": 30.45, "elapsed_time": "0:19:45", "remaining_time": "0:45:08", "throughput": 2625.52, "total_tokens": 3112936} {"current_steps": 11620, "total_steps": 38150, "loss": 0.4431, "lr": 4.389285416987261e-05, "epoch": 3.0458715596330275, "percentage": 30.46, "elapsed_time": "0:19:46", "remaining_time": "0:45:07", "throughput": 2625.42, "total_tokens": 3113928} {"current_steps": 11625, "total_steps": 38150, "loss": 0.3941, "lr": 4.388536189871708e-05, "epoch": 3.0471821756225426, "percentage": 30.47, "elapsed_time": "0:19:46", "remaining_time": "0:45:07", "throughput": 2625.59, "total_tokens": 3115384} {"current_steps": 11630, "total_steps": 38150, "loss": 0.9114, "lr": 4.387786567488794e-05, "epoch": 3.0484927916120577, "percentage": 30.48, "elapsed_time": "0:19:46", "remaining_time": "0:45:06", "throughput": 2625.63, "total_tokens": 3116616} {"current_steps": 11635, "total_steps": 38150, "loss": 0.3731, "lr": 4.387036549995413e-05, "epoch": 3.0498034076015728, "percentage": 30.5, "elapsed_time": "0:19:47", "remaining_time": "0:45:06", "throughput": 2625.66, "total_tokens": 3117768} {"current_steps": 11640, "total_steps": 38150, "loss": 0.3937, "lr": 4.386286137548543e-05, "epoch": 3.051114023591088, "percentage": 30.51, "elapsed_time": "0:19:47", "remaining_time": "0:45:05", "throughput": 2625.75, "total_tokens": 3119064} {"current_steps": 11645, "total_steps": 38150, "loss": 0.5141, "lr": 4.3855353303052436e-05, "epoch": 3.052424639580603, "percentage": 30.52, "elapsed_time": "0:19:48", "remaining_time": "0:45:04", "throughput": 2625.98, "total_tokens": 3120520} {"current_steps": 11650, "total_steps": 38150, "loss": 0.4238, "lr": 4.384784128422657e-05, "epoch": 3.053735255570118, "percentage": 30.54, "elapsed_time": "0:19:48", "remaining_time": "0:45:04", "throughput": 2625.82, "total_tokens": 3121416} {"current_steps": 11655, "total_steps": 38150, "loss": 0.5727, "lr": 4.3840325320580086e-05, "epoch": 3.055045871559633, "percentage": 30.55, "elapsed_time": "0:19:49", "remaining_time": "0:45:03", "throughput": 2625.97, "total_tokens": 3122744} {"current_steps": 11660, "total_steps": 38150, "loss": 0.3003, "lr": 4.383280541368608e-05, "epoch": 3.0563564875491482, "percentage": 30.56, "elapsed_time": "0:19:49", "remaining_time": "0:45:03", "throughput": 2626.57, "total_tokens": 3125080} {"current_steps": 11665, "total_steps": 38150, "loss": 0.3629, "lr": 4.382528156511843e-05, "epoch": 3.0576671035386633, "percentage": 30.58, "elapsed_time": "0:19:50", "remaining_time": "0:45:02", "throughput": 2626.52, "total_tokens": 3126104} {"current_steps": 11670, "total_steps": 38150, "loss": 0.4208, "lr": 4.381775377645188e-05, "epoch": 3.0589777195281784, "percentage": 30.59, "elapsed_time": "0:19:50", "remaining_time": "0:45:01", "throughput": 2626.59, "total_tokens": 3127304} {"current_steps": 11675, "total_steps": 38150, "loss": 0.3621, "lr": 4.381022204926198e-05, "epoch": 3.0602883355176935, "percentage": 30.6, "elapsed_time": "0:19:51", "remaining_time": "0:45:01", "throughput": 2626.75, "total_tokens": 3128712} {"current_steps": 11680, "total_steps": 38150, "loss": 0.6157, "lr": 4.38026863851251e-05, "epoch": 3.061598951507208, "percentage": 30.62, "elapsed_time": "0:19:51", "remaining_time": "0:45:00", "throughput": 2626.68, "total_tokens": 3129720} {"current_steps": 11685, "total_steps": 38150, "loss": 0.4427, "lr": 4.379514678561846e-05, "epoch": 3.0629095674967233, "percentage": 30.63, "elapsed_time": "0:19:52", "remaining_time": "0:44:59", "throughput": 2626.86, "total_tokens": 3131224} {"current_steps": 11690, "total_steps": 38150, "loss": 0.2769, "lr": 4.3787603252320065e-05, "epoch": 3.0642201834862384, "percentage": 30.64, "elapsed_time": "0:19:52", "remaining_time": "0:44:59", "throughput": 2627.15, "total_tokens": 3132888} {"current_steps": 11695, "total_steps": 38150, "loss": 0.388, "lr": 4.378005578680877e-05, "epoch": 3.0655307994757535, "percentage": 30.66, "elapsed_time": "0:19:52", "remaining_time": "0:44:58", "throughput": 2627.4, "total_tokens": 3134472} {"current_steps": 11700, "total_steps": 38150, "loss": 0.5551, "lr": 4.377250439066426e-05, "epoch": 3.0668414154652686, "percentage": 30.67, "elapsed_time": "0:19:53", "remaining_time": "0:44:57", "throughput": 2627.28, "total_tokens": 3135416} {"current_steps": 11705, "total_steps": 38150, "loss": 0.769, "lr": 4.3764949065467006e-05, "epoch": 3.0681520314547837, "percentage": 30.68, "elapsed_time": "0:19:53", "remaining_time": "0:44:57", "throughput": 2627.36, "total_tokens": 3136616} {"current_steps": 11710, "total_steps": 38150, "loss": 0.4483, "lr": 4.375738981279834e-05, "epoch": 3.0694626474442988, "percentage": 30.69, "elapsed_time": "0:19:54", "remaining_time": "0:44:56", "throughput": 2627.35, "total_tokens": 3137720} {"current_steps": 11715, "total_steps": 38150, "loss": 0.4704, "lr": 4.37498266342404e-05, "epoch": 3.070773263433814, "percentage": 30.71, "elapsed_time": "0:19:54", "remaining_time": "0:44:55", "throughput": 2627.23, "total_tokens": 3138680} {"current_steps": 11720, "total_steps": 38150, "loss": 0.252, "lr": 4.3742259531376135e-05, "epoch": 3.072083879423329, "percentage": 30.72, "elapsed_time": "0:19:55", "remaining_time": "0:44:55", "throughput": 2627.13, "total_tokens": 3139672} {"current_steps": 11725, "total_steps": 38150, "loss": 0.249, "lr": 4.373468850578933e-05, "epoch": 3.073394495412844, "percentage": 30.73, "elapsed_time": "0:19:55", "remaining_time": "0:44:54", "throughput": 2627.16, "total_tokens": 3140824} {"current_steps": 11730, "total_steps": 38150, "loss": 0.4372, "lr": 4.37271135590646e-05, "epoch": 3.074705111402359, "percentage": 30.75, "elapsed_time": "0:19:55", "remaining_time": "0:44:53", "throughput": 2627.24, "total_tokens": 3142040} {"current_steps": 11735, "total_steps": 38150, "loss": 0.1898, "lr": 4.371953469278737e-05, "epoch": 3.0760157273918742, "percentage": 30.76, "elapsed_time": "0:19:56", "remaining_time": "0:44:52", "throughput": 2627.19, "total_tokens": 3143080} {"current_steps": 11740, "total_steps": 38150, "loss": 0.3967, "lr": 4.371195190854386e-05, "epoch": 3.0773263433813893, "percentage": 30.77, "elapsed_time": "0:19:56", "remaining_time": "0:44:52", "throughput": 2627.34, "total_tokens": 3144504} {"current_steps": 11745, "total_steps": 38150, "loss": 0.4637, "lr": 4.370436520792115e-05, "epoch": 3.0786369593709044, "percentage": 30.79, "elapsed_time": "0:19:57", "remaining_time": "0:44:51", "throughput": 2627.47, "total_tokens": 3145816} {"current_steps": 11750, "total_steps": 38150, "loss": 0.5318, "lr": 4.369677459250712e-05, "epoch": 3.0799475753604195, "percentage": 30.8, "elapsed_time": "0:19:57", "remaining_time": "0:44:51", "throughput": 2627.79, "total_tokens": 3147528} {"current_steps": 11755, "total_steps": 38150, "loss": 0.526, "lr": 4.3689180063890476e-05, "epoch": 3.0812581913499346, "percentage": 30.81, "elapsed_time": "0:19:58", "remaining_time": "0:44:50", "throughput": 2627.79, "total_tokens": 3148648} {"current_steps": 11760, "total_steps": 38150, "loss": 0.364, "lr": 4.368158162366073e-05, "epoch": 3.0825688073394497, "percentage": 30.83, "elapsed_time": "0:19:58", "remaining_time": "0:44:49", "throughput": 2627.91, "total_tokens": 3149976} {"current_steps": 11765, "total_steps": 38150, "loss": 0.5678, "lr": 4.367397927340824e-05, "epoch": 3.083879423328965, "percentage": 30.84, "elapsed_time": "0:19:59", "remaining_time": "0:44:49", "throughput": 2628.2, "total_tokens": 3151624} {"current_steps": 11770, "total_steps": 38150, "loss": 0.4596, "lr": 4.366637301472415e-05, "epoch": 3.08519003931848, "percentage": 30.85, "elapsed_time": "0:19:59", "remaining_time": "0:44:48", "throughput": 2628.45, "total_tokens": 3153160} {"current_steps": 11775, "total_steps": 38150, "loss": 0.4235, "lr": 4.365876284920044e-05, "epoch": 3.0865006553079946, "percentage": 30.87, "elapsed_time": "0:20:00", "remaining_time": "0:44:48", "throughput": 2628.66, "total_tokens": 3154600} {"current_steps": 11780, "total_steps": 38150, "loss": 0.298, "lr": 4.365114877842991e-05, "epoch": 3.0878112712975097, "percentage": 30.88, "elapsed_time": "0:20:00", "remaining_time": "0:44:47", "throughput": 2628.75, "total_tokens": 3155912} {"current_steps": 11785, "total_steps": 38150, "loss": 0.473, "lr": 4.364353080400616e-05, "epoch": 3.0891218872870247, "percentage": 30.89, "elapsed_time": "0:20:00", "remaining_time": "0:44:46", "throughput": 2628.67, "total_tokens": 3156936} {"current_steps": 11790, "total_steps": 38150, "loss": 0.413, "lr": 4.363590892752363e-05, "epoch": 3.09043250327654, "percentage": 30.9, "elapsed_time": "0:20:01", "remaining_time": "0:44:46", "throughput": 2628.78, "total_tokens": 3158216} {"current_steps": 11795, "total_steps": 38150, "loss": 0.4592, "lr": 4.362828315057756e-05, "epoch": 3.091743119266055, "percentage": 30.92, "elapsed_time": "0:20:01", "remaining_time": "0:44:45", "throughput": 2628.87, "total_tokens": 3159544} {"current_steps": 11800, "total_steps": 38150, "loss": 0.3698, "lr": 4.362065347476401e-05, "epoch": 3.09305373525557, "percentage": 30.93, "elapsed_time": "0:20:02", "remaining_time": "0:44:45", "throughput": 2629.23, "total_tokens": 3161384} {"current_steps": 11805, "total_steps": 38150, "loss": 0.2577, "lr": 4.361301990167988e-05, "epoch": 3.094364351245085, "percentage": 30.94, "elapsed_time": "0:20:02", "remaining_time": "0:44:44", "throughput": 2629.12, "total_tokens": 3162360} {"current_steps": 11810, "total_steps": 38150, "loss": 0.4642, "lr": 4.360538243292282e-05, "epoch": 3.0956749672346002, "percentage": 30.96, "elapsed_time": "0:20:03", "remaining_time": "0:44:43", "throughput": 2629.04, "total_tokens": 3163352} {"current_steps": 11815, "total_steps": 38150, "loss": 0.3416, "lr": 4.359774107009138e-05, "epoch": 3.0969855832241153, "percentage": 30.97, "elapsed_time": "0:20:03", "remaining_time": "0:44:42", "throughput": 2629.13, "total_tokens": 3164648} {"current_steps": 11820, "total_steps": 38150, "loss": 0.3921, "lr": 4.3590095814784866e-05, "epoch": 3.0982961992136304, "percentage": 30.98, "elapsed_time": "0:20:04", "remaining_time": "0:44:42", "throughput": 2629.13, "total_tokens": 3165752} {"current_steps": 11825, "total_steps": 38150, "loss": 0.2985, "lr": 4.3582446668603414e-05, "epoch": 3.0996068152031455, "percentage": 31.0, "elapsed_time": "0:20:04", "remaining_time": "0:44:41", "throughput": 2629.47, "total_tokens": 3167384} {"current_steps": 11830, "total_steps": 38150, "loss": 0.3986, "lr": 4.357479363314799e-05, "epoch": 3.1009174311926606, "percentage": 31.01, "elapsed_time": "0:20:05", "remaining_time": "0:44:41", "throughput": 2629.83, "total_tokens": 3169288} {"current_steps": 11835, "total_steps": 38150, "loss": 0.3172, "lr": 4.356713671002035e-05, "epoch": 3.1022280471821757, "percentage": 31.02, "elapsed_time": "0:20:05", "remaining_time": "0:44:40", "throughput": 2629.74, "total_tokens": 3170264} {"current_steps": 11840, "total_steps": 38150, "loss": 0.3793, "lr": 4.355947590082308e-05, "epoch": 3.103538663171691, "percentage": 31.04, "elapsed_time": "0:20:05", "remaining_time": "0:44:39", "throughput": 2629.78, "total_tokens": 3171448} {"current_steps": 11845, "total_steps": 38150, "loss": 0.4418, "lr": 4.355181120715957e-05, "epoch": 3.104849279161206, "percentage": 31.05, "elapsed_time": "0:20:06", "remaining_time": "0:44:39", "throughput": 2630.06, "total_tokens": 3173016} {"current_steps": 11850, "total_steps": 38150, "loss": 0.3108, "lr": 4.3544142630634024e-05, "epoch": 3.106159895150721, "percentage": 31.06, "elapsed_time": "0:20:06", "remaining_time": "0:44:38", "throughput": 2630.44, "total_tokens": 3174872} {"current_steps": 11855, "total_steps": 38150, "loss": 0.3533, "lr": 4.3536470172851476e-05, "epoch": 3.107470511140236, "percentage": 31.07, "elapsed_time": "0:20:07", "remaining_time": "0:44:38", "throughput": 2630.83, "total_tokens": 3176840} {"current_steps": 11860, "total_steps": 38150, "loss": 0.4659, "lr": 4.352879383541775e-05, "epoch": 3.108781127129751, "percentage": 31.09, "elapsed_time": "0:20:08", "remaining_time": "0:44:37", "throughput": 2630.98, "total_tokens": 3178328} {"current_steps": 11865, "total_steps": 38150, "loss": 0.4544, "lr": 4.352111361993948e-05, "epoch": 3.1100917431192663, "percentage": 31.1, "elapsed_time": "0:20:08", "remaining_time": "0:44:37", "throughput": 2631.13, "total_tokens": 3179672} {"current_steps": 11870, "total_steps": 38150, "loss": 0.4396, "lr": 4.351342952802414e-05, "epoch": 3.111402359108781, "percentage": 31.11, "elapsed_time": "0:20:08", "remaining_time": "0:44:36", "throughput": 2631.31, "total_tokens": 3181128} {"current_steps": 11875, "total_steps": 38150, "loss": 0.2446, "lr": 4.3505741561279984e-05, "epoch": 3.112712975098296, "percentage": 31.13, "elapsed_time": "0:20:09", "remaining_time": "0:44:35", "throughput": 2631.58, "total_tokens": 3182648} {"current_steps": 11880, "total_steps": 38150, "loss": 0.387, "lr": 4.349804972131609e-05, "epoch": 3.114023591087811, "percentage": 31.14, "elapsed_time": "0:20:09", "remaining_time": "0:44:35", "throughput": 2631.87, "total_tokens": 3184312} {"current_steps": 11885, "total_steps": 38150, "loss": 0.5017, "lr": 4.349035400974236e-05, "epoch": 3.1153342070773262, "percentage": 31.15, "elapsed_time": "0:20:10", "remaining_time": "0:44:34", "throughput": 2631.89, "total_tokens": 3185448} {"current_steps": 11890, "total_steps": 38150, "loss": 0.3177, "lr": 4.348265442816949e-05, "epoch": 3.1166448230668413, "percentage": 31.17, "elapsed_time": "0:20:10", "remaining_time": "0:44:34", "throughput": 2632.08, "total_tokens": 3186920} {"current_steps": 11895, "total_steps": 38150, "loss": 0.4904, "lr": 4.347495097820897e-05, "epoch": 3.1179554390563564, "percentage": 31.18, "elapsed_time": "0:20:11", "remaining_time": "0:44:33", "throughput": 2632.38, "total_tokens": 3188568} {"current_steps": 11900, "total_steps": 38150, "loss": 0.3734, "lr": 4.346724366147314e-05, "epoch": 3.1192660550458715, "percentage": 31.19, "elapsed_time": "0:20:11", "remaining_time": "0:44:32", "throughput": 2632.39, "total_tokens": 3189800} {"current_steps": 11905, "total_steps": 38150, "loss": 0.2996, "lr": 4.345953247957512e-05, "epoch": 3.1205766710353866, "percentage": 31.21, "elapsed_time": "0:20:12", "remaining_time": "0:44:32", "throughput": 2632.33, "total_tokens": 3190856} {"current_steps": 11910, "total_steps": 38150, "loss": 0.3528, "lr": 4.345181743412885e-05, "epoch": 3.1218872870249017, "percentage": 31.22, "elapsed_time": "0:20:12", "remaining_time": "0:44:31", "throughput": 2632.59, "total_tokens": 3192552} {"current_steps": 11915, "total_steps": 38150, "loss": 0.4727, "lr": 4.344409852674907e-05, "epoch": 3.123197903014417, "percentage": 31.23, "elapsed_time": "0:20:13", "remaining_time": "0:44:31", "throughput": 2632.59, "total_tokens": 3193672} {"current_steps": 11920, "total_steps": 38150, "loss": 0.3412, "lr": 4.343637575905133e-05, "epoch": 3.124508519003932, "percentage": 31.25, "elapsed_time": "0:20:13", "remaining_time": "0:44:30", "throughput": 2632.55, "total_tokens": 3194760} {"current_steps": 11925, "total_steps": 38150, "loss": 0.2603, "lr": 4.342864913265201e-05, "epoch": 3.125819134993447, "percentage": 31.26, "elapsed_time": "0:20:13", "remaining_time": "0:44:29", "throughput": 2632.49, "total_tokens": 3195768} {"current_steps": 11930, "total_steps": 38150, "loss": 0.4667, "lr": 4.3420918649168265e-05, "epoch": 3.127129750982962, "percentage": 31.27, "elapsed_time": "0:20:14", "remaining_time": "0:44:29", "throughput": 2632.52, "total_tokens": 3196936} {"current_steps": 11935, "total_steps": 38150, "loss": 0.4124, "lr": 4.341318431021808e-05, "epoch": 3.128440366972477, "percentage": 31.28, "elapsed_time": "0:20:14", "remaining_time": "0:44:28", "throughput": 2632.69, "total_tokens": 3198360} {"current_steps": 11940, "total_steps": 38150, "loss": 0.4426, "lr": 4.340544611742023e-05, "epoch": 3.1297509829619923, "percentage": 31.3, "elapsed_time": "0:20:15", "remaining_time": "0:44:27", "throughput": 2632.87, "total_tokens": 3199816} {"current_steps": 11945, "total_steps": 38150, "loss": 0.4121, "lr": 4.339770407239431e-05, "epoch": 3.1310615989515074, "percentage": 31.31, "elapsed_time": "0:20:15", "remaining_time": "0:44:27", "throughput": 2632.77, "total_tokens": 3200808} {"current_steps": 11950, "total_steps": 38150, "loss": 0.5386, "lr": 4.3389958176760714e-05, "epoch": 3.1323722149410225, "percentage": 31.32, "elapsed_time": "0:20:16", "remaining_time": "0:44:26", "throughput": 2633.33, "total_tokens": 3202984} {"current_steps": 11955, "total_steps": 38150, "loss": 0.3013, "lr": 4.3382208432140646e-05, "epoch": 3.133682830930537, "percentage": 31.34, "elapsed_time": "0:20:16", "remaining_time": "0:44:26", "throughput": 2633.46, "total_tokens": 3204296} {"current_steps": 11960, "total_steps": 38150, "loss": 0.371, "lr": 4.337445484015613e-05, "epoch": 3.134993446920052, "percentage": 31.35, "elapsed_time": "0:20:17", "remaining_time": "0:44:25", "throughput": 2633.61, "total_tokens": 3205704} {"current_steps": 11965, "total_steps": 38150, "loss": 0.4403, "lr": 4.3366697402429945e-05, "epoch": 3.1363040629095673, "percentage": 31.36, "elapsed_time": "0:20:17", "remaining_time": "0:44:24", "throughput": 2633.9, "total_tokens": 3207240} {"current_steps": 11970, "total_steps": 38150, "loss": 0.389, "lr": 4.335893612058574e-05, "epoch": 3.1376146788990824, "percentage": 31.38, "elapsed_time": "0:20:18", "remaining_time": "0:44:24", "throughput": 2633.84, "total_tokens": 3208264} {"current_steps": 11975, "total_steps": 38150, "loss": 0.4544, "lr": 4.335117099624792e-05, "epoch": 3.1389252948885975, "percentage": 31.39, "elapsed_time": "0:20:18", "remaining_time": "0:44:23", "throughput": 2633.96, "total_tokens": 3209656} {"current_steps": 11980, "total_steps": 38150, "loss": 0.3482, "lr": 4.3343402031041726e-05, "epoch": 3.1402359108781126, "percentage": 31.4, "elapsed_time": "0:20:18", "remaining_time": "0:44:22", "throughput": 2633.85, "total_tokens": 3210616} {"current_steps": 11985, "total_steps": 38150, "loss": 0.4139, "lr": 4.333562922659318e-05, "epoch": 3.1415465268676277, "percentage": 31.42, "elapsed_time": "0:20:19", "remaining_time": "0:44:22", "throughput": 2633.78, "total_tokens": 3211640} {"current_steps": 11990, "total_steps": 38150, "loss": 0.3847, "lr": 4.332785258452911e-05, "epoch": 3.142857142857143, "percentage": 31.43, "elapsed_time": "0:20:19", "remaining_time": "0:44:21", "throughput": 2633.93, "total_tokens": 3213096} {"current_steps": 11995, "total_steps": 38150, "loss": 0.3989, "lr": 4.332007210647717e-05, "epoch": 3.144167758846658, "percentage": 31.44, "elapsed_time": "0:20:20", "remaining_time": "0:44:20", "throughput": 2633.84, "total_tokens": 3214072} {"current_steps": 12000, "total_steps": 38150, "loss": 0.3849, "lr": 4.3312287794065795e-05, "epoch": 3.145478374836173, "percentage": 31.45, "elapsed_time": "0:20:20", "remaining_time": "0:44:20", "throughput": 2633.94, "total_tokens": 3215416} {"current_steps": 12005, "total_steps": 38150, "loss": 0.2404, "lr": 4.330449964892422e-05, "epoch": 3.146788990825688, "percentage": 31.47, "elapsed_time": "0:20:21", "remaining_time": "0:44:19", "throughput": 2633.99, "total_tokens": 3216680} {"current_steps": 12010, "total_steps": 38150, "loss": 0.4377, "lr": 4.32967076726825e-05, "epoch": 3.148099606815203, "percentage": 31.48, "elapsed_time": "0:20:21", "remaining_time": "0:44:18", "throughput": 2633.92, "total_tokens": 3217704} {"current_steps": 12015, "total_steps": 38150, "loss": 0.5057, "lr": 4.328891186697148e-05, "epoch": 3.1494102228047183, "percentage": 31.49, "elapsed_time": "0:20:22", "remaining_time": "0:44:18", "throughput": 2633.94, "total_tokens": 3218840} {"current_steps": 12020, "total_steps": 38150, "loss": 0.2536, "lr": 4.328111223342281e-05, "epoch": 3.1507208387942334, "percentage": 31.51, "elapsed_time": "0:20:22", "remaining_time": "0:44:17", "throughput": 2634.06, "total_tokens": 3220264} {"current_steps": 12025, "total_steps": 38150, "loss": 0.8794, "lr": 4.327330877366893e-05, "epoch": 3.1520314547837485, "percentage": 31.52, "elapsed_time": "0:20:22", "remaining_time": "0:44:17", "throughput": 2634.06, "total_tokens": 3221416} {"current_steps": 12030, "total_steps": 38150, "loss": 0.5601, "lr": 4.3265501489343094e-05, "epoch": 3.1533420707732636, "percentage": 31.53, "elapsed_time": "0:20:23", "remaining_time": "0:44:16", "throughput": 2634.12, "total_tokens": 3222616} {"current_steps": 12035, "total_steps": 38150, "loss": 0.3504, "lr": 4.325769038207936e-05, "epoch": 3.1546526867627787, "percentage": 31.55, "elapsed_time": "0:20:23", "remaining_time": "0:44:15", "throughput": 2634.05, "total_tokens": 3223624} {"current_steps": 12040, "total_steps": 38150, "loss": 0.3147, "lr": 4.3249875453512586e-05, "epoch": 3.1559633027522938, "percentage": 31.56, "elapsed_time": "0:20:24", "remaining_time": "0:44:15", "throughput": 2634.34, "total_tokens": 3225256} {"current_steps": 12045, "total_steps": 38150, "loss": 0.4685, "lr": 4.32420567052784e-05, "epoch": 3.157273918741809, "percentage": 31.57, "elapsed_time": "0:20:24", "remaining_time": "0:44:14", "throughput": 2634.52, "total_tokens": 3226632} {"current_steps": 12050, "total_steps": 38150, "loss": 0.3407, "lr": 4.323423413901327e-05, "epoch": 3.1585845347313235, "percentage": 31.59, "elapsed_time": "0:20:25", "remaining_time": "0:44:13", "throughput": 2634.54, "total_tokens": 3227768} {"current_steps": 12055, "total_steps": 38150, "loss": 0.3802, "lr": 4.322640775635445e-05, "epoch": 3.1598951507208386, "percentage": 31.6, "elapsed_time": "0:20:25", "remaining_time": "0:44:13", "throughput": 2634.68, "total_tokens": 3229128} {"current_steps": 12060, "total_steps": 38150, "loss": 0.432, "lr": 4.321857755893996e-05, "epoch": 3.1612057667103537, "percentage": 31.61, "elapsed_time": "0:20:26", "remaining_time": "0:44:12", "throughput": 2634.66, "total_tokens": 3230216} {"current_steps": 12065, "total_steps": 38150, "loss": 0.3695, "lr": 4.3210743548408684e-05, "epoch": 3.162516382699869, "percentage": 31.63, "elapsed_time": "0:20:26", "remaining_time": "0:44:11", "throughput": 2634.62, "total_tokens": 3231256} {"current_steps": 12070, "total_steps": 38150, "loss": 0.5679, "lr": 4.3202905726400236e-05, "epoch": 3.163826998689384, "percentage": 31.64, "elapsed_time": "0:20:26", "remaining_time": "0:44:11", "throughput": 2634.86, "total_tokens": 3232808} {"current_steps": 12075, "total_steps": 38150, "loss": 0.3818, "lr": 4.3195064094555085e-05, "epoch": 3.165137614678899, "percentage": 31.65, "elapsed_time": "0:20:27", "remaining_time": "0:44:10", "throughput": 2635.33, "total_tokens": 3234776} {"current_steps": 12080, "total_steps": 38150, "loss": 0.5757, "lr": 4.318721865451445e-05, "epoch": 3.166448230668414, "percentage": 31.66, "elapsed_time": "0:20:27", "remaining_time": "0:44:09", "throughput": 2635.41, "total_tokens": 3236088} {"current_steps": 12085, "total_steps": 38150, "loss": 0.4092, "lr": 4.317936940792037e-05, "epoch": 3.167758846657929, "percentage": 31.68, "elapsed_time": "0:20:28", "remaining_time": "0:44:09", "throughput": 2635.52, "total_tokens": 3237448} {"current_steps": 12090, "total_steps": 38150, "loss": 0.3107, "lr": 4.317151635641569e-05, "epoch": 3.1690694626474443, "percentage": 31.69, "elapsed_time": "0:20:28", "remaining_time": "0:44:08", "throughput": 2635.52, "total_tokens": 3238552} {"current_steps": 12095, "total_steps": 38150, "loss": 0.4435, "lr": 4.316365950164404e-05, "epoch": 3.1703800786369594, "percentage": 31.7, "elapsed_time": "0:20:29", "remaining_time": "0:44:08", "throughput": 2635.54, "total_tokens": 3239704} {"current_steps": 12100, "total_steps": 38150, "loss": 0.4967, "lr": 4.3155798845249827e-05, "epoch": 3.1716906946264745, "percentage": 31.72, "elapsed_time": "0:20:29", "remaining_time": "0:44:07", "throughput": 2635.82, "total_tokens": 3241256} {"current_steps": 12105, "total_steps": 38150, "loss": 0.3817, "lr": 4.3147934388878295e-05, "epoch": 3.1730013106159896, "percentage": 31.73, "elapsed_time": "0:20:30", "remaining_time": "0:44:06", "throughput": 2635.98, "total_tokens": 3242696} {"current_steps": 12110, "total_steps": 38150, "loss": 0.4294, "lr": 4.314006613417546e-05, "epoch": 3.1743119266055047, "percentage": 31.74, "elapsed_time": "0:20:30", "remaining_time": "0:44:06", "throughput": 2636.21, "total_tokens": 3244280} {"current_steps": 12115, "total_steps": 38150, "loss": 0.2806, "lr": 4.3132194082788116e-05, "epoch": 3.1756225425950197, "percentage": 31.76, "elapsed_time": "0:20:31", "remaining_time": "0:44:05", "throughput": 2636.3, "total_tokens": 3245608} {"current_steps": 12120, "total_steps": 38150, "loss": 0.3158, "lr": 4.312431823636388e-05, "epoch": 3.176933158584535, "percentage": 31.77, "elapsed_time": "0:20:31", "remaining_time": "0:44:05", "throughput": 2636.36, "total_tokens": 3246904} {"current_steps": 12125, "total_steps": 38150, "loss": 0.3654, "lr": 4.311643859655116e-05, "epoch": 3.17824377457405, "percentage": 31.78, "elapsed_time": "0:20:32", "remaining_time": "0:44:04", "throughput": 2636.54, "total_tokens": 3248360} {"current_steps": 12130, "total_steps": 38150, "loss": 0.4307, "lr": 4.3108555164999144e-05, "epoch": 3.179554390563565, "percentage": 31.8, "elapsed_time": "0:20:32", "remaining_time": "0:44:03", "throughput": 2636.58, "total_tokens": 3249560} {"current_steps": 12135, "total_steps": 38150, "loss": 0.4303, "lr": 4.310066794335782e-05, "epoch": 3.18086500655308, "percentage": 31.81, "elapsed_time": "0:20:32", "remaining_time": "0:44:03", "throughput": 2636.63, "total_tokens": 3250792} {"current_steps": 12140, "total_steps": 38150, "loss": 0.3017, "lr": 4.309277693327797e-05, "epoch": 3.1821756225425952, "percentage": 31.82, "elapsed_time": "0:20:33", "remaining_time": "0:44:02", "throughput": 2636.76, "total_tokens": 3252120} {"current_steps": 12145, "total_steps": 38150, "loss": 0.2989, "lr": 4.308488213641116e-05, "epoch": 3.18348623853211, "percentage": 31.83, "elapsed_time": "0:20:33", "remaining_time": "0:44:01", "throughput": 2636.86, "total_tokens": 3253432} {"current_steps": 12150, "total_steps": 38150, "loss": 0.3667, "lr": 4.3076983554409784e-05, "epoch": 3.184796854521625, "percentage": 31.85, "elapsed_time": "0:20:34", "remaining_time": "0:44:01", "throughput": 2636.89, "total_tokens": 3254600} {"current_steps": 12155, "total_steps": 38150, "loss": 0.4297, "lr": 4.306908118892698e-05, "epoch": 3.18610747051114, "percentage": 31.86, "elapsed_time": "0:20:34", "remaining_time": "0:44:00", "throughput": 2636.89, "total_tokens": 3255704} {"current_steps": 12160, "total_steps": 38150, "loss": 0.3356, "lr": 4.30611750416167e-05, "epoch": 3.187418086500655, "percentage": 31.87, "elapsed_time": "0:20:35", "remaining_time": "0:43:59", "throughput": 2636.96, "total_tokens": 3256904} {"current_steps": 12165, "total_steps": 38150, "loss": 0.2908, "lr": 4.305326511413369e-05, "epoch": 3.1887287024901703, "percentage": 31.89, "elapsed_time": "0:20:35", "remaining_time": "0:43:59", "throughput": 2637.08, "total_tokens": 3258184} {"current_steps": 12170, "total_steps": 38150, "loss": 0.4185, "lr": 4.304535140813349e-05, "epoch": 3.1900393184796854, "percentage": 31.9, "elapsed_time": "0:20:35", "remaining_time": "0:43:58", "throughput": 2637.15, "total_tokens": 3259432} {"current_steps": 12175, "total_steps": 38150, "loss": 0.4594, "lr": 4.303743392527242e-05, "epoch": 3.1913499344692005, "percentage": 31.91, "elapsed_time": "0:20:36", "remaining_time": "0:43:57", "throughput": 2637.2, "total_tokens": 3260616} {"current_steps": 12180, "total_steps": 38150, "loss": 0.534, "lr": 4.302951266720759e-05, "epoch": 3.1926605504587156, "percentage": 31.93, "elapsed_time": "0:20:36", "remaining_time": "0:43:57", "throughput": 2637.46, "total_tokens": 3262200} {"current_steps": 12185, "total_steps": 38150, "loss": 0.3532, "lr": 4.3021587635596914e-05, "epoch": 3.1939711664482306, "percentage": 31.94, "elapsed_time": "0:20:37", "remaining_time": "0:43:56", "throughput": 2637.82, "total_tokens": 3264136} {"current_steps": 12190, "total_steps": 38150, "loss": 0.5683, "lr": 4.301365883209909e-05, "epoch": 3.1952817824377457, "percentage": 31.95, "elapsed_time": "0:20:37", "remaining_time": "0:43:56", "throughput": 2637.73, "total_tokens": 3265112} {"current_steps": 12195, "total_steps": 38150, "loss": 0.4884, "lr": 4.300572625837359e-05, "epoch": 3.196592398427261, "percentage": 31.97, "elapsed_time": "0:20:38", "remaining_time": "0:43:56", "throughput": 2638.59, "total_tokens": 3268472} {"current_steps": 12200, "total_steps": 38150, "loss": 0.5123, "lr": 4.29977899160807e-05, "epoch": 3.197903014416776, "percentage": 31.98, "elapsed_time": "0:20:39", "remaining_time": "0:43:55", "throughput": 2638.89, "total_tokens": 3270168} {"current_steps": 12205, "total_steps": 38150, "loss": 0.304, "lr": 4.298984980688148e-05, "epoch": 3.199213630406291, "percentage": 31.99, "elapsed_time": "0:20:39", "remaining_time": "0:43:55", "throughput": 2639.21, "total_tokens": 3271752} {"current_steps": 12210, "total_steps": 38150, "loss": 0.3346, "lr": 4.298190593243778e-05, "epoch": 3.200524246395806, "percentage": 32.01, "elapsed_time": "0:20:40", "remaining_time": "0:43:54", "throughput": 2639.21, "total_tokens": 3272888} {"current_steps": 12215, "total_steps": 38150, "loss": 0.528, "lr": 4.297395829441223e-05, "epoch": 3.2018348623853212, "percentage": 32.02, "elapsed_time": "0:20:40", "remaining_time": "0:43:53", "throughput": 2639.18, "total_tokens": 3273960} {"current_steps": 12220, "total_steps": 38150, "loss": 0.478, "lr": 4.2966006894468274e-05, "epoch": 3.2031454783748363, "percentage": 32.03, "elapsed_time": "0:20:40", "remaining_time": "0:43:53", "throughput": 2639.29, "total_tokens": 3275240} {"current_steps": 12225, "total_steps": 38150, "loss": 0.3644, "lr": 4.295805173427012e-05, "epoch": 3.2044560943643514, "percentage": 32.04, "elapsed_time": "0:20:41", "remaining_time": "0:43:52", "throughput": 2639.64, "total_tokens": 3277096} {"current_steps": 12230, "total_steps": 38150, "loss": 0.3813, "lr": 4.295009281548276e-05, "epoch": 3.2057667103538665, "percentage": 32.06, "elapsed_time": "0:20:42", "remaining_time": "0:43:52", "throughput": 2639.89, "total_tokens": 3278744} {"current_steps": 12235, "total_steps": 38150, "loss": 0.337, "lr": 4.294213013977199e-05, "epoch": 3.2070773263433816, "percentage": 32.07, "elapsed_time": "0:20:42", "remaining_time": "0:43:51", "throughput": 2640.3, "total_tokens": 3280616} {"current_steps": 12240, "total_steps": 38150, "loss": 0.4558, "lr": 4.2934163708804385e-05, "epoch": 3.2083879423328963, "percentage": 32.08, "elapsed_time": "0:20:42", "remaining_time": "0:43:51", "throughput": 2640.44, "total_tokens": 3282008} {"current_steps": 12245, "total_steps": 38150, "loss": 0.4207, "lr": 4.29261935242473e-05, "epoch": 3.2096985583224114, "percentage": 32.1, "elapsed_time": "0:20:43", "remaining_time": "0:43:50", "throughput": 2640.55, "total_tokens": 3283288} {"current_steps": 12250, "total_steps": 38150, "loss": 0.3631, "lr": 4.291821958776889e-05, "epoch": 3.2110091743119265, "percentage": 32.11, "elapsed_time": "0:20:43", "remaining_time": "0:43:49", "throughput": 2640.74, "total_tokens": 3284696} {"current_steps": 12255, "total_steps": 38150, "loss": 0.4117, "lr": 4.291024190103808e-05, "epoch": 3.2123197903014415, "percentage": 32.12, "elapsed_time": "0:20:44", "remaining_time": "0:43:49", "throughput": 2640.77, "total_tokens": 3285880} {"current_steps": 12260, "total_steps": 38150, "loss": 0.5161, "lr": 4.290226046572459e-05, "epoch": 3.2136304062909566, "percentage": 32.14, "elapsed_time": "0:20:44", "remaining_time": "0:43:48", "throughput": 2640.84, "total_tokens": 3287112} {"current_steps": 12265, "total_steps": 38150, "loss": 0.4489, "lr": 4.289427528349891e-05, "epoch": 3.2149410222804717, "percentage": 32.15, "elapsed_time": "0:20:45", "remaining_time": "0:43:48", "throughput": 2641.11, "total_tokens": 3288792} {"current_steps": 12270, "total_steps": 38150, "loss": 0.3408, "lr": 4.2886286356032334e-05, "epoch": 3.216251638269987, "percentage": 32.16, "elapsed_time": "0:20:45", "remaining_time": "0:43:47", "throughput": 2641.18, "total_tokens": 3290104} {"current_steps": 12275, "total_steps": 38150, "loss": 0.4164, "lr": 4.287829368499693e-05, "epoch": 3.217562254259502, "percentage": 32.18, "elapsed_time": "0:20:46", "remaining_time": "0:43:46", "throughput": 2641.24, "total_tokens": 3291304} {"current_steps": 12280, "total_steps": 38150, "loss": 0.4914, "lr": 4.2870297272065546e-05, "epoch": 3.218872870249017, "percentage": 32.19, "elapsed_time": "0:20:46", "remaining_time": "0:43:46", "throughput": 2641.31, "total_tokens": 3292600} {"current_steps": 12285, "total_steps": 38150, "loss": 0.5052, "lr": 4.286229711891182e-05, "epoch": 3.220183486238532, "percentage": 32.2, "elapsed_time": "0:20:46", "remaining_time": "0:43:45", "throughput": 2641.28, "total_tokens": 3293672} {"current_steps": 12290, "total_steps": 38150, "loss": 0.4786, "lr": 4.285429322721017e-05, "epoch": 3.221494102228047, "percentage": 32.21, "elapsed_time": "0:20:47", "remaining_time": "0:43:44", "throughput": 2641.49, "total_tokens": 3295192} {"current_steps": 12295, "total_steps": 38150, "loss": 0.3945, "lr": 4.284628559863581e-05, "epoch": 3.2228047182175623, "percentage": 32.23, "elapsed_time": "0:20:47", "remaining_time": "0:43:44", "throughput": 2641.44, "total_tokens": 3296216} {"current_steps": 12300, "total_steps": 38150, "loss": 0.457, "lr": 4.2838274234864694e-05, "epoch": 3.2241153342070774, "percentage": 32.24, "elapsed_time": "0:20:48", "remaining_time": "0:43:43", "throughput": 2641.51, "total_tokens": 3297464} {"current_steps": 12305, "total_steps": 38150, "loss": 0.5819, "lr": 4.283025913757361e-05, "epoch": 3.2254259501965925, "percentage": 32.25, "elapsed_time": "0:20:48", "remaining_time": "0:43:42", "throughput": 2641.61, "total_tokens": 3298744} {"current_steps": 12310, "total_steps": 38150, "loss": 0.2139, "lr": 4.2822240308440096e-05, "epoch": 3.2267365661861076, "percentage": 32.27, "elapsed_time": "0:20:49", "remaining_time": "0:43:42", "throughput": 2641.58, "total_tokens": 3299848} {"current_steps": 12315, "total_steps": 38150, "loss": 0.2597, "lr": 4.281421774914248e-05, "epoch": 3.2280471821756227, "percentage": 32.28, "elapsed_time": "0:20:49", "remaining_time": "0:43:41", "throughput": 2641.83, "total_tokens": 3301432} {"current_steps": 12320, "total_steps": 38150, "loss": 0.471, "lr": 4.280619146135988e-05, "epoch": 3.229357798165138, "percentage": 32.29, "elapsed_time": "0:20:50", "remaining_time": "0:43:41", "throughput": 2642.14, "total_tokens": 3303176} {"current_steps": 12325, "total_steps": 38150, "loss": 0.4342, "lr": 4.2798161446772156e-05, "epoch": 3.230668414154653, "percentage": 32.31, "elapsed_time": "0:20:50", "remaining_time": "0:43:40", "throughput": 2642.45, "total_tokens": 3304824} {"current_steps": 12330, "total_steps": 38150, "loss": 0.3074, "lr": 4.279012770706e-05, "epoch": 3.231979030144168, "percentage": 32.32, "elapsed_time": "0:20:51", "remaining_time": "0:43:39", "throughput": 2642.63, "total_tokens": 3306312} {"current_steps": 12335, "total_steps": 38150, "loss": 0.4195, "lr": 4.278209024390486e-05, "epoch": 3.2332896461336826, "percentage": 32.33, "elapsed_time": "0:20:51", "remaining_time": "0:43:39", "throughput": 2642.86, "total_tokens": 3307864} {"current_steps": 12340, "total_steps": 38150, "loss": 0.4659, "lr": 4.2774049058988955e-05, "epoch": 3.2346002621231977, "percentage": 32.35, "elapsed_time": "0:20:52", "remaining_time": "0:43:38", "throughput": 2643.02, "total_tokens": 3309304} {"current_steps": 12345, "total_steps": 38150, "loss": 0.3406, "lr": 4.276600415399529e-05, "epoch": 3.235910878112713, "percentage": 32.36, "elapsed_time": "0:20:52", "remaining_time": "0:43:38", "throughput": 2643.11, "total_tokens": 3310568} {"current_steps": 12350, "total_steps": 38150, "loss": 0.3521, "lr": 4.275795553060765e-05, "epoch": 3.237221494102228, "percentage": 32.37, "elapsed_time": "0:20:52", "remaining_time": "0:43:37", "throughput": 2643.29, "total_tokens": 3312024} {"current_steps": 12355, "total_steps": 38150, "loss": 0.4076, "lr": 4.274990319051061e-05, "epoch": 3.238532110091743, "percentage": 32.39, "elapsed_time": "0:20:53", "remaining_time": "0:43:36", "throughput": 2643.37, "total_tokens": 3313336} {"current_steps": 12360, "total_steps": 38150, "loss": 0.5152, "lr": 4.2741847135389495e-05, "epoch": 3.239842726081258, "percentage": 32.4, "elapsed_time": "0:20:53", "remaining_time": "0:43:36", "throughput": 2643.45, "total_tokens": 3314616} {"current_steps": 12365, "total_steps": 38150, "loss": 0.4068, "lr": 4.2733787366930436e-05, "epoch": 3.241153342070773, "percentage": 32.41, "elapsed_time": "0:20:54", "remaining_time": "0:43:35", "throughput": 2643.55, "total_tokens": 3315864} {"current_steps": 12370, "total_steps": 38150, "loss": 0.5671, "lr": 4.2725723886820314e-05, "epoch": 3.2424639580602883, "percentage": 32.42, "elapsed_time": "0:20:54", "remaining_time": "0:43:35", "throughput": 2643.59, "total_tokens": 3317144} {"current_steps": 12375, "total_steps": 38150, "loss": 0.3519, "lr": 4.271765669674682e-05, "epoch": 3.2437745740498034, "percentage": 32.44, "elapsed_time": "0:20:55", "remaining_time": "0:43:34", "throughput": 2643.85, "total_tokens": 3318728} {"current_steps": 12380, "total_steps": 38150, "loss": 0.3144, "lr": 4.270958579839839e-05, "epoch": 3.2450851900393185, "percentage": 32.45, "elapsed_time": "0:20:55", "remaining_time": "0:43:33", "throughput": 2643.91, "total_tokens": 3320008} {"current_steps": 12385, "total_steps": 38150, "loss": 0.4802, "lr": 4.270151119346424e-05, "epoch": 3.2463958060288336, "percentage": 32.46, "elapsed_time": "0:20:56", "remaining_time": "0:43:33", "throughput": 2644.15, "total_tokens": 3321496} {"current_steps": 12390, "total_steps": 38150, "loss": 0.4705, "lr": 4.26934328836344e-05, "epoch": 3.2477064220183487, "percentage": 32.48, "elapsed_time": "0:20:56", "remaining_time": "0:43:32", "throughput": 2644.17, "total_tokens": 3322632} {"current_steps": 12395, "total_steps": 38150, "loss": 0.2731, "lr": 4.268535087059962e-05, "epoch": 3.249017038007864, "percentage": 32.49, "elapsed_time": "0:20:57", "remaining_time": "0:43:31", "throughput": 2644.39, "total_tokens": 3324168} {"current_steps": 12400, "total_steps": 38150, "loss": 0.3962, "lr": 4.267726515605146e-05, "epoch": 3.250327653997379, "percentage": 32.5, "elapsed_time": "0:20:57", "remaining_time": "0:43:31", "throughput": 2644.59, "total_tokens": 3325592} {"current_steps": 12405, "total_steps": 38150, "loss": 0.3931, "lr": 4.2669175741682255e-05, "epoch": 3.251638269986894, "percentage": 32.52, "elapsed_time": "0:20:57", "remaining_time": "0:43:30", "throughput": 2644.67, "total_tokens": 3326920} {"current_steps": 12410, "total_steps": 38150, "loss": 0.3757, "lr": 4.266108262918509e-05, "epoch": 3.252948885976409, "percentage": 32.53, "elapsed_time": "0:20:58", "remaining_time": "0:43:30", "throughput": 2644.59, "total_tokens": 3327912} {"current_steps": 12415, "total_steps": 38150, "loss": 0.6686, "lr": 4.265298582025385e-05, "epoch": 3.254259501965924, "percentage": 32.54, "elapsed_time": "0:20:58", "remaining_time": "0:43:29", "throughput": 2644.76, "total_tokens": 3329352} {"current_steps": 12420, "total_steps": 38150, "loss": 0.4976, "lr": 4.264488531658317e-05, "epoch": 3.255570117955439, "percentage": 32.56, "elapsed_time": "0:20:59", "remaining_time": "0:43:28", "throughput": 2644.68, "total_tokens": 3330456} {"current_steps": 12425, "total_steps": 38150, "loss": 0.3666, "lr": 4.26367811198685e-05, "epoch": 3.2568807339449544, "percentage": 32.57, "elapsed_time": "0:20:59", "remaining_time": "0:43:28", "throughput": 2644.76, "total_tokens": 3331752} {"current_steps": 12430, "total_steps": 38150, "loss": 0.4355, "lr": 4.2628673231806e-05, "epoch": 3.258191349934469, "percentage": 32.58, "elapsed_time": "0:21:00", "remaining_time": "0:43:27", "throughput": 2644.89, "total_tokens": 3333128} {"current_steps": 12435, "total_steps": 38150, "loss": 0.402, "lr": 4.262056165409266e-05, "epoch": 3.259501965923984, "percentage": 32.6, "elapsed_time": "0:21:00", "remaining_time": "0:43:26", "throughput": 2644.84, "total_tokens": 3334200} {"current_steps": 12440, "total_steps": 38150, "loss": 0.2202, "lr": 4.261244638842621e-05, "epoch": 3.260812581913499, "percentage": 32.61, "elapsed_time": "0:21:01", "remaining_time": "0:43:26", "throughput": 2644.96, "total_tokens": 3335496} {"current_steps": 12445, "total_steps": 38150, "loss": 0.6634, "lr": 4.260432743650516e-05, "epoch": 3.2621231979030143, "percentage": 32.62, "elapsed_time": "0:21:01", "remaining_time": "0:43:25", "throughput": 2644.85, "total_tokens": 3336488} {"current_steps": 12450, "total_steps": 38150, "loss": 0.4814, "lr": 4.25962048000288e-05, "epoch": 3.2634338138925294, "percentage": 32.63, "elapsed_time": "0:21:01", "remaining_time": "0:43:24", "throughput": 2645.01, "total_tokens": 3337832} {"current_steps": 12455, "total_steps": 38150, "loss": 0.5547, "lr": 4.258807848069718e-05, "epoch": 3.2647444298820445, "percentage": 32.65, "elapsed_time": "0:21:02", "remaining_time": "0:43:24", "throughput": 2645.23, "total_tokens": 3339384} {"current_steps": 12460, "total_steps": 38150, "loss": 0.5006, "lr": 4.257994848021112e-05, "epoch": 3.2660550458715596, "percentage": 32.66, "elapsed_time": "0:21:02", "remaining_time": "0:43:23", "throughput": 2645.46, "total_tokens": 3340904} {"current_steps": 12465, "total_steps": 38150, "loss": 0.5016, "lr": 4.257181480027222e-05, "epoch": 3.2673656618610747, "percentage": 32.67, "elapsed_time": "0:21:03", "remaining_time": "0:43:23", "throughput": 2645.59, "total_tokens": 3342296} {"current_steps": 12470, "total_steps": 38150, "loss": 0.7109, "lr": 4.256367744258285e-05, "epoch": 3.26867627785059, "percentage": 32.69, "elapsed_time": "0:21:03", "remaining_time": "0:43:22", "throughput": 2645.51, "total_tokens": 3343336} {"current_steps": 12475, "total_steps": 38150, "loss": 0.2901, "lr": 4.255553640884613e-05, "epoch": 3.269986893840105, "percentage": 32.7, "elapsed_time": "0:21:04", "remaining_time": "0:43:21", "throughput": 2645.51, "total_tokens": 3344472} {"current_steps": 12480, "total_steps": 38150, "loss": 0.3933, "lr": 4.254739170076597e-05, "epoch": 3.27129750982962, "percentage": 32.71, "elapsed_time": "0:21:04", "remaining_time": "0:43:21", "throughput": 2645.6, "total_tokens": 3345720} {"current_steps": 12485, "total_steps": 38150, "loss": 0.4161, "lr": 4.253924332004706e-05, "epoch": 3.272608125819135, "percentage": 32.73, "elapsed_time": "0:21:05", "remaining_time": "0:43:20", "throughput": 2645.66, "total_tokens": 3346920} {"current_steps": 12490, "total_steps": 38150, "loss": 0.3644, "lr": 4.2531091268394816e-05, "epoch": 3.27391874180865, "percentage": 32.74, "elapsed_time": "0:21:05", "remaining_time": "0:43:19", "throughput": 2645.74, "total_tokens": 3348232} {"current_steps": 12495, "total_steps": 38150, "loss": 0.3619, "lr": 4.252293554751547e-05, "epoch": 3.2752293577981653, "percentage": 32.75, "elapsed_time": "0:21:05", "remaining_time": "0:43:19", "throughput": 2645.74, "total_tokens": 3349400} {"current_steps": 12500, "total_steps": 38150, "loss": 0.5961, "lr": 4.251477615911599e-05, "epoch": 3.2765399737876804, "percentage": 32.77, "elapsed_time": "0:21:06", "remaining_time": "0:43:18", "throughput": 2645.76, "total_tokens": 3350552} {"current_steps": 12505, "total_steps": 38150, "loss": 0.3668, "lr": 4.250661310490412e-05, "epoch": 3.2778505897771955, "percentage": 32.78, "elapsed_time": "0:21:06", "remaining_time": "0:43:17", "throughput": 2645.86, "total_tokens": 3351832} {"current_steps": 12510, "total_steps": 38150, "loss": 0.2603, "lr": 4.249844638658838e-05, "epoch": 3.2791612057667106, "percentage": 32.79, "elapsed_time": "0:21:07", "remaining_time": "0:43:17", "throughput": 2646.21, "total_tokens": 3353512} {"current_steps": 12515, "total_steps": 38150, "loss": 0.3586, "lr": 4.249027600587804e-05, "epoch": 3.280471821756225, "percentage": 32.8, "elapsed_time": "0:21:07", "remaining_time": "0:43:16", "throughput": 2646.29, "total_tokens": 3354744} {"current_steps": 12520, "total_steps": 38150, "loss": 0.314, "lr": 4.248210196448316e-05, "epoch": 3.2817824377457407, "percentage": 32.82, "elapsed_time": "0:21:08", "remaining_time": "0:43:16", "throughput": 2646.36, "total_tokens": 3355960} {"current_steps": 12525, "total_steps": 38150, "loss": 0.4184, "lr": 4.247392426411454e-05, "epoch": 3.2830930537352554, "percentage": 32.83, "elapsed_time": "0:21:08", "remaining_time": "0:43:15", "throughput": 2646.26, "total_tokens": 3356952} {"current_steps": 12530, "total_steps": 38150, "loss": 0.4711, "lr": 4.246574290648376e-05, "epoch": 3.2844036697247705, "percentage": 32.84, "elapsed_time": "0:21:09", "remaining_time": "0:43:14", "throughput": 2646.42, "total_tokens": 3358312} {"current_steps": 12535, "total_steps": 38150, "loss": 0.4218, "lr": 4.245755789330318e-05, "epoch": 3.2857142857142856, "percentage": 32.86, "elapsed_time": "0:21:09", "remaining_time": "0:43:14", "throughput": 2646.63, "total_tokens": 3359912} {"current_steps": 12540, "total_steps": 38150, "loss": 0.4437, "lr": 4.2449369226285884e-05, "epoch": 3.2870249017038007, "percentage": 32.87, "elapsed_time": "0:21:09", "remaining_time": "0:43:13", "throughput": 2646.56, "total_tokens": 3360920} {"current_steps": 12545, "total_steps": 38150, "loss": 0.3594, "lr": 4.2441176907145775e-05, "epoch": 3.288335517693316, "percentage": 32.88, "elapsed_time": "0:21:10", "remaining_time": "0:43:12", "throughput": 2646.6, "total_tokens": 3362104} {"current_steps": 12550, "total_steps": 38150, "loss": 0.3186, "lr": 4.243298093759746e-05, "epoch": 3.289646133682831, "percentage": 32.9, "elapsed_time": "0:21:10", "remaining_time": "0:43:12", "throughput": 2646.62, "total_tokens": 3363288} {"current_steps": 12555, "total_steps": 38150, "loss": 0.3898, "lr": 4.242478131935637e-05, "epoch": 3.290956749672346, "percentage": 32.91, "elapsed_time": "0:21:11", "remaining_time": "0:43:11", "throughput": 2646.63, "total_tokens": 3364424} {"current_steps": 12560, "total_steps": 38150, "loss": 0.4653, "lr": 4.241657805413865e-05, "epoch": 3.292267365661861, "percentage": 32.92, "elapsed_time": "0:21:11", "remaining_time": "0:43:10", "throughput": 2646.75, "total_tokens": 3365736} {"current_steps": 12565, "total_steps": 38150, "loss": 0.3838, "lr": 4.240837114366123e-05, "epoch": 3.293577981651376, "percentage": 32.94, "elapsed_time": "0:21:12", "remaining_time": "0:43:10", "throughput": 2646.82, "total_tokens": 3366968} {"current_steps": 12570, "total_steps": 38150, "loss": 0.3126, "lr": 4.2400160589641825e-05, "epoch": 3.2948885976408913, "percentage": 32.95, "elapsed_time": "0:21:12", "remaining_time": "0:43:09", "throughput": 2646.89, "total_tokens": 3368216} {"current_steps": 12575, "total_steps": 38150, "loss": 0.4153, "lr": 4.239194639379887e-05, "epoch": 3.2961992136304064, "percentage": 32.96, "elapsed_time": "0:21:12", "remaining_time": "0:43:08", "throughput": 2646.97, "total_tokens": 3369464} {"current_steps": 12580, "total_steps": 38150, "loss": 0.395, "lr": 4.238372855785158e-05, "epoch": 3.2975098296199215, "percentage": 32.98, "elapsed_time": "0:21:13", "remaining_time": "0:43:08", "throughput": 2646.97, "total_tokens": 3370584} {"current_steps": 12585, "total_steps": 38150, "loss": 0.4322, "lr": 4.2375507083519936e-05, "epoch": 3.2988204456094365, "percentage": 32.99, "elapsed_time": "0:21:13", "remaining_time": "0:43:07", "throughput": 2647.06, "total_tokens": 3371848} {"current_steps": 12590, "total_steps": 38150, "loss": 0.4081, "lr": 4.2367281972524685e-05, "epoch": 3.3001310615989516, "percentage": 33.0, "elapsed_time": "0:21:14", "remaining_time": "0:43:07", "throughput": 2647.11, "total_tokens": 3373128} {"current_steps": 12595, "total_steps": 38150, "loss": 0.447, "lr": 4.235905322658733e-05, "epoch": 3.3014416775884667, "percentage": 33.01, "elapsed_time": "0:21:14", "remaining_time": "0:43:06", "throughput": 2647.13, "total_tokens": 3374296} {"current_steps": 12600, "total_steps": 38150, "loss": 0.2892, "lr": 4.235082084743013e-05, "epoch": 3.302752293577982, "percentage": 33.03, "elapsed_time": "0:21:15", "remaining_time": "0:43:05", "throughput": 2647.25, "total_tokens": 3375592} {"current_steps": 12605, "total_steps": 38150, "loss": 0.394, "lr": 4.23425848367761e-05, "epoch": 3.304062909567497, "percentage": 33.04, "elapsed_time": "0:21:15", "remaining_time": "0:43:05", "throughput": 2647.59, "total_tokens": 3377336} {"current_steps": 12610, "total_steps": 38150, "loss": 0.4431, "lr": 4.2334345196349036e-05, "epoch": 3.3053735255570116, "percentage": 33.05, "elapsed_time": "0:21:16", "remaining_time": "0:43:04", "throughput": 2647.59, "total_tokens": 3378440} {"current_steps": 12615, "total_steps": 38150, "loss": 0.4397, "lr": 4.2326101927873464e-05, "epoch": 3.3066841415465267, "percentage": 33.07, "elapsed_time": "0:21:16", "remaining_time": "0:43:03", "throughput": 2647.81, "total_tokens": 3380088} {"current_steps": 12620, "total_steps": 38150, "loss": 0.5059, "lr": 4.2317855033074706e-05, "epoch": 3.3079947575360418, "percentage": 33.08, "elapsed_time": "0:21:17", "remaining_time": "0:43:03", "throughput": 2647.76, "total_tokens": 3381208} {"current_steps": 12625, "total_steps": 38150, "loss": 0.5732, "lr": 4.2309604513678804e-05, "epoch": 3.309305373525557, "percentage": 33.09, "elapsed_time": "0:21:17", "remaining_time": "0:43:02", "throughput": 2647.87, "total_tokens": 3382568} {"current_steps": 12630, "total_steps": 38150, "loss": 0.7269, "lr": 4.230135037141259e-05, "epoch": 3.310615989515072, "percentage": 33.11, "elapsed_time": "0:21:17", "remaining_time": "0:43:02", "throughput": 2647.91, "total_tokens": 3383768} {"current_steps": 12635, "total_steps": 38150, "loss": 0.2816, "lr": 4.229309260800364e-05, "epoch": 3.311926605504587, "percentage": 33.12, "elapsed_time": "0:21:18", "remaining_time": "0:43:01", "throughput": 2647.79, "total_tokens": 3384712} {"current_steps": 12640, "total_steps": 38150, "loss": 0.4728, "lr": 4.228483122518029e-05, "epoch": 3.313237221494102, "percentage": 33.13, "elapsed_time": "0:21:18", "remaining_time": "0:43:00", "throughput": 2647.88, "total_tokens": 3386040} {"current_steps": 12645, "total_steps": 38150, "loss": 0.385, "lr": 4.227656622467162e-05, "epoch": 3.3145478374836173, "percentage": 33.15, "elapsed_time": "0:21:19", "remaining_time": "0:43:00", "throughput": 2647.91, "total_tokens": 3387208} {"current_steps": 12650, "total_steps": 38150, "loss": 0.4637, "lr": 4.2268297608207496e-05, "epoch": 3.3158584534731324, "percentage": 33.16, "elapsed_time": "0:21:19", "remaining_time": "0:42:59", "throughput": 2647.96, "total_tokens": 3388408} {"current_steps": 12655, "total_steps": 38150, "loss": 0.4633, "lr": 4.226002537751852e-05, "epoch": 3.3171690694626474, "percentage": 33.17, "elapsed_time": "0:21:20", "remaining_time": "0:42:58", "throughput": 2647.92, "total_tokens": 3389448} {"current_steps": 12660, "total_steps": 38150, "loss": 0.4246, "lr": 4.225174953433605e-05, "epoch": 3.3184796854521625, "percentage": 33.18, "elapsed_time": "0:21:20", "remaining_time": "0:42:58", "throughput": 2647.9, "total_tokens": 3390568} {"current_steps": 12665, "total_steps": 38150, "loss": 0.3323, "lr": 4.224347008039222e-05, "epoch": 3.3197903014416776, "percentage": 33.2, "elapsed_time": "0:21:20", "remaining_time": "0:42:57", "throughput": 2647.96, "total_tokens": 3391768} {"current_steps": 12670, "total_steps": 38150, "loss": 0.4181, "lr": 4.22351870174199e-05, "epoch": 3.3211009174311927, "percentage": 33.21, "elapsed_time": "0:21:21", "remaining_time": "0:42:56", "throughput": 2648.15, "total_tokens": 3393208} {"current_steps": 12675, "total_steps": 38150, "loss": 0.2595, "lr": 4.222690034715271e-05, "epoch": 3.322411533420708, "percentage": 33.22, "elapsed_time": "0:21:21", "remaining_time": "0:42:56", "throughput": 2648.09, "total_tokens": 3394248} {"current_steps": 12680, "total_steps": 38150, "loss": 0.4584, "lr": 4.2218610071325036e-05, "epoch": 3.323722149410223, "percentage": 33.24, "elapsed_time": "0:21:22", "remaining_time": "0:42:55", "throughput": 2648.52, "total_tokens": 3396232} {"current_steps": 12685, "total_steps": 38150, "loss": 0.3484, "lr": 4.221031619167204e-05, "epoch": 3.325032765399738, "percentage": 33.25, "elapsed_time": "0:21:22", "remaining_time": "0:42:55", "throughput": 2648.59, "total_tokens": 3397432} {"current_steps": 12690, "total_steps": 38150, "loss": 0.3366, "lr": 4.2202018709929595e-05, "epoch": 3.326343381389253, "percentage": 33.26, "elapsed_time": "0:21:23", "remaining_time": "0:42:54", "throughput": 2648.71, "total_tokens": 3398760} {"current_steps": 12695, "total_steps": 38150, "loss": 0.5251, "lr": 4.219371762783436e-05, "epoch": 3.327653997378768, "percentage": 33.28, "elapsed_time": "0:21:23", "remaining_time": "0:42:53", "throughput": 2648.68, "total_tokens": 3399848} {"current_steps": 12700, "total_steps": 38150, "loss": 0.4646, "lr": 4.218541294712373e-05, "epoch": 3.3289646133682833, "percentage": 33.29, "elapsed_time": "0:21:24", "remaining_time": "0:42:53", "throughput": 2648.81, "total_tokens": 3401240} {"current_steps": 12705, "total_steps": 38150, "loss": 1.0467, "lr": 4.217710466953586e-05, "epoch": 3.330275229357798, "percentage": 33.3, "elapsed_time": "0:21:24", "remaining_time": "0:42:52", "throughput": 2649.04, "total_tokens": 3402920} {"current_steps": 12710, "total_steps": 38150, "loss": 0.3714, "lr": 4.2168792796809674e-05, "epoch": 3.331585845347313, "percentage": 33.32, "elapsed_time": "0:21:25", "remaining_time": "0:42:52", "throughput": 2649.09, "total_tokens": 3404184} {"current_steps": 12715, "total_steps": 38150, "loss": 0.3518, "lr": 4.216047733068481e-05, "epoch": 3.332896461336828, "percentage": 33.33, "elapsed_time": "0:21:25", "remaining_time": "0:42:51", "throughput": 2649.25, "total_tokens": 3405576} {"current_steps": 12720, "total_steps": 38150, "loss": 0.4728, "lr": 4.21521582729017e-05, "epoch": 3.3342070773263432, "percentage": 33.34, "elapsed_time": "0:21:25", "remaining_time": "0:42:50", "throughput": 2649.27, "total_tokens": 3406712} {"current_steps": 12725, "total_steps": 38150, "loss": 0.4884, "lr": 4.21438356252015e-05, "epoch": 3.3355176933158583, "percentage": 33.36, "elapsed_time": "0:21:26", "remaining_time": "0:42:50", "throughput": 2649.33, "total_tokens": 3407928} {"current_steps": 12730, "total_steps": 38150, "loss": 0.5323, "lr": 4.213550938932612e-05, "epoch": 3.3368283093053734, "percentage": 33.37, "elapsed_time": "0:21:26", "remaining_time": "0:42:49", "throughput": 2649.46, "total_tokens": 3409272} {"current_steps": 12735, "total_steps": 38150, "loss": 0.3373, "lr": 4.2127179567018235e-05, "epoch": 3.3381389252948885, "percentage": 33.38, "elapsed_time": "0:21:27", "remaining_time": "0:42:48", "throughput": 2649.56, "total_tokens": 3410568} {"current_steps": 12740, "total_steps": 38150, "loss": 0.3495, "lr": 4.211884616002126e-05, "epoch": 3.3394495412844036, "percentage": 33.39, "elapsed_time": "0:21:27", "remaining_time": "0:42:48", "throughput": 2649.81, "total_tokens": 3412248} {"current_steps": 12745, "total_steps": 38150, "loss": 0.4353, "lr": 4.211050917007937e-05, "epoch": 3.3407601572739187, "percentage": 33.41, "elapsed_time": "0:21:28", "remaining_time": "0:42:47", "throughput": 2650.16, "total_tokens": 3414104} {"current_steps": 12750, "total_steps": 38150, "loss": 0.3073, "lr": 4.210216859893747e-05, "epoch": 3.342070773263434, "percentage": 33.42, "elapsed_time": "0:21:28", "remaining_time": "0:42:47", "throughput": 2650.16, "total_tokens": 3415256} {"current_steps": 12755, "total_steps": 38150, "loss": 0.4557, "lr": 4.2093824448341226e-05, "epoch": 3.343381389252949, "percentage": 33.43, "elapsed_time": "0:21:29", "remaining_time": "0:42:46", "throughput": 2650.08, "total_tokens": 3416264} {"current_steps": 12760, "total_steps": 38150, "loss": 0.3983, "lr": 4.208547672003707e-05, "epoch": 3.344692005242464, "percentage": 33.45, "elapsed_time": "0:21:29", "remaining_time": "0:42:45", "throughput": 2650.21, "total_tokens": 3417592} {"current_steps": 12765, "total_steps": 38150, "loss": 0.4268, "lr": 4.207712541577215e-05, "epoch": 3.346002621231979, "percentage": 33.46, "elapsed_time": "0:21:29", "remaining_time": "0:42:45", "throughput": 2650.42, "total_tokens": 3419032} {"current_steps": 12770, "total_steps": 38150, "loss": 0.3815, "lr": 4.2068770537294395e-05, "epoch": 3.347313237221494, "percentage": 33.47, "elapsed_time": "0:21:30", "remaining_time": "0:42:44", "throughput": 2650.38, "total_tokens": 3420104} {"current_steps": 12775, "total_steps": 38150, "loss": 0.3218, "lr": 4.2060412086352455e-05, "epoch": 3.3486238532110093, "percentage": 33.49, "elapsed_time": "0:21:30", "remaining_time": "0:42:44", "throughput": 2650.67, "total_tokens": 3421704} {"current_steps": 12780, "total_steps": 38150, "loss": 0.3517, "lr": 4.2052050064695746e-05, "epoch": 3.3499344692005244, "percentage": 33.5, "elapsed_time": "0:21:31", "remaining_time": "0:42:43", "throughput": 2650.73, "total_tokens": 3422904} {"current_steps": 12785, "total_steps": 38150, "loss": 0.3044, "lr": 4.204368447407442e-05, "epoch": 3.3512450851900395, "percentage": 33.51, "elapsed_time": "0:21:31", "remaining_time": "0:42:42", "throughput": 2650.93, "total_tokens": 3424456} {"current_steps": 12790, "total_steps": 38150, "loss": 0.2629, "lr": 4.203531531623938e-05, "epoch": 3.352555701179554, "percentage": 33.53, "elapsed_time": "0:21:32", "remaining_time": "0:42:42", "throughput": 2650.93, "total_tokens": 3425576} {"current_steps": 12795, "total_steps": 38150, "loss": 0.3681, "lr": 4.2026942592942285e-05, "epoch": 3.3538663171690697, "percentage": 33.54, "elapsed_time": "0:21:32", "remaining_time": "0:42:41", "throughput": 2651.06, "total_tokens": 3426920} {"current_steps": 12800, "total_steps": 38150, "loss": 0.4257, "lr": 4.2018566305935525e-05, "epoch": 3.3551769331585843, "percentage": 33.55, "elapsed_time": "0:21:33", "remaining_time": "0:42:41", "throughput": 2651.31, "total_tokens": 3428504} {"current_steps": 12805, "total_steps": 38150, "loss": 0.2916, "lr": 4.201018645697224e-05, "epoch": 3.3564875491480994, "percentage": 33.56, "elapsed_time": "0:21:33", "remaining_time": "0:42:40", "throughput": 2651.16, "total_tokens": 3429416} {"current_steps": 12810, "total_steps": 38150, "loss": 0.3275, "lr": 4.200180304780632e-05, "epoch": 3.3577981651376145, "percentage": 33.58, "elapsed_time": "0:21:33", "remaining_time": "0:42:39", "throughput": 2651.3, "total_tokens": 3430776} {"current_steps": 12815, "total_steps": 38150, "loss": 0.5434, "lr": 4.1993416080192404e-05, "epoch": 3.3591087811271296, "percentage": 33.59, "elapsed_time": "0:21:34", "remaining_time": "0:42:39", "throughput": 2651.2, "total_tokens": 3431832} {"current_steps": 12820, "total_steps": 38150, "loss": 0.5209, "lr": 4.198502555588586e-05, "epoch": 3.3604193971166447, "percentage": 33.6, "elapsed_time": "0:21:34", "remaining_time": "0:42:38", "throughput": 2651.16, "total_tokens": 3432904} {"current_steps": 12825, "total_steps": 38150, "loss": 0.342, "lr": 4.197663147664281e-05, "epoch": 3.36173001310616, "percentage": 33.62, "elapsed_time": "0:21:35", "remaining_time": "0:42:37", "throughput": 2651.12, "total_tokens": 3433976} {"current_steps": 12830, "total_steps": 38150, "loss": 0.3664, "lr": 4.196823384422014e-05, "epoch": 3.363040629095675, "percentage": 33.63, "elapsed_time": "0:21:35", "remaining_time": "0:42:37", "throughput": 2651.25, "total_tokens": 3435320} {"current_steps": 12835, "total_steps": 38150, "loss": 0.3759, "lr": 4.195983266037543e-05, "epoch": 3.36435124508519, "percentage": 33.64, "elapsed_time": "0:21:36", "remaining_time": "0:42:36", "throughput": 2651.28, "total_tokens": 3436552} {"current_steps": 12840, "total_steps": 38150, "loss": 0.3533, "lr": 4.1951427926867056e-05, "epoch": 3.365661861074705, "percentage": 33.66, "elapsed_time": "0:21:36", "remaining_time": "0:42:35", "throughput": 2651.21, "total_tokens": 3437656} {"current_steps": 12845, "total_steps": 38150, "loss": 0.4454, "lr": 4.1943019645454115e-05, "epoch": 3.36697247706422, "percentage": 33.67, "elapsed_time": "0:21:37", "remaining_time": "0:42:35", "throughput": 2651.09, "total_tokens": 3438616} {"current_steps": 12850, "total_steps": 38150, "loss": 0.4485, "lr": 4.193460781789642e-05, "epoch": 3.3682830930537353, "percentage": 33.68, "elapsed_time": "0:21:37", "remaining_time": "0:42:34", "throughput": 2651.17, "total_tokens": 3439848} {"current_steps": 12855, "total_steps": 38150, "loss": 0.4078, "lr": 4.192619244595458e-05, "epoch": 3.3695937090432504, "percentage": 33.7, "elapsed_time": "0:21:37", "remaining_time": "0:42:33", "throughput": 2651.28, "total_tokens": 3441176} {"current_steps": 12860, "total_steps": 38150, "loss": 0.4583, "lr": 4.191777353138991e-05, "epoch": 3.3709043250327655, "percentage": 33.71, "elapsed_time": "0:21:38", "remaining_time": "0:42:33", "throughput": 2651.45, "total_tokens": 3442696} {"current_steps": 12865, "total_steps": 38150, "loss": 0.3703, "lr": 4.1909351075964464e-05, "epoch": 3.3722149410222806, "percentage": 33.72, "elapsed_time": "0:21:38", "remaining_time": "0:42:32", "throughput": 2651.45, "total_tokens": 3443832} {"current_steps": 12870, "total_steps": 38150, "loss": 0.3972, "lr": 4.190092508144106e-05, "epoch": 3.3735255570117957, "percentage": 33.74, "elapsed_time": "0:21:39", "remaining_time": "0:42:32", "throughput": 2651.43, "total_tokens": 3444952} {"current_steps": 12875, "total_steps": 38150, "loss": 0.3608, "lr": 4.189249554958324e-05, "epoch": 3.374836173001311, "percentage": 33.75, "elapsed_time": "0:21:39", "remaining_time": "0:42:31", "throughput": 2651.52, "total_tokens": 3446232} {"current_steps": 12880, "total_steps": 38150, "loss": 0.3526, "lr": 4.188406248215528e-05, "epoch": 3.376146788990826, "percentage": 33.76, "elapsed_time": "0:21:40", "remaining_time": "0:42:30", "throughput": 2651.59, "total_tokens": 3447528} {"current_steps": 12885, "total_steps": 38150, "loss": 0.739, "lr": 4.1875625880922225e-05, "epoch": 3.3774574049803405, "percentage": 33.77, "elapsed_time": "0:21:40", "remaining_time": "0:42:30", "throughput": 2651.95, "total_tokens": 3449352} {"current_steps": 12890, "total_steps": 38150, "loss": 0.5389, "lr": 4.186718574764983e-05, "epoch": 3.378768020969856, "percentage": 33.79, "elapsed_time": "0:21:41", "remaining_time": "0:42:29", "throughput": 2651.98, "total_tokens": 3450536} {"current_steps": 12895, "total_steps": 38150, "loss": 0.3815, "lr": 4.18587420841046e-05, "epoch": 3.3800786369593707, "percentage": 33.8, "elapsed_time": "0:21:41", "remaining_time": "0:42:29", "throughput": 2651.98, "total_tokens": 3451688} {"current_steps": 12900, "total_steps": 38150, "loss": 0.408, "lr": 4.185029489205379e-05, "epoch": 3.381389252948886, "percentage": 33.81, "elapsed_time": "0:21:41", "remaining_time": "0:42:28", "throughput": 2651.95, "total_tokens": 3452760} {"current_steps": 12905, "total_steps": 38150, "loss": 0.3342, "lr": 4.1841844173265357e-05, "epoch": 3.382699868938401, "percentage": 33.83, "elapsed_time": "0:21:42", "remaining_time": "0:42:27", "throughput": 2652.4, "total_tokens": 3454712} {"current_steps": 12910, "total_steps": 38150, "loss": 0.4669, "lr": 4.183338992950805e-05, "epoch": 3.384010484927916, "percentage": 33.84, "elapsed_time": "0:21:43", "remaining_time": "0:42:27", "throughput": 2652.78, "total_tokens": 3456632} {"current_steps": 12915, "total_steps": 38150, "loss": 0.3798, "lr": 4.182493216255132e-05, "epoch": 3.385321100917431, "percentage": 33.85, "elapsed_time": "0:21:43", "remaining_time": "0:42:26", "throughput": 2652.88, "total_tokens": 3457992} {"current_steps": 12920, "total_steps": 38150, "loss": 0.2629, "lr": 4.181647087416536e-05, "epoch": 3.386631716906946, "percentage": 33.87, "elapsed_time": "0:21:43", "remaining_time": "0:42:26", "throughput": 2652.97, "total_tokens": 3459224} {"current_steps": 12925, "total_steps": 38150, "loss": 0.3652, "lr": 4.18080060661211e-05, "epoch": 3.3879423328964613, "percentage": 33.88, "elapsed_time": "0:21:44", "remaining_time": "0:42:25", "throughput": 2653.17, "total_tokens": 3460680} {"current_steps": 12930, "total_steps": 38150, "loss": 0.4239, "lr": 4.179953774019021e-05, "epoch": 3.3892529488859764, "percentage": 33.89, "elapsed_time": "0:21:44", "remaining_time": "0:42:25", "throughput": 2653.53, "total_tokens": 3462520} {"current_steps": 12935, "total_steps": 38150, "loss": 0.3743, "lr": 4.1791065898145095e-05, "epoch": 3.3905635648754915, "percentage": 33.91, "elapsed_time": "0:21:45", "remaining_time": "0:42:24", "throughput": 2653.62, "total_tokens": 3463768} {"current_steps": 12940, "total_steps": 38150, "loss": 0.3534, "lr": 4.178259054175891e-05, "epoch": 3.3918741808650066, "percentage": 33.92, "elapsed_time": "0:21:45", "remaining_time": "0:42:23", "throughput": 2653.71, "total_tokens": 3465032} {"current_steps": 12945, "total_steps": 38150, "loss": 0.3675, "lr": 4.177411167280551e-05, "epoch": 3.3931847968545217, "percentage": 33.93, "elapsed_time": "0:21:46", "remaining_time": "0:42:23", "throughput": 2653.88, "total_tokens": 3466520} {"current_steps": 12950, "total_steps": 38150, "loss": 0.5296, "lr": 4.176562929305953e-05, "epoch": 3.3944954128440368, "percentage": 33.94, "elapsed_time": "0:21:46", "remaining_time": "0:42:22", "throughput": 2653.95, "total_tokens": 3467800} {"current_steps": 12955, "total_steps": 38150, "loss": 0.3691, "lr": 4.1757143404296305e-05, "epoch": 3.395806028833552, "percentage": 33.96, "elapsed_time": "0:21:47", "remaining_time": "0:42:22", "throughput": 2653.89, "total_tokens": 3468840} {"current_steps": 12960, "total_steps": 38150, "loss": 0.5245, "lr": 4.1748654008291914e-05, "epoch": 3.397116644823067, "percentage": 33.97, "elapsed_time": "0:21:47", "remaining_time": "0:42:21", "throughput": 2653.87, "total_tokens": 3469912} {"current_steps": 12965, "total_steps": 38150, "loss": 0.3527, "lr": 4.1740161106823185e-05, "epoch": 3.398427260812582, "percentage": 33.98, "elapsed_time": "0:21:48", "remaining_time": "0:42:20", "throughput": 2654.12, "total_tokens": 3471736} {"current_steps": 12970, "total_steps": 38150, "loss": 0.3505, "lr": 4.173166470166766e-05, "epoch": 3.399737876802097, "percentage": 34.0, "elapsed_time": "0:21:48", "remaining_time": "0:42:20", "throughput": 2654.28, "total_tokens": 3473304} {"current_steps": 12975, "total_steps": 38150, "loss": 0.4045, "lr": 4.172316479460362e-05, "epoch": 3.4010484927916123, "percentage": 34.01, "elapsed_time": "0:21:48", "remaining_time": "0:42:19", "throughput": 2654.36, "total_tokens": 3474552} {"current_steps": 12980, "total_steps": 38150, "loss": 0.435, "lr": 4.171466138741009e-05, "epoch": 3.402359108781127, "percentage": 34.02, "elapsed_time": "0:21:49", "remaining_time": "0:42:19", "throughput": 2654.44, "total_tokens": 3475864} {"current_steps": 12985, "total_steps": 38150, "loss": 0.3328, "lr": 4.170615448186681e-05, "epoch": 3.4036697247706424, "percentage": 34.04, "elapsed_time": "0:21:49", "remaining_time": "0:42:18", "throughput": 2654.59, "total_tokens": 3477288} {"current_steps": 12990, "total_steps": 38150, "loss": 0.3456, "lr": 4.169764407975426e-05, "epoch": 3.404980340760157, "percentage": 34.05, "elapsed_time": "0:21:50", "remaining_time": "0:42:18", "throughput": 2654.73, "total_tokens": 3478712} {"current_steps": 12995, "total_steps": 38150, "loss": 0.6317, "lr": 4.168913018285366e-05, "epoch": 3.406290956749672, "percentage": 34.06, "elapsed_time": "0:21:50", "remaining_time": "0:42:17", "throughput": 2654.8, "total_tokens": 3480040} {"current_steps": 13000, "total_steps": 38150, "loss": 0.6444, "lr": 4.168061279294694e-05, "epoch": 3.4076015727391873, "percentage": 34.08, "elapsed_time": "0:21:51", "remaining_time": "0:42:17", "throughput": 2655.12, "total_tokens": 3481864} {"current_steps": 13005, "total_steps": 38150, "loss": 0.3922, "lr": 4.16720919118168e-05, "epoch": 3.4089121887287024, "percentage": 34.09, "elapsed_time": "0:21:51", "remaining_time": "0:42:16", "throughput": 2655.26, "total_tokens": 3483224} {"current_steps": 13010, "total_steps": 38150, "loss": 0.3439, "lr": 4.1663567541246615e-05, "epoch": 3.4102228047182175, "percentage": 34.1, "elapsed_time": "0:21:52", "remaining_time": "0:42:15", "throughput": 2655.47, "total_tokens": 3484728} {"current_steps": 13015, "total_steps": 38150, "loss": 0.4969, "lr": 4.165503968302055e-05, "epoch": 3.4115334207077326, "percentage": 34.12, "elapsed_time": "0:21:52", "remaining_time": "0:42:15", "throughput": 2655.75, "total_tokens": 3486376} {"current_steps": 13020, "total_steps": 38150, "loss": 0.5586, "lr": 4.1646508338923446e-05, "epoch": 3.4128440366972477, "percentage": 34.13, "elapsed_time": "0:21:53", "remaining_time": "0:42:14", "throughput": 2655.82, "total_tokens": 3487640} {"current_steps": 13025, "total_steps": 38150, "loss": 0.3994, "lr": 4.1637973510740914e-05, "epoch": 3.4141546526867628, "percentage": 34.14, "elapsed_time": "0:21:53", "remaining_time": "0:42:14", "throughput": 2656.02, "total_tokens": 3489160} {"current_steps": 13030, "total_steps": 38150, "loss": 0.3836, "lr": 4.162943520025927e-05, "epoch": 3.415465268676278, "percentage": 34.15, "elapsed_time": "0:21:54", "remaining_time": "0:42:13", "throughput": 2656.3, "total_tokens": 3490888} {"current_steps": 13035, "total_steps": 38150, "loss": 0.5215, "lr": 4.162089340926558e-05, "epoch": 3.416775884665793, "percentage": 34.17, "elapsed_time": "0:21:54", "remaining_time": "0:42:13", "throughput": 2656.45, "total_tokens": 3492344} {"current_steps": 13040, "total_steps": 38150, "loss": 0.4906, "lr": 4.161234813954761e-05, "epoch": 3.418086500655308, "percentage": 34.18, "elapsed_time": "0:21:55", "remaining_time": "0:42:12", "throughput": 2656.38, "total_tokens": 3493384} {"current_steps": 13045, "total_steps": 38150, "loss": 0.3092, "lr": 4.160379939289388e-05, "epoch": 3.419397116644823, "percentage": 34.19, "elapsed_time": "0:21:55", "remaining_time": "0:42:11", "throughput": 2656.54, "total_tokens": 3494760} {"current_steps": 13050, "total_steps": 38150, "loss": 0.3946, "lr": 4.1595247171093635e-05, "epoch": 3.4207077326343382, "percentage": 34.21, "elapsed_time": "0:21:55", "remaining_time": "0:42:11", "throughput": 2656.55, "total_tokens": 3495896} {"current_steps": 13055, "total_steps": 38150, "loss": 0.4925, "lr": 4.158669147593682e-05, "epoch": 3.4220183486238533, "percentage": 34.22, "elapsed_time": "0:21:56", "remaining_time": "0:42:10", "throughput": 2656.64, "total_tokens": 3497160} {"current_steps": 13060, "total_steps": 38150, "loss": 0.2923, "lr": 4.157813230921414e-05, "epoch": 3.4233289646133684, "percentage": 34.23, "elapsed_time": "0:21:56", "remaining_time": "0:42:09", "throughput": 2656.75, "total_tokens": 3498472} {"current_steps": 13065, "total_steps": 38150, "loss": 0.514, "lr": 4.156956967271702e-05, "epoch": 3.4246395806028835, "percentage": 34.25, "elapsed_time": "0:21:57", "remaining_time": "0:42:09", "throughput": 2656.8, "total_tokens": 3499688} {"current_steps": 13070, "total_steps": 38150, "loss": 0.2567, "lr": 4.156100356823759e-05, "epoch": 3.4259501965923986, "percentage": 34.26, "elapsed_time": "0:21:57", "remaining_time": "0:42:08", "throughput": 2656.92, "total_tokens": 3500984} {"current_steps": 13075, "total_steps": 38150, "loss": 0.817, "lr": 4.1552433997568736e-05, "epoch": 3.4272608125819133, "percentage": 34.27, "elapsed_time": "0:21:58", "remaining_time": "0:42:07", "throughput": 2656.97, "total_tokens": 3502184} {"current_steps": 13080, "total_steps": 38150, "loss": 0.3549, "lr": 4.154386096250404e-05, "epoch": 3.4285714285714284, "percentage": 34.29, "elapsed_time": "0:21:58", "remaining_time": "0:42:07", "throughput": 2657.18, "total_tokens": 3503640} {"current_steps": 13085, "total_steps": 38150, "loss": 0.396, "lr": 4.153528446483783e-05, "epoch": 3.4298820445609435, "percentage": 34.3, "elapsed_time": "0:21:59", "remaining_time": "0:42:06", "throughput": 2657.31, "total_tokens": 3505032} {"current_steps": 13090, "total_steps": 38150, "loss": 0.4259, "lr": 4.1526704506365153e-05, "epoch": 3.4311926605504586, "percentage": 34.31, "elapsed_time": "0:21:59", "remaining_time": "0:42:05", "throughput": 2657.28, "total_tokens": 3506088} {"current_steps": 13095, "total_steps": 38150, "loss": 0.5663, "lr": 4.1518121088881785e-05, "epoch": 3.4325032765399737, "percentage": 34.33, "elapsed_time": "0:21:59", "remaining_time": "0:42:05", "throughput": 2657.17, "total_tokens": 3507048} {"current_steps": 13100, "total_steps": 38150, "loss": 0.3425, "lr": 4.1509534214184206e-05, "epoch": 3.4338138925294888, "percentage": 34.34, "elapsed_time": "0:22:00", "remaining_time": "0:42:04", "throughput": 2657.23, "total_tokens": 3508296} {"current_steps": 13105, "total_steps": 38150, "loss": 0.7316, "lr": 4.1500943884069644e-05, "epoch": 3.435124508519004, "percentage": 34.35, "elapsed_time": "0:22:00", "remaining_time": "0:42:04", "throughput": 2657.23, "total_tokens": 3509496} {"current_steps": 13110, "total_steps": 38150, "loss": 0.3824, "lr": 4.149235010033604e-05, "epoch": 3.436435124508519, "percentage": 34.36, "elapsed_time": "0:22:01", "remaining_time": "0:42:03", "throughput": 2657.45, "total_tokens": 3511080} {"current_steps": 13115, "total_steps": 38150, "loss": 0.3905, "lr": 4.148375286478206e-05, "epoch": 3.437745740498034, "percentage": 34.38, "elapsed_time": "0:22:01", "remaining_time": "0:42:02", "throughput": 2657.56, "total_tokens": 3512440} {"current_steps": 13120, "total_steps": 38150, "loss": 0.3584, "lr": 4.147515217920709e-05, "epoch": 3.439056356487549, "percentage": 34.39, "elapsed_time": "0:22:02", "remaining_time": "0:42:02", "throughput": 2657.6, "total_tokens": 3513720} {"current_steps": 13125, "total_steps": 38150, "loss": 0.4368, "lr": 4.146654804541122e-05, "epoch": 3.4403669724770642, "percentage": 34.4, "elapsed_time": "0:22:02", "remaining_time": "0:42:01", "throughput": 2657.7, "total_tokens": 3515240} {"current_steps": 13130, "total_steps": 38150, "loss": 0.34, "lr": 4.145794046519531e-05, "epoch": 3.4416775884665793, "percentage": 34.42, "elapsed_time": "0:22:03", "remaining_time": "0:42:01", "throughput": 2657.75, "total_tokens": 3516424} {"current_steps": 13135, "total_steps": 38150, "loss": 0.5692, "lr": 4.14493294403609e-05, "epoch": 3.4429882044560944, "percentage": 34.43, "elapsed_time": "0:22:03", "remaining_time": "0:42:00", "throughput": 2657.76, "total_tokens": 3517592} {"current_steps": 13140, "total_steps": 38150, "loss": 0.337, "lr": 4.144071497271025e-05, "epoch": 3.4442988204456095, "percentage": 34.44, "elapsed_time": "0:22:03", "remaining_time": "0:41:59", "throughput": 2657.77, "total_tokens": 3518728} {"current_steps": 13145, "total_steps": 38150, "loss": 0.3537, "lr": 4.143209706404637e-05, "epoch": 3.4456094364351246, "percentage": 34.46, "elapsed_time": "0:22:04", "remaining_time": "0:41:59", "throughput": 2657.82, "total_tokens": 3519960} {"current_steps": 13150, "total_steps": 38150, "loss": 0.3317, "lr": 4.142347571617296e-05, "epoch": 3.4469200524246397, "percentage": 34.47, "elapsed_time": "0:22:04", "remaining_time": "0:41:58", "throughput": 2657.82, "total_tokens": 3521096} {"current_steps": 13155, "total_steps": 38150, "loss": 0.4853, "lr": 4.1414850930894466e-05, "epoch": 3.448230668414155, "percentage": 34.48, "elapsed_time": "0:22:05", "remaining_time": "0:41:58", "throughput": 2657.9, "total_tokens": 3522360} {"current_steps": 13160, "total_steps": 38150, "loss": 0.2938, "lr": 4.1406222710016034e-05, "epoch": 3.44954128440367, "percentage": 34.5, "elapsed_time": "0:22:05", "remaining_time": "0:41:57", "throughput": 2658.04, "total_tokens": 3523768} {"current_steps": 13165, "total_steps": 38150, "loss": 0.4118, "lr": 4.1397591055343534e-05, "epoch": 3.450851900393185, "percentage": 34.51, "elapsed_time": "0:22:06", "remaining_time": "0:41:56", "throughput": 2658.23, "total_tokens": 3525368} {"current_steps": 13170, "total_steps": 38150, "loss": 0.7666, "lr": 4.1388955968683565e-05, "epoch": 3.4521625163826997, "percentage": 34.52, "elapsed_time": "0:22:06", "remaining_time": "0:41:56", "throughput": 2658.33, "total_tokens": 3526664} {"current_steps": 13175, "total_steps": 38150, "loss": 0.4677, "lr": 4.1380317451843425e-05, "epoch": 3.4534731323722148, "percentage": 34.53, "elapsed_time": "0:22:07", "remaining_time": "0:41:55", "throughput": 2658.47, "total_tokens": 3528088} {"current_steps": 13180, "total_steps": 38150, "loss": 0.295, "lr": 4.137167550663115e-05, "epoch": 3.45478374836173, "percentage": 34.55, "elapsed_time": "0:22:07", "remaining_time": "0:41:55", "throughput": 2658.61, "total_tokens": 3529496} {"current_steps": 13185, "total_steps": 38150, "loss": 0.3824, "lr": 4.136303013485547e-05, "epoch": 3.456094364351245, "percentage": 34.56, "elapsed_time": "0:22:08", "remaining_time": "0:41:54", "throughput": 2659.02, "total_tokens": 3531720} {"current_steps": 13190, "total_steps": 38150, "loss": 0.4613, "lr": 4.1354381338325864e-05, "epoch": 3.45740498034076, "percentage": 34.57, "elapsed_time": "0:22:08", "remaining_time": "0:41:54", "throughput": 2659.09, "total_tokens": 3533032} {"current_steps": 13195, "total_steps": 38150, "loss": 0.5375, "lr": 4.13457291188525e-05, "epoch": 3.458715596330275, "percentage": 34.59, "elapsed_time": "0:22:09", "remaining_time": "0:41:53", "throughput": 2659.07, "total_tokens": 3534136} {"current_steps": 13200, "total_steps": 38150, "loss": 0.6634, "lr": 4.1337073478246275e-05, "epoch": 3.4600262123197902, "percentage": 34.6, "elapsed_time": "0:22:09", "remaining_time": "0:41:52", "throughput": 2659.08, "total_tokens": 3535272} {"current_steps": 13205, "total_steps": 38150, "loss": 0.3228, "lr": 4.1328414418318795e-05, "epoch": 3.4613368283093053, "percentage": 34.61, "elapsed_time": "0:22:09", "remaining_time": "0:41:52", "throughput": 2659.15, "total_tokens": 3536536} {"current_steps": 13210, "total_steps": 38150, "loss": 0.3696, "lr": 4.13197519408824e-05, "epoch": 3.4626474442988204, "percentage": 34.63, "elapsed_time": "0:22:10", "remaining_time": "0:41:51", "throughput": 2659.05, "total_tokens": 3537496} {"current_steps": 13215, "total_steps": 38150, "loss": 0.4494, "lr": 4.1311086047750114e-05, "epoch": 3.4639580602883355, "percentage": 34.64, "elapsed_time": "0:22:10", "remaining_time": "0:41:51", "throughput": 2659.08, "total_tokens": 3538696} {"current_steps": 13220, "total_steps": 38150, "loss": 0.6978, "lr": 4.13024167407357e-05, "epoch": 3.4652686762778506, "percentage": 34.65, "elapsed_time": "0:22:11", "remaining_time": "0:41:50", "throughput": 2659.26, "total_tokens": 3540184} {"current_steps": 13225, "total_steps": 38150, "loss": 0.3214, "lr": 4.129374402165363e-05, "epoch": 3.4665792922673657, "percentage": 34.67, "elapsed_time": "0:22:11", "remaining_time": "0:41:49", "throughput": 2659.37, "total_tokens": 3541576} {"current_steps": 13230, "total_steps": 38150, "loss": 0.3514, "lr": 4.128506789231911e-05, "epoch": 3.467889908256881, "percentage": 34.68, "elapsed_time": "0:22:12", "remaining_time": "0:41:49", "throughput": 2660.18, "total_tokens": 3544776} {"current_steps": 13235, "total_steps": 38150, "loss": 0.3034, "lr": 4.1276388354548e-05, "epoch": 3.469200524246396, "percentage": 34.69, "elapsed_time": "0:22:12", "remaining_time": "0:41:49", "throughput": 2660.18, "total_tokens": 3545976} {"current_steps": 13240, "total_steps": 38150, "loss": 0.3163, "lr": 4.126770541015693e-05, "epoch": 3.470511140235911, "percentage": 34.71, "elapsed_time": "0:22:13", "remaining_time": "0:41:48", "throughput": 2660.21, "total_tokens": 3547160} {"current_steps": 13245, "total_steps": 38150, "loss": 0.3108, "lr": 4.1259019060963236e-05, "epoch": 3.471821756225426, "percentage": 34.72, "elapsed_time": "0:22:13", "remaining_time": "0:41:48", "throughput": 2660.22, "total_tokens": 3548296} {"current_steps": 13250, "total_steps": 38150, "loss": 0.3291, "lr": 4.125032930878493e-05, "epoch": 3.473132372214941, "percentage": 34.73, "elapsed_time": "0:22:14", "remaining_time": "0:41:47", "throughput": 2660.29, "total_tokens": 3549624} {"current_steps": 13255, "total_steps": 38150, "loss": 0.3871, "lr": 4.1241636155440785e-05, "epoch": 3.474442988204456, "percentage": 34.74, "elapsed_time": "0:22:14", "remaining_time": "0:41:46", "throughput": 2660.32, "total_tokens": 3550824} {"current_steps": 13260, "total_steps": 38150, "loss": 0.3628, "lr": 4.123293960275027e-05, "epoch": 3.4757536041939714, "percentage": 34.76, "elapsed_time": "0:22:15", "remaining_time": "0:41:46", "throughput": 2660.45, "total_tokens": 3552232} {"current_steps": 13265, "total_steps": 38150, "loss": 0.4636, "lr": 4.1224239652533526e-05, "epoch": 3.477064220183486, "percentage": 34.77, "elapsed_time": "0:22:15", "remaining_time": "0:41:45", "throughput": 2660.54, "total_tokens": 3553512} {"current_steps": 13270, "total_steps": 38150, "loss": 0.323, "lr": 4.121553630661147e-05, "epoch": 3.478374836173001, "percentage": 34.78, "elapsed_time": "0:22:16", "remaining_time": "0:41:45", "throughput": 2660.59, "total_tokens": 3554728} {"current_steps": 13275, "total_steps": 38150, "loss": 0.5968, "lr": 4.120682956680567e-05, "epoch": 3.4796854521625162, "percentage": 34.8, "elapsed_time": "0:22:16", "remaining_time": "0:41:44", "throughput": 2660.53, "total_tokens": 3555800} {"current_steps": 13280, "total_steps": 38150, "loss": 0.4268, "lr": 4.1198119434938455e-05, "epoch": 3.4809960681520313, "percentage": 34.81, "elapsed_time": "0:22:16", "remaining_time": "0:41:43", "throughput": 2660.77, "total_tokens": 3557400} {"current_steps": 13285, "total_steps": 38150, "loss": 0.3639, "lr": 4.118940591283282e-05, "epoch": 3.4823066841415464, "percentage": 34.82, "elapsed_time": "0:22:17", "remaining_time": "0:41:43", "throughput": 2660.77, "total_tokens": 3558504} {"current_steps": 13290, "total_steps": 38150, "loss": 0.4258, "lr": 4.118068900231251e-05, "epoch": 3.4836173001310615, "percentage": 34.84, "elapsed_time": "0:22:17", "remaining_time": "0:41:42", "throughput": 2660.92, "total_tokens": 3559928} {"current_steps": 13295, "total_steps": 38150, "loss": 0.8284, "lr": 4.117196870520195e-05, "epoch": 3.4849279161205766, "percentage": 34.85, "elapsed_time": "0:22:18", "remaining_time": "0:41:42", "throughput": 2661.02, "total_tokens": 3561320} {"current_steps": 13300, "total_steps": 38150, "loss": 0.5668, "lr": 4.116324502332628e-05, "epoch": 3.4862385321100917, "percentage": 34.86, "elapsed_time": "0:22:18", "remaining_time": "0:41:41", "throughput": 2660.85, "total_tokens": 3562200} {"current_steps": 13305, "total_steps": 38150, "loss": 0.5506, "lr": 4.115451795851136e-05, "epoch": 3.487549148099607, "percentage": 34.88, "elapsed_time": "0:22:19", "remaining_time": "0:41:40", "throughput": 2660.92, "total_tokens": 3563544} {"current_steps": 13310, "total_steps": 38150, "loss": 0.4438, "lr": 4.1145787512583736e-05, "epoch": 3.488859764089122, "percentage": 34.89, "elapsed_time": "0:22:19", "remaining_time": "0:41:40", "throughput": 2661.17, "total_tokens": 3565320} {"current_steps": 13315, "total_steps": 38150, "loss": 0.4653, "lr": 4.113705368737069e-05, "epoch": 3.490170380078637, "percentage": 34.9, "elapsed_time": "0:22:20", "remaining_time": "0:41:39", "throughput": 2661.53, "total_tokens": 3567288} {"current_steps": 13320, "total_steps": 38150, "loss": 0.4601, "lr": 4.112831648470018e-05, "epoch": 3.491480996068152, "percentage": 34.91, "elapsed_time": "0:22:20", "remaining_time": "0:41:39", "throughput": 2661.6, "total_tokens": 3568616} {"current_steps": 13325, "total_steps": 38150, "loss": 0.4228, "lr": 4.111957590640091e-05, "epoch": 3.492791612057667, "percentage": 34.93, "elapsed_time": "0:22:21", "remaining_time": "0:41:38", "throughput": 2661.82, "total_tokens": 3570184} {"current_steps": 13330, "total_steps": 38150, "loss": 0.5275, "lr": 4.111083195430225e-05, "epoch": 3.4941022280471823, "percentage": 34.94, "elapsed_time": "0:22:21", "remaining_time": "0:41:38", "throughput": 2662.17, "total_tokens": 3572040} {"current_steps": 13335, "total_steps": 38150, "loss": 0.4301, "lr": 4.110208463023429e-05, "epoch": 3.4954128440366974, "percentage": 34.95, "elapsed_time": "0:22:22", "remaining_time": "0:41:37", "throughput": 2662.31, "total_tokens": 3573560} {"current_steps": 13340, "total_steps": 38150, "loss": 0.4921, "lr": 4.109333393602786e-05, "epoch": 3.4967234600262125, "percentage": 34.97, "elapsed_time": "0:22:22", "remaining_time": "0:41:37", "throughput": 2662.49, "total_tokens": 3575048} {"current_steps": 13345, "total_steps": 38150, "loss": 0.4203, "lr": 4.108457987351443e-05, "epoch": 3.4980340760157276, "percentage": 34.98, "elapsed_time": "0:22:23", "remaining_time": "0:41:36", "throughput": 2662.63, "total_tokens": 3576408} {"current_steps": 13350, "total_steps": 38150, "loss": 0.2849, "lr": 4.107582244452622e-05, "epoch": 3.4993446920052422, "percentage": 34.99, "elapsed_time": "0:22:23", "remaining_time": "0:41:35", "throughput": 2662.57, "total_tokens": 3577448} {"current_steps": 13355, "total_steps": 38150, "loss": 0.3807, "lr": 4.106706165089616e-05, "epoch": 3.5006553079947578, "percentage": 35.01, "elapsed_time": "0:22:24", "remaining_time": "0:41:35", "throughput": 2662.89, "total_tokens": 3579256} {"current_steps": 13356, "total_steps": 38150, "eval_loss": 0.5102009177207947, "epoch": 3.5009174311926605, "percentage": 35.01, "elapsed_time": "0:22:41", "remaining_time": "0:42:06", "throughput": 2629.84, "total_tokens": 3579432} {"current_steps": 13360, "total_steps": 38150, "loss": 0.4248, "lr": 4.105829749445785e-05, "epoch": 3.5019659239842724, "percentage": 35.02, "elapsed_time": "0:22:43", "remaining_time": "0:42:09", "throughput": 2626.96, "total_tokens": 3580584} {"current_steps": 13365, "total_steps": 38150, "loss": 0.3418, "lr": 4.104952997704563e-05, "epoch": 3.5032765399737875, "percentage": 35.03, "elapsed_time": "0:22:43", "remaining_time": "0:42:08", "throughput": 2627.31, "total_tokens": 3582440} {"current_steps": 13370, "total_steps": 38150, "loss": 0.3379, "lr": 4.1040759100494506e-05, "epoch": 3.5045871559633026, "percentage": 35.05, "elapsed_time": "0:22:43", "remaining_time": "0:42:07", "throughput": 2627.26, "total_tokens": 3583496} {"current_steps": 13375, "total_steps": 38150, "loss": 0.2127, "lr": 4.103198486664023e-05, "epoch": 3.5058977719528177, "percentage": 35.06, "elapsed_time": "0:22:44", "remaining_time": "0:42:07", "throughput": 2627.34, "total_tokens": 3584856} {"current_steps": 13380, "total_steps": 38150, "loss": 0.3744, "lr": 4.1023207277319213e-05, "epoch": 3.507208387942333, "percentage": 35.07, "elapsed_time": "0:22:44", "remaining_time": "0:42:06", "throughput": 2627.37, "total_tokens": 3586120} {"current_steps": 13385, "total_steps": 38150, "loss": 0.2028, "lr": 4.10144263343686e-05, "epoch": 3.508519003931848, "percentage": 35.09, "elapsed_time": "0:22:45", "remaining_time": "0:42:06", "throughput": 2627.55, "total_tokens": 3587688} {"current_steps": 13390, "total_steps": 38150, "loss": 0.6037, "lr": 4.1005642039626235e-05, "epoch": 3.509829619921363, "percentage": 35.1, "elapsed_time": "0:22:45", "remaining_time": "0:42:05", "throughput": 2627.59, "total_tokens": 3588888} {"current_steps": 13395, "total_steps": 38150, "loss": 0.3359, "lr": 4.099685439493064e-05, "epoch": 3.511140235910878, "percentage": 35.11, "elapsed_time": "0:22:46", "remaining_time": "0:42:05", "throughput": 2627.83, "total_tokens": 3590488} {"current_steps": 13400, "total_steps": 38150, "loss": 0.3224, "lr": 4.098806340212106e-05, "epoch": 3.512450851900393, "percentage": 35.12, "elapsed_time": "0:22:46", "remaining_time": "0:42:04", "throughput": 2627.85, "total_tokens": 3591640} {"current_steps": 13405, "total_steps": 38150, "loss": 0.3487, "lr": 4.097926906303744e-05, "epoch": 3.5137614678899083, "percentage": 35.14, "elapsed_time": "0:22:47", "remaining_time": "0:42:03", "throughput": 2627.88, "total_tokens": 3592904} {"current_steps": 13410, "total_steps": 38150, "loss": 0.4647, "lr": 4.0970471379520414e-05, "epoch": 3.5150720838794234, "percentage": 35.15, "elapsed_time": "0:22:47", "remaining_time": "0:42:03", "throughput": 2628.19, "total_tokens": 3594712} {"current_steps": 13415, "total_steps": 38150, "loss": 0.3464, "lr": 4.096167035341132e-05, "epoch": 3.5163826998689385, "percentage": 35.16, "elapsed_time": "0:22:48", "remaining_time": "0:42:02", "throughput": 2628.24, "total_tokens": 3595896} {"current_steps": 13420, "total_steps": 38150, "loss": 0.4442, "lr": 4.09528659865522e-05, "epoch": 3.5176933158584536, "percentage": 35.18, "elapsed_time": "0:22:48", "remaining_time": "0:42:02", "throughput": 2628.43, "total_tokens": 3597416} {"current_steps": 13425, "total_steps": 38150, "loss": 0.4448, "lr": 4.094405828078579e-05, "epoch": 3.5190039318479687, "percentage": 35.19, "elapsed_time": "0:22:49", "remaining_time": "0:42:01", "throughput": 2628.51, "total_tokens": 3598664} {"current_steps": 13430, "total_steps": 38150, "loss": 0.4974, "lr": 4.093524723795554e-05, "epoch": 3.5203145478374838, "percentage": 35.2, "elapsed_time": "0:22:49", "remaining_time": "0:42:00", "throughput": 2628.51, "total_tokens": 3599784} {"current_steps": 13435, "total_steps": 38150, "loss": 0.4703, "lr": 4.0926432859905574e-05, "epoch": 3.5216251638269984, "percentage": 35.22, "elapsed_time": "0:22:49", "remaining_time": "0:42:00", "throughput": 2628.77, "total_tokens": 3601336} {"current_steps": 13440, "total_steps": 38150, "loss": 0.374, "lr": 4.0917615148480726e-05, "epoch": 3.522935779816514, "percentage": 35.23, "elapsed_time": "0:22:50", "remaining_time": "0:41:59", "throughput": 2629.04, "total_tokens": 3602968} {"current_steps": 13445, "total_steps": 38150, "loss": 0.422, "lr": 4.0908794105526537e-05, "epoch": 3.5242463958060286, "percentage": 35.24, "elapsed_time": "0:22:50", "remaining_time": "0:41:58", "throughput": 2629.18, "total_tokens": 3604312} {"current_steps": 13450, "total_steps": 38150, "loss": 0.4349, "lr": 4.089996973288922e-05, "epoch": 3.525557011795544, "percentage": 35.26, "elapsed_time": "0:22:51", "remaining_time": "0:41:58", "throughput": 2629.29, "total_tokens": 3605608} {"current_steps": 13455, "total_steps": 38150, "loss": 0.4601, "lr": 4.089114203241572e-05, "epoch": 3.526867627785059, "percentage": 35.27, "elapsed_time": "0:22:51", "remaining_time": "0:41:57", "throughput": 2629.64, "total_tokens": 3607448} {"current_steps": 13460, "total_steps": 38150, "loss": 0.4398, "lr": 4.088231100595364e-05, "epoch": 3.528178243774574, "percentage": 35.28, "elapsed_time": "0:22:52", "remaining_time": "0:41:57", "throughput": 2629.69, "total_tokens": 3608728} {"current_steps": 13465, "total_steps": 38150, "loss": 0.342, "lr": 4.087347665535133e-05, "epoch": 3.529488859764089, "percentage": 35.29, "elapsed_time": "0:22:52", "remaining_time": "0:41:56", "throughput": 2629.73, "total_tokens": 3609896} {"current_steps": 13470, "total_steps": 38150, "loss": 0.3974, "lr": 4.0864638982457766e-05, "epoch": 3.530799475753604, "percentage": 35.31, "elapsed_time": "0:22:53", "remaining_time": "0:41:55", "throughput": 2629.77, "total_tokens": 3611064} {"current_steps": 13475, "total_steps": 38150, "loss": 0.3438, "lr": 4.085579798912268e-05, "epoch": 3.532110091743119, "percentage": 35.32, "elapsed_time": "0:22:53", "remaining_time": "0:41:55", "throughput": 2629.78, "total_tokens": 3612280} {"current_steps": 13480, "total_steps": 38150, "loss": 0.4579, "lr": 4.084695367719647e-05, "epoch": 3.5334207077326343, "percentage": 35.33, "elapsed_time": "0:22:54", "remaining_time": "0:41:54", "throughput": 2629.83, "total_tokens": 3613464} {"current_steps": 13485, "total_steps": 38150, "loss": 0.4044, "lr": 4.083810604853023e-05, "epoch": 3.5347313237221494, "percentage": 35.35, "elapsed_time": "0:22:54", "remaining_time": "0:41:54", "throughput": 2629.97, "total_tokens": 3614936} {"current_steps": 13490, "total_steps": 38150, "loss": 0.3332, "lr": 4.082925510497577e-05, "epoch": 3.5360419397116645, "percentage": 35.36, "elapsed_time": "0:22:54", "remaining_time": "0:41:53", "throughput": 2630.0, "total_tokens": 3616232} {"current_steps": 13495, "total_steps": 38150, "loss": 0.2313, "lr": 4.0820400848385564e-05, "epoch": 3.5373525557011796, "percentage": 35.37, "elapsed_time": "0:22:55", "remaining_time": "0:41:52", "throughput": 2629.8, "total_tokens": 3617048} {"current_steps": 13500, "total_steps": 38150, "loss": 0.4266, "lr": 4.0811543280612805e-05, "epoch": 3.5386631716906947, "percentage": 35.39, "elapsed_time": "0:22:55", "remaining_time": "0:41:52", "throughput": 2629.94, "total_tokens": 3618440} {"current_steps": 13505, "total_steps": 38150, "loss": 0.5347, "lr": 4.080268240351135e-05, "epoch": 3.5399737876802098, "percentage": 35.4, "elapsed_time": "0:22:56", "remaining_time": "0:41:51", "throughput": 2630.01, "total_tokens": 3619800} {"current_steps": 13510, "total_steps": 38150, "loss": 0.3309, "lr": 4.079381821893576e-05, "epoch": 3.541284403669725, "percentage": 35.41, "elapsed_time": "0:22:56", "remaining_time": "0:41:51", "throughput": 2630.05, "total_tokens": 3620984} {"current_steps": 13515, "total_steps": 38150, "loss": 0.3331, "lr": 4.078495072874132e-05, "epoch": 3.54259501965924, "percentage": 35.43, "elapsed_time": "0:22:57", "remaining_time": "0:41:50", "throughput": 2629.95, "total_tokens": 3621960} {"current_steps": 13520, "total_steps": 38150, "loss": 0.2528, "lr": 4.0776079934783975e-05, "epoch": 3.543905635648755, "percentage": 35.44, "elapsed_time": "0:22:57", "remaining_time": "0:41:49", "throughput": 2629.91, "total_tokens": 3623016} {"current_steps": 13525, "total_steps": 38150, "loss": 0.417, "lr": 4.076720583892034e-05, "epoch": 3.54521625163827, "percentage": 35.45, "elapsed_time": "0:22:58", "remaining_time": "0:41:49", "throughput": 2630.08, "total_tokens": 3624408} {"current_steps": 13530, "total_steps": 38150, "loss": 0.3921, "lr": 4.075832844300778e-05, "epoch": 3.546526867627785, "percentage": 35.47, "elapsed_time": "0:22:58", "remaining_time": "0:41:48", "throughput": 2630.1, "total_tokens": 3625624} {"current_steps": 13535, "total_steps": 38150, "loss": 0.3543, "lr": 4.0749447748904304e-05, "epoch": 3.5478374836173003, "percentage": 35.48, "elapsed_time": "0:22:58", "remaining_time": "0:41:47", "throughput": 2630.12, "total_tokens": 3626808} {"current_steps": 13540, "total_steps": 38150, "loss": 0.5306, "lr": 4.074056375846862e-05, "epoch": 3.549148099606815, "percentage": 35.49, "elapsed_time": "0:22:59", "remaining_time": "0:41:47", "throughput": 2630.19, "total_tokens": 3628104} {"current_steps": 13545, "total_steps": 38150, "loss": 0.3626, "lr": 4.0731676473560145e-05, "epoch": 3.5504587155963305, "percentage": 35.5, "elapsed_time": "0:22:59", "remaining_time": "0:41:46", "throughput": 2630.08, "total_tokens": 3629048} {"current_steps": 13550, "total_steps": 38150, "loss": 0.4778, "lr": 4.072278589603896e-05, "epoch": 3.551769331585845, "percentage": 35.52, "elapsed_time": "0:23:00", "remaining_time": "0:41:45", "throughput": 2630.26, "total_tokens": 3630536} {"current_steps": 13555, "total_steps": 38150, "loss": 0.2788, "lr": 4.0713892027765863e-05, "epoch": 3.5530799475753603, "percentage": 35.53, "elapsed_time": "0:23:00", "remaining_time": "0:41:45", "throughput": 2630.2, "total_tokens": 3631560} {"current_steps": 13560, "total_steps": 38150, "loss": 0.3451, "lr": 4.070499487060231e-05, "epoch": 3.5543905635648754, "percentage": 35.54, "elapsed_time": "0:23:01", "remaining_time": "0:41:44", "throughput": 2630.22, "total_tokens": 3632712} {"current_steps": 13565, "total_steps": 38150, "loss": 0.4575, "lr": 4.069609442641046e-05, "epoch": 3.5557011795543905, "percentage": 35.56, "elapsed_time": "0:23:01", "remaining_time": "0:41:44", "throughput": 2630.31, "total_tokens": 3634088} {"current_steps": 13570, "total_steps": 38150, "loss": 0.5027, "lr": 4.068719069705318e-05, "epoch": 3.5570117955439056, "percentage": 35.57, "elapsed_time": "0:23:02", "remaining_time": "0:41:43", "throughput": 2630.43, "total_tokens": 3635480} {"current_steps": 13575, "total_steps": 38150, "loss": 0.519, "lr": 4.0678283684393995e-05, "epoch": 3.5583224115334207, "percentage": 35.58, "elapsed_time": "0:23:02", "remaining_time": "0:41:42", "throughput": 2630.64, "total_tokens": 3637080} {"current_steps": 13580, "total_steps": 38150, "loss": 0.4761, "lr": 4.0669373390297115e-05, "epoch": 3.5596330275229358, "percentage": 35.6, "elapsed_time": "0:23:03", "remaining_time": "0:41:42", "throughput": 2630.66, "total_tokens": 3638248} {"current_steps": 13585, "total_steps": 38150, "loss": 0.3503, "lr": 4.066045981662746e-05, "epoch": 3.560943643512451, "percentage": 35.61, "elapsed_time": "0:23:03", "remaining_time": "0:41:41", "throughput": 2630.73, "total_tokens": 3639448} {"current_steps": 13590, "total_steps": 38150, "loss": 0.3341, "lr": 4.065154296525063e-05, "epoch": 3.562254259501966, "percentage": 35.62, "elapsed_time": "0:23:03", "remaining_time": "0:41:40", "throughput": 2630.77, "total_tokens": 3640648} {"current_steps": 13595, "total_steps": 38150, "loss": 0.3498, "lr": 4.064262283803289e-05, "epoch": 3.563564875491481, "percentage": 35.64, "elapsed_time": "0:23:04", "remaining_time": "0:41:40", "throughput": 2630.94, "total_tokens": 3642120} {"current_steps": 13600, "total_steps": 38150, "loss": 0.4661, "lr": 4.0633699436841224e-05, "epoch": 3.564875491480996, "percentage": 35.65, "elapsed_time": "0:23:04", "remaining_time": "0:41:39", "throughput": 2630.92, "total_tokens": 3643208} {"current_steps": 13605, "total_steps": 38150, "loss": 0.3659, "lr": 4.062477276354328e-05, "epoch": 3.5661861074705112, "percentage": 35.66, "elapsed_time": "0:23:05", "remaining_time": "0:41:39", "throughput": 2631.09, "total_tokens": 3644776} {"current_steps": 13610, "total_steps": 38150, "loss": 0.3944, "lr": 4.06158428200074e-05, "epoch": 3.5674967234600263, "percentage": 35.67, "elapsed_time": "0:23:05", "remaining_time": "0:41:38", "throughput": 2631.13, "total_tokens": 3646056} {"current_steps": 13615, "total_steps": 38150, "loss": 0.402, "lr": 4.0606909608102595e-05, "epoch": 3.5688073394495414, "percentage": 35.69, "elapsed_time": "0:23:06", "remaining_time": "0:41:38", "throughput": 2631.42, "total_tokens": 3647800} {"current_steps": 13620, "total_steps": 38150, "loss": 0.4091, "lr": 4.059797312969857e-05, "epoch": 3.5701179554390565, "percentage": 35.7, "elapsed_time": "0:23:06", "remaining_time": "0:41:37", "throughput": 2631.61, "total_tokens": 3649240} {"current_steps": 13625, "total_steps": 38150, "loss": 0.4816, "lr": 4.058903338666573e-05, "epoch": 3.571428571428571, "percentage": 35.71, "elapsed_time": "0:23:07", "remaining_time": "0:41:36", "throughput": 2631.75, "total_tokens": 3650568} {"current_steps": 13630, "total_steps": 38150, "loss": 0.4822, "lr": 4.058009038087513e-05, "epoch": 3.5727391874180867, "percentage": 35.73, "elapsed_time": "0:23:07", "remaining_time": "0:41:36", "throughput": 2631.89, "total_tokens": 3652056} {"current_steps": 13635, "total_steps": 38150, "loss": 0.3147, "lr": 4.0571144114198536e-05, "epoch": 3.5740498034076014, "percentage": 35.74, "elapsed_time": "0:23:08", "remaining_time": "0:41:35", "throughput": 2631.84, "total_tokens": 3653128} {"current_steps": 13640, "total_steps": 38150, "loss": 0.4863, "lr": 4.056219458850838e-05, "epoch": 3.575360419397117, "percentage": 35.75, "elapsed_time": "0:23:08", "remaining_time": "0:41:35", "throughput": 2632.04, "total_tokens": 3654648} {"current_steps": 13645, "total_steps": 38150, "loss": 0.3349, "lr": 4.05532418056778e-05, "epoch": 3.5766710353866316, "percentage": 35.77, "elapsed_time": "0:23:08", "remaining_time": "0:41:34", "throughput": 2632.07, "total_tokens": 3655896} {"current_steps": 13650, "total_steps": 38150, "loss": 0.3856, "lr": 4.054428576758057e-05, "epoch": 3.5779816513761467, "percentage": 35.78, "elapsed_time": "0:23:09", "remaining_time": "0:41:33", "throughput": 2632.3, "total_tokens": 3657624} {"current_steps": 13655, "total_steps": 38150, "loss": 0.2934, "lr": 4.053532647609119e-05, "epoch": 3.5792922673656618, "percentage": 35.79, "elapsed_time": "0:23:09", "remaining_time": "0:41:33", "throughput": 2632.35, "total_tokens": 3658808} {"current_steps": 13660, "total_steps": 38150, "loss": 0.5789, "lr": 4.0526363933084824e-05, "epoch": 3.580602883355177, "percentage": 35.81, "elapsed_time": "0:23:10", "remaining_time": "0:41:32", "throughput": 2632.39, "total_tokens": 3660088} {"current_steps": 13665, "total_steps": 38150, "loss": 0.2108, "lr": 4.051739814043731e-05, "epoch": 3.581913499344692, "percentage": 35.82, "elapsed_time": "0:23:10", "remaining_time": "0:41:32", "throughput": 2632.35, "total_tokens": 3661160} {"current_steps": 13670, "total_steps": 38150, "loss": 0.4389, "lr": 4.0508429100025185e-05, "epoch": 3.583224115334207, "percentage": 35.83, "elapsed_time": "0:23:11", "remaining_time": "0:41:31", "throughput": 2632.44, "total_tokens": 3662424} {"current_steps": 13675, "total_steps": 38150, "loss": 0.3331, "lr": 4.049945681372565e-05, "epoch": 3.584534731323722, "percentage": 35.85, "elapsed_time": "0:23:11", "remaining_time": "0:41:30", "throughput": 2632.47, "total_tokens": 3663656} {"current_steps": 13680, "total_steps": 38150, "loss": 0.2565, "lr": 4.049048128341657e-05, "epoch": 3.5858453473132372, "percentage": 35.86, "elapsed_time": "0:23:12", "remaining_time": "0:41:30", "throughput": 2632.42, "total_tokens": 3664712} {"current_steps": 13685, "total_steps": 38150, "loss": 0.4023, "lr": 4.048150251097653e-05, "epoch": 3.5871559633027523, "percentage": 35.87, "elapsed_time": "0:23:12", "remaining_time": "0:41:29", "throughput": 2632.67, "total_tokens": 3666312} {"current_steps": 13690, "total_steps": 38150, "loss": 0.3888, "lr": 4.047252049828476e-05, "epoch": 3.5884665792922674, "percentage": 35.88, "elapsed_time": "0:23:13", "remaining_time": "0:41:28", "throughput": 2632.58, "total_tokens": 3667304} {"current_steps": 13695, "total_steps": 38150, "loss": 0.3845, "lr": 4.046353524722119e-05, "epoch": 3.5897771952817825, "percentage": 35.9, "elapsed_time": "0:23:13", "remaining_time": "0:41:28", "throughput": 2632.52, "total_tokens": 3668328} {"current_steps": 13700, "total_steps": 38150, "loss": 0.5451, "lr": 4.0454546759666414e-05, "epoch": 3.5910878112712976, "percentage": 35.91, "elapsed_time": "0:23:13", "remaining_time": "0:41:27", "throughput": 2632.53, "total_tokens": 3669464} {"current_steps": 13705, "total_steps": 38150, "loss": 0.3157, "lr": 4.04455550375017e-05, "epoch": 3.5923984272608127, "percentage": 35.92, "elapsed_time": "0:23:14", "remaining_time": "0:41:26", "throughput": 2632.54, "total_tokens": 3670584} {"current_steps": 13710, "total_steps": 38150, "loss": 0.4267, "lr": 4.0436560082609e-05, "epoch": 3.593709043250328, "percentage": 35.94, "elapsed_time": "0:23:14", "remaining_time": "0:41:26", "throughput": 2632.46, "total_tokens": 3671592} {"current_steps": 13715, "total_steps": 38150, "loss": 0.4472, "lr": 4.0427561896870955e-05, "epoch": 3.595019659239843, "percentage": 35.95, "elapsed_time": "0:23:15", "remaining_time": "0:41:25", "throughput": 2632.63, "total_tokens": 3673048} {"current_steps": 13720, "total_steps": 38150, "loss": 0.5738, "lr": 4.041856048217085e-05, "epoch": 3.5963302752293576, "percentage": 35.96, "elapsed_time": "0:23:15", "remaining_time": "0:41:25", "throughput": 2632.78, "total_tokens": 3674568} {"current_steps": 13725, "total_steps": 38150, "loss": 0.4093, "lr": 4.040955584039269e-05, "epoch": 3.597640891218873, "percentage": 35.98, "elapsed_time": "0:23:16", "remaining_time": "0:41:24", "throughput": 2632.72, "total_tokens": 3675608} {"current_steps": 13730, "total_steps": 38150, "loss": 0.3541, "lr": 4.040054797342112e-05, "epoch": 3.5989515072083877, "percentage": 35.99, "elapsed_time": "0:23:16", "remaining_time": "0:41:23", "throughput": 2632.77, "total_tokens": 3676872} {"current_steps": 13735, "total_steps": 38150, "loss": 0.3001, "lr": 4.039153688314145e-05, "epoch": 3.6002621231979033, "percentage": 36.0, "elapsed_time": "0:23:17", "remaining_time": "0:41:23", "throughput": 2632.91, "total_tokens": 3678360} {"current_steps": 13740, "total_steps": 38150, "loss": 0.3875, "lr": 4.038252257143973e-05, "epoch": 3.601572739187418, "percentage": 36.02, "elapsed_time": "0:23:17", "remaining_time": "0:41:22", "throughput": 2633.14, "total_tokens": 3679992} {"current_steps": 13745, "total_steps": 38150, "loss": 0.4495, "lr": 4.03735050402026e-05, "epoch": 3.602883355176933, "percentage": 36.03, "elapsed_time": "0:23:18", "remaining_time": "0:41:22", "throughput": 2633.55, "total_tokens": 3682120} {"current_steps": 13750, "total_steps": 38150, "loss": 0.3637, "lr": 4.036448429131743e-05, "epoch": 3.604193971166448, "percentage": 36.04, "elapsed_time": "0:23:18", "remaining_time": "0:41:21", "throughput": 2633.69, "total_tokens": 3683480} {"current_steps": 13755, "total_steps": 38150, "loss": 0.3792, "lr": 4.035546032667225e-05, "epoch": 3.6055045871559632, "percentage": 36.06, "elapsed_time": "0:23:19", "remaining_time": "0:41:21", "throughput": 2633.97, "total_tokens": 3685368} {"current_steps": 13760, "total_steps": 38150, "loss": 0.5745, "lr": 4.034643314815575e-05, "epoch": 3.6068152031454783, "percentage": 36.07, "elapsed_time": "0:23:19", "remaining_time": "0:41:20", "throughput": 2634.01, "total_tokens": 3686552} {"current_steps": 13765, "total_steps": 38150, "loss": 0.371, "lr": 4.0337402757657314e-05, "epoch": 3.6081258191349934, "percentage": 36.08, "elapsed_time": "0:23:20", "remaining_time": "0:41:20", "throughput": 2634.09, "total_tokens": 3687816} {"current_steps": 13770, "total_steps": 38150, "loss": 0.3458, "lr": 4.032836915706698e-05, "epoch": 3.6094364351245085, "percentage": 36.09, "elapsed_time": "0:23:20", "remaining_time": "0:41:19", "throughput": 2634.23, "total_tokens": 3689176} {"current_steps": 13775, "total_steps": 38150, "loss": 0.3531, "lr": 4.0319332348275465e-05, "epoch": 3.6107470511140236, "percentage": 36.11, "elapsed_time": "0:23:20", "remaining_time": "0:41:18", "throughput": 2634.18, "total_tokens": 3690232} {"current_steps": 13780, "total_steps": 38150, "loss": 0.331, "lr": 4.031029233317416e-05, "epoch": 3.6120576671035387, "percentage": 36.12, "elapsed_time": "0:23:21", "remaining_time": "0:41:18", "throughput": 2634.25, "total_tokens": 3691480} {"current_steps": 13785, "total_steps": 38150, "loss": 0.4524, "lr": 4.0301249113655125e-05, "epoch": 3.613368283093054, "percentage": 36.13, "elapsed_time": "0:23:21", "remaining_time": "0:41:17", "throughput": 2634.46, "total_tokens": 3693016} {"current_steps": 13790, "total_steps": 38150, "loss": 0.3734, "lr": 4.0292202691611094e-05, "epoch": 3.614678899082569, "percentage": 36.15, "elapsed_time": "0:23:22", "remaining_time": "0:41:17", "throughput": 2634.46, "total_tokens": 3694136} {"current_steps": 13795, "total_steps": 38150, "loss": 0.5623, "lr": 4.028315306893545e-05, "epoch": 3.615989515072084, "percentage": 36.16, "elapsed_time": "0:23:22", "remaining_time": "0:41:16", "throughput": 2634.68, "total_tokens": 3695672} {"current_steps": 13800, "total_steps": 38150, "loss": 0.3129, "lr": 4.0274100247522287e-05, "epoch": 3.617300131061599, "percentage": 36.17, "elapsed_time": "0:23:23", "remaining_time": "0:41:15", "throughput": 2634.82, "total_tokens": 3697032} {"current_steps": 13805, "total_steps": 38150, "loss": 0.3507, "lr": 4.026504422926632e-05, "epoch": 3.618610747051114, "percentage": 36.19, "elapsed_time": "0:23:23", "remaining_time": "0:41:15", "throughput": 2634.79, "total_tokens": 3698088} {"current_steps": 13810, "total_steps": 38150, "loss": 0.3867, "lr": 4.025598501606299e-05, "epoch": 3.6199213630406293, "percentage": 36.2, "elapsed_time": "0:23:24", "remaining_time": "0:41:14", "throughput": 2634.98, "total_tokens": 3699624} {"current_steps": 13815, "total_steps": 38150, "loss": 0.3851, "lr": 4.024692260980835e-05, "epoch": 3.621231979030144, "percentage": 36.21, "elapsed_time": "0:23:24", "remaining_time": "0:41:14", "throughput": 2635.13, "total_tokens": 3701080} {"current_steps": 13820, "total_steps": 38150, "loss": 0.4054, "lr": 4.023785701239915e-05, "epoch": 3.6225425950196595, "percentage": 36.23, "elapsed_time": "0:23:24", "remaining_time": "0:41:13", "throughput": 2635.06, "total_tokens": 3702088} {"current_steps": 13825, "total_steps": 38150, "loss": 0.3359, "lr": 4.022878822573281e-05, "epoch": 3.623853211009174, "percentage": 36.24, "elapsed_time": "0:23:25", "remaining_time": "0:41:12", "throughput": 2635.05, "total_tokens": 3703224} {"current_steps": 13830, "total_steps": 38150, "loss": 0.4456, "lr": 4.0219716251707395e-05, "epoch": 3.625163826998689, "percentage": 36.25, "elapsed_time": "0:23:25", "remaining_time": "0:41:12", "throughput": 2635.17, "total_tokens": 3704520} {"current_steps": 13835, "total_steps": 38150, "loss": 0.2641, "lr": 4.021064109222168e-05, "epoch": 3.6264744429882043, "percentage": 36.26, "elapsed_time": "0:23:26", "remaining_time": "0:41:11", "throughput": 2635.56, "total_tokens": 3706584} {"current_steps": 13840, "total_steps": 38150, "loss": 0.5227, "lr": 4.020156274917506e-05, "epoch": 3.6277850589777194, "percentage": 36.28, "elapsed_time": "0:23:26", "remaining_time": "0:41:11", "throughput": 2635.81, "total_tokens": 3708200} {"current_steps": 13845, "total_steps": 38150, "loss": 0.3542, "lr": 4.019248122446763e-05, "epoch": 3.6290956749672345, "percentage": 36.29, "elapsed_time": "0:23:27", "remaining_time": "0:41:10", "throughput": 2635.95, "total_tokens": 3709560} {"current_steps": 13850, "total_steps": 38150, "loss": 0.5539, "lr": 4.0183396520000114e-05, "epoch": 3.6304062909567496, "percentage": 36.3, "elapsed_time": "0:23:27", "remaining_time": "0:41:09", "throughput": 2636.12, "total_tokens": 3710952} {"current_steps": 13855, "total_steps": 38150, "loss": 0.5472, "lr": 4.0174308637673956e-05, "epoch": 3.6317169069462647, "percentage": 36.32, "elapsed_time": "0:23:28", "remaining_time": "0:41:09", "throughput": 2636.3, "total_tokens": 3712392} {"current_steps": 13860, "total_steps": 38150, "loss": 0.494, "lr": 4.016521757939121e-05, "epoch": 3.63302752293578, "percentage": 36.33, "elapsed_time": "0:23:28", "remaining_time": "0:41:08", "throughput": 2636.29, "total_tokens": 3713464} {"current_steps": 13865, "total_steps": 38150, "loss": 0.3408, "lr": 4.015612334705464e-05, "epoch": 3.634338138925295, "percentage": 36.34, "elapsed_time": "0:23:29", "remaining_time": "0:41:08", "throughput": 2636.46, "total_tokens": 3714968} {"current_steps": 13870, "total_steps": 38150, "loss": 0.5619, "lr": 4.014702594256764e-05, "epoch": 3.63564875491481, "percentage": 36.36, "elapsed_time": "0:23:29", "remaining_time": "0:41:07", "throughput": 2636.55, "total_tokens": 3716248} {"current_steps": 13875, "total_steps": 38150, "loss": 0.4333, "lr": 4.013792536783427e-05, "epoch": 3.636959370904325, "percentage": 36.37, "elapsed_time": "0:23:30", "remaining_time": "0:41:06", "throughput": 2636.68, "total_tokens": 3717736} {"current_steps": 13880, "total_steps": 38150, "loss": 0.4496, "lr": 4.012882162475928e-05, "epoch": 3.63826998689384, "percentage": 36.38, "elapsed_time": "0:23:30", "remaining_time": "0:41:06", "throughput": 2636.71, "total_tokens": 3718904} {"current_steps": 13885, "total_steps": 38150, "loss": 0.3186, "lr": 4.011971471524807e-05, "epoch": 3.6395806028833553, "percentage": 36.4, "elapsed_time": "0:23:30", "remaining_time": "0:41:05", "throughput": 2636.76, "total_tokens": 3720104} {"current_steps": 13890, "total_steps": 38150, "loss": 0.3688, "lr": 4.011060464120669e-05, "epoch": 3.6408912188728704, "percentage": 36.41, "elapsed_time": "0:23:31", "remaining_time": "0:41:04", "throughput": 2636.79, "total_tokens": 3721288} {"current_steps": 13895, "total_steps": 38150, "loss": 0.4019, "lr": 4.010149140454188e-05, "epoch": 3.6422018348623855, "percentage": 36.42, "elapsed_time": "0:23:31", "remaining_time": "0:41:04", "throughput": 2636.96, "total_tokens": 3722856} {"current_steps": 13900, "total_steps": 38150, "loss": 0.3515, "lr": 4.009237500716101e-05, "epoch": 3.6435124508519, "percentage": 36.44, "elapsed_time": "0:23:32", "remaining_time": "0:41:03", "throughput": 2637.12, "total_tokens": 3724264} {"current_steps": 13905, "total_steps": 38150, "loss": 0.1809, "lr": 4.008325545097212e-05, "epoch": 3.6448230668414157, "percentage": 36.45, "elapsed_time": "0:23:32", "remaining_time": "0:41:03", "throughput": 2637.17, "total_tokens": 3725528} {"current_steps": 13910, "total_steps": 38150, "loss": 0.4193, "lr": 4.0074132737883927e-05, "epoch": 3.6461336828309303, "percentage": 36.46, "elapsed_time": "0:23:33", "remaining_time": "0:41:02", "throughput": 2637.31, "total_tokens": 3726888} {"current_steps": 13915, "total_steps": 38150, "loss": 0.5271, "lr": 4.00650068698058e-05, "epoch": 3.647444298820446, "percentage": 36.47, "elapsed_time": "0:23:33", "remaining_time": "0:41:02", "throughput": 2637.4, "total_tokens": 3728472} {"current_steps": 13920, "total_steps": 38150, "loss": 0.4862, "lr": 4.005587784864776e-05, "epoch": 3.6487549148099605, "percentage": 36.49, "elapsed_time": "0:23:34", "remaining_time": "0:41:01", "throughput": 2637.48, "total_tokens": 3729704} {"current_steps": 13925, "total_steps": 38150, "loss": 0.3618, "lr": 4.0046745676320504e-05, "epoch": 3.6500655307994756, "percentage": 36.5, "elapsed_time": "0:23:34", "remaining_time": "0:41:00", "throughput": 2637.58, "total_tokens": 3731144} {"current_steps": 13930, "total_steps": 38150, "loss": 0.4771, "lr": 4.003761035473538e-05, "epoch": 3.6513761467889907, "percentage": 36.51, "elapsed_time": "0:23:35", "remaining_time": "0:41:00", "throughput": 2637.62, "total_tokens": 3732456} {"current_steps": 13935, "total_steps": 38150, "loss": 0.4796, "lr": 4.002847188580439e-05, "epoch": 3.652686762778506, "percentage": 36.53, "elapsed_time": "0:23:35", "remaining_time": "0:40:59", "throughput": 2637.97, "total_tokens": 3734312} {"current_steps": 13940, "total_steps": 38150, "loss": 0.4003, "lr": 4.0019330271440206e-05, "epoch": 3.653997378768021, "percentage": 36.54, "elapsed_time": "0:23:36", "remaining_time": "0:40:59", "throughput": 2638.22, "total_tokens": 3735944} {"current_steps": 13945, "total_steps": 38150, "loss": 0.3611, "lr": 4.001018551355614e-05, "epoch": 3.655307994757536, "percentage": 36.55, "elapsed_time": "0:23:36", "remaining_time": "0:40:58", "throughput": 2638.32, "total_tokens": 3737304} {"current_steps": 13950, "total_steps": 38150, "loss": 0.3251, "lr": 4.0001037614066184e-05, "epoch": 3.656618610747051, "percentage": 36.57, "elapsed_time": "0:23:37", "remaining_time": "0:40:58", "throughput": 2638.43, "total_tokens": 3738696} {"current_steps": 13955, "total_steps": 38150, "loss": 0.4176, "lr": 3.9991886574884975e-05, "epoch": 3.657929226736566, "percentage": 36.58, "elapsed_time": "0:23:37", "remaining_time": "0:40:57", "throughput": 2638.4, "total_tokens": 3739752} {"current_steps": 13960, "total_steps": 38150, "loss": 0.4406, "lr": 3.998273239792781e-05, "epoch": 3.6592398427260813, "percentage": 36.59, "elapsed_time": "0:23:37", "remaining_time": "0:40:56", "throughput": 2638.58, "total_tokens": 3741176} {"current_steps": 13965, "total_steps": 38150, "loss": 0.39, "lr": 3.997357508511064e-05, "epoch": 3.6605504587155964, "percentage": 36.61, "elapsed_time": "0:23:38", "remaining_time": "0:40:56", "throughput": 2638.67, "total_tokens": 3742472} {"current_steps": 13970, "total_steps": 38150, "loss": 0.4158, "lr": 3.996441463835008e-05, "epoch": 3.6618610747051115, "percentage": 36.62, "elapsed_time": "0:23:38", "remaining_time": "0:40:55", "throughput": 2638.65, "total_tokens": 3743592} {"current_steps": 13975, "total_steps": 38150, "loss": 0.3284, "lr": 3.995525105956339e-05, "epoch": 3.6631716906946266, "percentage": 36.63, "elapsed_time": "0:23:39", "remaining_time": "0:40:55", "throughput": 2638.75, "total_tokens": 3744888} {"current_steps": 13980, "total_steps": 38150, "loss": 0.4235, "lr": 3.9946084350668506e-05, "epoch": 3.6644823066841417, "percentage": 36.64, "elapsed_time": "0:23:39", "remaining_time": "0:40:54", "throughput": 2638.68, "total_tokens": 3745928} {"current_steps": 13985, "total_steps": 38150, "loss": 0.4785, "lr": 3.993691451358398e-05, "epoch": 3.6657929226736568, "percentage": 36.66, "elapsed_time": "0:23:40", "remaining_time": "0:40:53", "throughput": 2638.61, "total_tokens": 3746936} {"current_steps": 13990, "total_steps": 38150, "loss": 0.3556, "lr": 3.992774155022906e-05, "epoch": 3.667103538663172, "percentage": 36.67, "elapsed_time": "0:23:40", "remaining_time": "0:40:53", "throughput": 2638.87, "total_tokens": 3748600} {"current_steps": 13995, "total_steps": 38150, "loss": 0.4946, "lr": 3.991856546252362e-05, "epoch": 3.6684141546526865, "percentage": 36.68, "elapsed_time": "0:23:41", "remaining_time": "0:40:52", "throughput": 2639.04, "total_tokens": 3750104} {"current_steps": 14000, "total_steps": 38150, "loss": 0.3474, "lr": 3.9909386252388215e-05, "epoch": 3.669724770642202, "percentage": 36.7, "elapsed_time": "0:23:41", "remaining_time": "0:40:52", "throughput": 2639.28, "total_tokens": 3751752} {"current_steps": 14005, "total_steps": 38150, "loss": 0.317, "lr": 3.990020392174402e-05, "epoch": 3.6710353866317167, "percentage": 36.71, "elapsed_time": "0:23:41", "remaining_time": "0:40:51", "throughput": 2639.45, "total_tokens": 3753224} {"current_steps": 14010, "total_steps": 38150, "loss": 0.4909, "lr": 3.9891018472512895e-05, "epoch": 3.6723460026212322, "percentage": 36.72, "elapsed_time": "0:23:42", "remaining_time": "0:40:50", "throughput": 2639.4, "total_tokens": 3754280} {"current_steps": 14015, "total_steps": 38150, "loss": 0.3633, "lr": 3.988182990661734e-05, "epoch": 3.673656618610747, "percentage": 36.74, "elapsed_time": "0:23:42", "remaining_time": "0:40:50", "throughput": 2639.51, "total_tokens": 3755640} {"current_steps": 14020, "total_steps": 38150, "loss": 0.3745, "lr": 3.987263822598049e-05, "epoch": 3.674967234600262, "percentage": 36.75, "elapsed_time": "0:23:43", "remaining_time": "0:40:49", "throughput": 2639.65, "total_tokens": 3757064} {"current_steps": 14025, "total_steps": 38150, "loss": 0.3356, "lr": 3.986344343252615e-05, "epoch": 3.676277850589777, "percentage": 36.76, "elapsed_time": "0:23:43", "remaining_time": "0:40:49", "throughput": 2639.73, "total_tokens": 3758296} {"current_steps": 14030, "total_steps": 38150, "loss": 0.3327, "lr": 3.9854245528178804e-05, "epoch": 3.677588466579292, "percentage": 36.78, "elapsed_time": "0:23:44", "remaining_time": "0:40:48", "throughput": 2639.77, "total_tokens": 3759496} {"current_steps": 14035, "total_steps": 38150, "loss": 0.6242, "lr": 3.984504451486352e-05, "epoch": 3.6788990825688073, "percentage": 36.79, "elapsed_time": "0:23:44", "remaining_time": "0:40:47", "throughput": 2639.82, "total_tokens": 3760712} {"current_steps": 14040, "total_steps": 38150, "loss": 0.4212, "lr": 3.983584039450607e-05, "epoch": 3.6802096985583224, "percentage": 36.8, "elapsed_time": "0:23:45", "remaining_time": "0:40:47", "throughput": 2639.8, "total_tokens": 3761800} {"current_steps": 14045, "total_steps": 38150, "loss": 0.3058, "lr": 3.982663316903286e-05, "epoch": 3.6815203145478375, "percentage": 36.82, "elapsed_time": "0:23:45", "remaining_time": "0:40:46", "throughput": 2640.0, "total_tokens": 3763368} {"current_steps": 14050, "total_steps": 38150, "loss": 0.4311, "lr": 3.981742284037095e-05, "epoch": 3.6828309305373526, "percentage": 36.83, "elapsed_time": "0:23:45", "remaining_time": "0:40:45", "throughput": 2640.08, "total_tokens": 3764632} {"current_steps": 14055, "total_steps": 38150, "loss": 0.4396, "lr": 3.980820941044803e-05, "epoch": 3.6841415465268676, "percentage": 36.84, "elapsed_time": "0:23:46", "remaining_time": "0:40:45", "throughput": 2640.16, "total_tokens": 3765896} {"current_steps": 14060, "total_steps": 38150, "loss": 0.3214, "lr": 3.979899288119248e-05, "epoch": 3.6854521625163827, "percentage": 36.85, "elapsed_time": "0:23:46", "remaining_time": "0:40:44", "throughput": 2640.21, "total_tokens": 3767128} {"current_steps": 14065, "total_steps": 38150, "loss": 0.3134, "lr": 3.978977325453329e-05, "epoch": 3.686762778505898, "percentage": 36.87, "elapsed_time": "0:23:47", "remaining_time": "0:40:44", "throughput": 2640.15, "total_tokens": 3768136} {"current_steps": 14070, "total_steps": 38150, "loss": 0.3557, "lr": 3.9780550532400106e-05, "epoch": 3.688073394495413, "percentage": 36.88, "elapsed_time": "0:23:47", "remaining_time": "0:40:43", "throughput": 2640.03, "total_tokens": 3769048} {"current_steps": 14075, "total_steps": 38150, "loss": 0.385, "lr": 3.9771324716723246e-05, "epoch": 3.689384010484928, "percentage": 36.89, "elapsed_time": "0:23:48", "remaining_time": "0:40:42", "throughput": 2640.09, "total_tokens": 3770312} {"current_steps": 14080, "total_steps": 38150, "loss": 0.4749, "lr": 3.976209580943363e-05, "epoch": 3.690694626474443, "percentage": 36.91, "elapsed_time": "0:23:48", "remaining_time": "0:40:42", "throughput": 2640.01, "total_tokens": 3771304} {"current_steps": 14085, "total_steps": 38150, "loss": 0.4882, "lr": 3.975286381246288e-05, "epoch": 3.6920052424639582, "percentage": 36.92, "elapsed_time": "0:23:48", "remaining_time": "0:40:41", "throughput": 2640.11, "total_tokens": 3772616} {"current_steps": 14090, "total_steps": 38150, "loss": 0.4535, "lr": 3.9743628727743224e-05, "epoch": 3.693315858453473, "percentage": 36.93, "elapsed_time": "0:23:49", "remaining_time": "0:40:40", "throughput": 2640.04, "total_tokens": 3773704} {"current_steps": 14095, "total_steps": 38150, "loss": 0.3495, "lr": 3.973439055720755e-05, "epoch": 3.6946264744429884, "percentage": 36.95, "elapsed_time": "0:23:49", "remaining_time": "0:40:40", "throughput": 2639.98, "total_tokens": 3774728} {"current_steps": 14100, "total_steps": 38150, "loss": 0.8127, "lr": 3.972514930278938e-05, "epoch": 3.695937090432503, "percentage": 36.96, "elapsed_time": "0:23:50", "remaining_time": "0:40:39", "throughput": 2640.17, "total_tokens": 3776440} {"current_steps": 14105, "total_steps": 38150, "loss": 0.3512, "lr": 3.971590496642291e-05, "epoch": 3.6972477064220186, "percentage": 36.97, "elapsed_time": "0:23:50", "remaining_time": "0:40:39", "throughput": 2640.29, "total_tokens": 3777768} {"current_steps": 14110, "total_steps": 38150, "loss": 0.3671, "lr": 3.970665755004296e-05, "epoch": 3.6985583224115333, "percentage": 36.99, "elapsed_time": "0:23:51", "remaining_time": "0:40:38", "throughput": 2640.25, "total_tokens": 3778824} {"current_steps": 14115, "total_steps": 38150, "loss": 0.3141, "lr": 3.9697407055585e-05, "epoch": 3.6998689384010484, "percentage": 37.0, "elapsed_time": "0:23:51", "remaining_time": "0:40:37", "throughput": 2640.41, "total_tokens": 3780344} {"current_steps": 14120, "total_steps": 38150, "loss": 0.4146, "lr": 3.9688153484985135e-05, "epoch": 3.7011795543905635, "percentage": 37.01, "elapsed_time": "0:23:52", "remaining_time": "0:40:37", "throughput": 2640.37, "total_tokens": 3781384} {"current_steps": 14125, "total_steps": 38150, "loss": 1.8359, "lr": 3.9678896840180125e-05, "epoch": 3.7024901703800785, "percentage": 37.02, "elapsed_time": "0:23:52", "remaining_time": "0:40:36", "throughput": 2640.36, "total_tokens": 3782488} {"current_steps": 14130, "total_steps": 38150, "loss": 0.4738, "lr": 3.9669637123107374e-05, "epoch": 3.7038007863695936, "percentage": 37.04, "elapsed_time": "0:23:53", "remaining_time": "0:40:36", "throughput": 2640.72, "total_tokens": 3784408} {"current_steps": 14135, "total_steps": 38150, "loss": 0.4437, "lr": 3.9660374335704906e-05, "epoch": 3.7051114023591087, "percentage": 37.05, "elapsed_time": "0:23:53", "remaining_time": "0:40:35", "throughput": 2640.73, "total_tokens": 3785608} {"current_steps": 14140, "total_steps": 38150, "loss": 0.4589, "lr": 3.965110847991143e-05, "epoch": 3.706422018348624, "percentage": 37.06, "elapsed_time": "0:23:53", "remaining_time": "0:40:34", "throughput": 2640.74, "total_tokens": 3786712} {"current_steps": 14145, "total_steps": 38150, "loss": 0.4379, "lr": 3.964183955766627e-05, "epoch": 3.707732634338139, "percentage": 37.08, "elapsed_time": "0:23:54", "remaining_time": "0:40:34", "throughput": 2640.79, "total_tokens": 3787928} {"current_steps": 14150, "total_steps": 38150, "loss": 0.4182, "lr": 3.963256757090938e-05, "epoch": 3.709043250327654, "percentage": 37.09, "elapsed_time": "0:23:54", "remaining_time": "0:40:33", "throughput": 2640.95, "total_tokens": 3789480} {"current_steps": 14155, "total_steps": 38150, "loss": 0.218, "lr": 3.962329252158139e-05, "epoch": 3.710353866317169, "percentage": 37.1, "elapsed_time": "0:23:55", "remaining_time": "0:40:33", "throughput": 2641.02, "total_tokens": 3790696} {"current_steps": 14160, "total_steps": 38150, "loss": 0.3692, "lr": 3.961401441162354e-05, "epoch": 3.711664482306684, "percentage": 37.12, "elapsed_time": "0:23:55", "remaining_time": "0:40:32", "throughput": 2641.04, "total_tokens": 3791832} {"current_steps": 14165, "total_steps": 38150, "loss": 0.4894, "lr": 3.960473324297772e-05, "epoch": 3.7129750982961993, "percentage": 37.13, "elapsed_time": "0:23:56", "remaining_time": "0:40:31", "throughput": 2641.01, "total_tokens": 3792888} {"current_steps": 14170, "total_steps": 38150, "loss": 0.4315, "lr": 3.959544901758646e-05, "epoch": 3.7142857142857144, "percentage": 37.14, "elapsed_time": "0:23:56", "remaining_time": "0:40:31", "throughput": 2641.34, "total_tokens": 3794792} {"current_steps": 14175, "total_steps": 38150, "loss": 0.6587, "lr": 3.958616173739295e-05, "epoch": 3.7155963302752295, "percentage": 37.16, "elapsed_time": "0:23:57", "remaining_time": "0:40:30", "throughput": 2641.71, "total_tokens": 3796712} {"current_steps": 14180, "total_steps": 38150, "loss": 0.4677, "lr": 3.9576871404340994e-05, "epoch": 3.7169069462647446, "percentage": 37.17, "elapsed_time": "0:23:57", "remaining_time": "0:40:30", "throughput": 2641.71, "total_tokens": 3797896} {"current_steps": 14185, "total_steps": 38150, "loss": 0.6573, "lr": 3.9567578020375036e-05, "epoch": 3.7182175622542593, "percentage": 37.18, "elapsed_time": "0:23:58", "remaining_time": "0:40:29", "throughput": 2641.58, "total_tokens": 3798808} {"current_steps": 14190, "total_steps": 38150, "loss": 0.3764, "lr": 3.955828158744017e-05, "epoch": 3.719528178243775, "percentage": 37.2, "elapsed_time": "0:23:58", "remaining_time": "0:40:29", "throughput": 2641.69, "total_tokens": 3800264} {"current_steps": 14195, "total_steps": 38150, "loss": 0.3211, "lr": 3.954898210748211e-05, "epoch": 3.7208387942332894, "percentage": 37.21, "elapsed_time": "0:23:59", "remaining_time": "0:40:28", "throughput": 2642.0, "total_tokens": 3802008} {"current_steps": 14200, "total_steps": 38150, "loss": 0.3357, "lr": 3.953967958244725e-05, "epoch": 3.722149410222805, "percentage": 37.22, "elapsed_time": "0:23:59", "remaining_time": "0:40:27", "throughput": 2642.02, "total_tokens": 3803256} {"current_steps": 14205, "total_steps": 38150, "loss": 0.6069, "lr": 3.9530374014282574e-05, "epoch": 3.7234600262123196, "percentage": 37.23, "elapsed_time": "0:23:59", "remaining_time": "0:40:27", "throughput": 2642.11, "total_tokens": 3804504} {"current_steps": 14210, "total_steps": 38150, "loss": 0.4425, "lr": 3.952106540493572e-05, "epoch": 3.7247706422018347, "percentage": 37.25, "elapsed_time": "0:24:00", "remaining_time": "0:40:26", "throughput": 2642.45, "total_tokens": 3806424} {"current_steps": 14215, "total_steps": 38150, "loss": 0.2906, "lr": 3.951175375635497e-05, "epoch": 3.72608125819135, "percentage": 37.26, "elapsed_time": "0:24:00", "remaining_time": "0:40:26", "throughput": 2642.56, "total_tokens": 3807752} {"current_steps": 14220, "total_steps": 38150, "loss": 0.3971, "lr": 3.9502439070489224e-05, "epoch": 3.727391874180865, "percentage": 37.27, "elapsed_time": "0:24:01", "remaining_time": "0:40:25", "throughput": 2642.55, "total_tokens": 3808856} {"current_steps": 14225, "total_steps": 38150, "loss": 0.5236, "lr": 3.949312134928805e-05, "epoch": 3.72870249017038, "percentage": 37.29, "elapsed_time": "0:24:01", "remaining_time": "0:40:24", "throughput": 2642.59, "total_tokens": 3810040} {"current_steps": 14230, "total_steps": 38150, "loss": 0.372, "lr": 3.948380059470161e-05, "epoch": 3.730013106159895, "percentage": 37.3, "elapsed_time": "0:24:02", "remaining_time": "0:40:24", "throughput": 2642.64, "total_tokens": 3811224} {"current_steps": 14235, "total_steps": 38150, "loss": 0.6475, "lr": 3.947447680868074e-05, "epoch": 3.73132372214941, "percentage": 37.31, "elapsed_time": "0:24:02", "remaining_time": "0:40:23", "throughput": 2642.68, "total_tokens": 3812424} {"current_steps": 14240, "total_steps": 38150, "loss": 0.4377, "lr": 3.9465149993176885e-05, "epoch": 3.7326343381389253, "percentage": 37.33, "elapsed_time": "0:24:03", "remaining_time": "0:40:23", "throughput": 2642.7, "total_tokens": 3813576} {"current_steps": 14245, "total_steps": 38150, "loss": 0.3661, "lr": 3.945582015014212e-05, "epoch": 3.7339449541284404, "percentage": 37.34, "elapsed_time": "0:24:03", "remaining_time": "0:40:22", "throughput": 2642.61, "total_tokens": 3814536} {"current_steps": 14250, "total_steps": 38150, "loss": 0.3776, "lr": 3.944648728152919e-05, "epoch": 3.7352555701179555, "percentage": 37.35, "elapsed_time": "0:24:04", "remaining_time": "0:40:21", "throughput": 2642.92, "total_tokens": 3816504} {"current_steps": 14255, "total_steps": 38150, "loss": 0.4027, "lr": 3.943715138929142e-05, "epoch": 3.7365661861074706, "percentage": 37.37, "elapsed_time": "0:24:04", "remaining_time": "0:40:21", "throughput": 2642.92, "total_tokens": 3817640} {"current_steps": 14260, "total_steps": 38150, "loss": 0.4671, "lr": 3.942781247538282e-05, "epoch": 3.7378768020969857, "percentage": 37.38, "elapsed_time": "0:24:04", "remaining_time": "0:40:20", "throughput": 2642.87, "total_tokens": 3818696} {"current_steps": 14265, "total_steps": 38150, "loss": 0.2391, "lr": 3.941847054175799e-05, "epoch": 3.739187418086501, "percentage": 37.39, "elapsed_time": "0:24:05", "remaining_time": "0:40:20", "throughput": 2642.84, "total_tokens": 3819736} {"current_steps": 14270, "total_steps": 38150, "loss": 0.5816, "lr": 3.940912559037219e-05, "epoch": 3.740498034076016, "percentage": 37.4, "elapsed_time": "0:24:05", "remaining_time": "0:40:19", "throughput": 2643.01, "total_tokens": 3821256} {"current_steps": 14275, "total_steps": 38150, "loss": 0.4451, "lr": 3.939977762318131e-05, "epoch": 3.741808650065531, "percentage": 37.42, "elapsed_time": "0:24:06", "remaining_time": "0:40:18", "throughput": 2643.07, "total_tokens": 3822472} {"current_steps": 14280, "total_steps": 38150, "loss": 0.4163, "lr": 3.939042664214184e-05, "epoch": 3.7431192660550456, "percentage": 37.43, "elapsed_time": "0:24:06", "remaining_time": "0:40:18", "throughput": 2642.96, "total_tokens": 3823400} {"current_steps": 14285, "total_steps": 38150, "loss": 0.5399, "lr": 3.938107264921095e-05, "epoch": 3.744429882044561, "percentage": 37.44, "elapsed_time": "0:24:07", "remaining_time": "0:40:17", "throughput": 2642.93, "total_tokens": 3824472} {"current_steps": 14290, "total_steps": 38150, "loss": 0.2439, "lr": 3.9371715646346396e-05, "epoch": 3.745740498034076, "percentage": 37.46, "elapsed_time": "0:24:07", "remaining_time": "0:40:17", "throughput": 2643.3, "total_tokens": 3826408} {"current_steps": 14295, "total_steps": 38150, "loss": 0.4557, "lr": 3.936235563550659e-05, "epoch": 3.747051114023591, "percentage": 37.47, "elapsed_time": "0:24:08", "remaining_time": "0:40:16", "throughput": 2643.61, "total_tokens": 3828456} {"current_steps": 14300, "total_steps": 38150, "loss": 0.3607, "lr": 3.935299261865057e-05, "epoch": 3.748361730013106, "percentage": 37.48, "elapsed_time": "0:24:08", "remaining_time": "0:40:16", "throughput": 2643.64, "total_tokens": 3829640} {"current_steps": 14305, "total_steps": 38150, "loss": 0.3436, "lr": 3.934362659773799e-05, "epoch": 3.749672346002621, "percentage": 37.5, "elapsed_time": "0:24:09", "remaining_time": "0:40:15", "throughput": 2643.6, "total_tokens": 3830680} {"current_steps": 14310, "total_steps": 38150, "loss": 0.4396, "lr": 3.933425757472915e-05, "epoch": 3.750982961992136, "percentage": 37.51, "elapsed_time": "0:24:09", "remaining_time": "0:40:14", "throughput": 2643.58, "total_tokens": 3831768} {"current_steps": 14315, "total_steps": 38150, "loss": 0.493, "lr": 3.932488555158497e-05, "epoch": 3.7522935779816513, "percentage": 37.52, "elapsed_time": "0:24:09", "remaining_time": "0:40:14", "throughput": 2643.75, "total_tokens": 3833272} {"current_steps": 14320, "total_steps": 38150, "loss": 0.2754, "lr": 3.931551053026699e-05, "epoch": 3.7536041939711664, "percentage": 37.54, "elapsed_time": "0:24:10", "remaining_time": "0:40:13", "throughput": 2643.78, "total_tokens": 3834408} {"current_steps": 14325, "total_steps": 38150, "loss": 0.3466, "lr": 3.9306132512737395e-05, "epoch": 3.7549148099606815, "percentage": 37.55, "elapsed_time": "0:24:10", "remaining_time": "0:40:12", "throughput": 2643.72, "total_tokens": 3835432} {"current_steps": 14330, "total_steps": 38150, "loss": 0.3127, "lr": 3.929675150095898e-05, "epoch": 3.7562254259501966, "percentage": 37.56, "elapsed_time": "0:24:11", "remaining_time": "0:40:12", "throughput": 2643.86, "total_tokens": 3836808} {"current_steps": 14335, "total_steps": 38150, "loss": 0.3816, "lr": 3.928736749689519e-05, "epoch": 3.7575360419397117, "percentage": 37.58, "elapsed_time": "0:24:11", "remaining_time": "0:40:11", "throughput": 2643.84, "total_tokens": 3837976} {"current_steps": 14340, "total_steps": 38150, "loss": 0.328, "lr": 3.927798050251006e-05, "epoch": 3.758846657929227, "percentage": 37.59, "elapsed_time": "0:24:12", "remaining_time": "0:40:11", "throughput": 2643.95, "total_tokens": 3839288} {"current_steps": 14345, "total_steps": 38150, "loss": 0.4451, "lr": 3.926859051976828e-05, "epoch": 3.760157273918742, "percentage": 37.6, "elapsed_time": "0:24:12", "remaining_time": "0:40:10", "throughput": 2644.03, "total_tokens": 3840600} {"current_steps": 14350, "total_steps": 38150, "loss": 0.4105, "lr": 3.9259197550635164e-05, "epoch": 3.761467889908257, "percentage": 37.61, "elapsed_time": "0:24:12", "remaining_time": "0:40:09", "throughput": 2644.02, "total_tokens": 3841704} {"current_steps": 14355, "total_steps": 38150, "loss": 0.5711, "lr": 3.924980159707664e-05, "epoch": 3.762778505897772, "percentage": 37.63, "elapsed_time": "0:24:13", "remaining_time": "0:40:09", "throughput": 2643.98, "total_tokens": 3842776} {"current_steps": 14360, "total_steps": 38150, "loss": 0.2611, "lr": 3.924040266105926e-05, "epoch": 3.764089121887287, "percentage": 37.64, "elapsed_time": "0:24:13", "remaining_time": "0:40:08", "throughput": 2644.04, "total_tokens": 3844072} {"current_steps": 14365, "total_steps": 38150, "loss": 0.426, "lr": 3.9231000744550205e-05, "epoch": 3.765399737876802, "percentage": 37.65, "elapsed_time": "0:24:14", "remaining_time": "0:40:07", "throughput": 2644.06, "total_tokens": 3845208} {"current_steps": 14370, "total_steps": 38150, "loss": 0.4567, "lr": 3.922159584951729e-05, "epoch": 3.7667103538663174, "percentage": 37.67, "elapsed_time": "0:24:14", "remaining_time": "0:40:07", "throughput": 2644.21, "total_tokens": 3846584} {"current_steps": 14375, "total_steps": 38150, "loss": 0.4338, "lr": 3.921218797792893e-05, "epoch": 3.768020969855832, "percentage": 37.68, "elapsed_time": "0:24:15", "remaining_time": "0:40:06", "throughput": 2644.36, "total_tokens": 3848040} {"current_steps": 14380, "total_steps": 38150, "loss": 0.4665, "lr": 3.9202777131754187e-05, "epoch": 3.7693315858453476, "percentage": 37.69, "elapsed_time": "0:24:15", "remaining_time": "0:40:06", "throughput": 2644.38, "total_tokens": 3849224} {"current_steps": 14385, "total_steps": 38150, "loss": 0.3963, "lr": 3.9193363312962725e-05, "epoch": 3.770642201834862, "percentage": 37.71, "elapsed_time": "0:24:16", "remaining_time": "0:40:05", "throughput": 2644.44, "total_tokens": 3850424} {"current_steps": 14390, "total_steps": 38150, "loss": 0.3696, "lr": 3.9183946523524856e-05, "epoch": 3.7719528178243773, "percentage": 37.72, "elapsed_time": "0:24:16", "remaining_time": "0:40:04", "throughput": 2644.65, "total_tokens": 3852008} {"current_steps": 14395, "total_steps": 38150, "loss": 0.4673, "lr": 3.917452676541148e-05, "epoch": 3.7732634338138924, "percentage": 37.73, "elapsed_time": "0:24:16", "remaining_time": "0:40:04", "throughput": 2644.66, "total_tokens": 3853160} {"current_steps": 14400, "total_steps": 38150, "loss": 0.4125, "lr": 3.916510404059415e-05, "epoch": 3.7745740498034075, "percentage": 37.75, "elapsed_time": "0:24:17", "remaining_time": "0:40:03", "throughput": 2644.77, "total_tokens": 3854568} {"current_steps": 14405, "total_steps": 38150, "loss": 0.4799, "lr": 3.9155678351045014e-05, "epoch": 3.7758846657929226, "percentage": 37.76, "elapsed_time": "0:24:17", "remaining_time": "0:40:03", "throughput": 2645.07, "total_tokens": 3856280} {"current_steps": 14410, "total_steps": 38150, "loss": 0.3305, "lr": 3.914624969873686e-05, "epoch": 3.7771952817824377, "percentage": 37.77, "elapsed_time": "0:24:18", "remaining_time": "0:40:02", "throughput": 2645.17, "total_tokens": 3857672} {"current_steps": 14415, "total_steps": 38150, "loss": 0.4973, "lr": 3.913681808564309e-05, "epoch": 3.778505897771953, "percentage": 37.79, "elapsed_time": "0:24:18", "remaining_time": "0:40:02", "throughput": 2645.24, "total_tokens": 3858904} {"current_steps": 14420, "total_steps": 38150, "loss": 0.4636, "lr": 3.912738351373772e-05, "epoch": 3.779816513761468, "percentage": 37.8, "elapsed_time": "0:24:19", "remaining_time": "0:40:01", "throughput": 2645.36, "total_tokens": 3860344} {"current_steps": 14425, "total_steps": 38150, "loss": 0.4521, "lr": 3.911794598499539e-05, "epoch": 3.781127129750983, "percentage": 37.81, "elapsed_time": "0:24:19", "remaining_time": "0:40:00", "throughput": 2645.3, "total_tokens": 3861368} {"current_steps": 14430, "total_steps": 38150, "loss": 0.4407, "lr": 3.9108505501391355e-05, "epoch": 3.782437745740498, "percentage": 37.82, "elapsed_time": "0:24:20", "remaining_time": "0:40:00", "throughput": 2645.3, "total_tokens": 3862504} {"current_steps": 14435, "total_steps": 38150, "loss": 0.361, "lr": 3.9099062064901497e-05, "epoch": 3.783748361730013, "percentage": 37.84, "elapsed_time": "0:24:20", "remaining_time": "0:39:59", "throughput": 2645.37, "total_tokens": 3863752} {"current_steps": 14440, "total_steps": 38150, "loss": 0.3239, "lr": 3.908961567750231e-05, "epoch": 3.7850589777195283, "percentage": 37.85, "elapsed_time": "0:24:21", "remaining_time": "0:39:58", "throughput": 2645.48, "total_tokens": 3865176} {"current_steps": 14445, "total_steps": 38150, "loss": 0.4267, "lr": 3.908016634117092e-05, "epoch": 3.7863695937090434, "percentage": 37.86, "elapsed_time": "0:24:21", "remaining_time": "0:39:58", "throughput": 2645.48, "total_tokens": 3866392} {"current_steps": 14450, "total_steps": 38150, "loss": 0.4309, "lr": 3.907071405788503e-05, "epoch": 3.7876802096985585, "percentage": 37.88, "elapsed_time": "0:24:21", "remaining_time": "0:39:57", "throughput": 2645.42, "total_tokens": 3867416} {"current_steps": 14455, "total_steps": 38150, "loss": 0.4843, "lr": 3.9061258829622995e-05, "epoch": 3.7889908256880735, "percentage": 37.89, "elapsed_time": "0:24:22", "remaining_time": "0:39:57", "throughput": 2645.51, "total_tokens": 3868712} {"current_steps": 14460, "total_steps": 38150, "loss": 0.2768, "lr": 3.905180065836379e-05, "epoch": 3.790301441677588, "percentage": 37.9, "elapsed_time": "0:24:22", "remaining_time": "0:39:56", "throughput": 2645.65, "total_tokens": 3870152} {"current_steps": 14465, "total_steps": 38150, "loss": 0.4391, "lr": 3.904233954608699e-05, "epoch": 3.7916120576671037, "percentage": 37.92, "elapsed_time": "0:24:23", "remaining_time": "0:39:56", "throughput": 2645.67, "total_tokens": 3871480} {"current_steps": 14470, "total_steps": 38150, "loss": 0.291, "lr": 3.903287549477279e-05, "epoch": 3.7929226736566184, "percentage": 37.93, "elapsed_time": "0:24:23", "remaining_time": "0:39:55", "throughput": 2645.79, "total_tokens": 3872792} {"current_steps": 14475, "total_steps": 38150, "loss": 0.4979, "lr": 3.9023408506401987e-05, "epoch": 3.794233289646134, "percentage": 37.94, "elapsed_time": "0:24:24", "remaining_time": "0:39:54", "throughput": 2645.83, "total_tokens": 3873944} {"current_steps": 14480, "total_steps": 38150, "loss": 0.5417, "lr": 3.901393858295602e-05, "epoch": 3.7955439056356486, "percentage": 37.96, "elapsed_time": "0:24:24", "remaining_time": "0:39:54", "throughput": 2646.26, "total_tokens": 3876200} {"current_steps": 14485, "total_steps": 38150, "loss": 0.4321, "lr": 3.900446572641692e-05, "epoch": 3.7968545216251637, "percentage": 37.97, "elapsed_time": "0:24:25", "remaining_time": "0:39:53", "throughput": 2646.49, "total_tokens": 3877928} {"current_steps": 14490, "total_steps": 38150, "loss": 0.4813, "lr": 3.899498993876733e-05, "epoch": 3.7981651376146788, "percentage": 37.98, "elapsed_time": "0:24:25", "remaining_time": "0:39:53", "throughput": 2646.39, "total_tokens": 3878904} {"current_steps": 14495, "total_steps": 38150, "loss": 0.3376, "lr": 3.898551122199054e-05, "epoch": 3.799475753604194, "percentage": 37.99, "elapsed_time": "0:24:26", "remaining_time": "0:39:52", "throughput": 2646.46, "total_tokens": 3880136} {"current_steps": 14500, "total_steps": 38150, "loss": 0.4757, "lr": 3.8976029578070415e-05, "epoch": 3.800786369593709, "percentage": 38.01, "elapsed_time": "0:24:26", "remaining_time": "0:39:52", "throughput": 2646.47, "total_tokens": 3881272} {"current_steps": 14505, "total_steps": 38150, "loss": 0.4246, "lr": 3.896654500899145e-05, "epoch": 3.802096985583224, "percentage": 38.02, "elapsed_time": "0:24:27", "remaining_time": "0:39:51", "throughput": 2646.54, "total_tokens": 3882504} {"current_steps": 14510, "total_steps": 38150, "loss": 0.4896, "lr": 3.895705751673874e-05, "epoch": 3.803407601572739, "percentage": 38.03, "elapsed_time": "0:24:27", "remaining_time": "0:39:51", "throughput": 2647.13, "total_tokens": 3885368} {"current_steps": 14515, "total_steps": 38150, "loss": 0.5492, "lr": 3.894756710329801e-05, "epoch": 3.8047182175622543, "percentage": 38.05, "elapsed_time": "0:24:28", "remaining_time": "0:39:50", "throughput": 2647.31, "total_tokens": 3886904} {"current_steps": 14520, "total_steps": 38150, "loss": 0.439, "lr": 3.893807377065559e-05, "epoch": 3.8060288335517694, "percentage": 38.06, "elapsed_time": "0:24:28", "remaining_time": "0:39:50", "throughput": 2647.27, "total_tokens": 3887976} {"current_steps": 14525, "total_steps": 38150, "loss": 0.3577, "lr": 3.8928577520798407e-05, "epoch": 3.8073394495412844, "percentage": 38.07, "elapsed_time": "0:24:29", "remaining_time": "0:39:49", "throughput": 2647.25, "total_tokens": 3889064} {"current_steps": 14530, "total_steps": 38150, "loss": 0.2164, "lr": 3.8919078355714025e-05, "epoch": 3.8086500655307995, "percentage": 38.09, "elapsed_time": "0:24:29", "remaining_time": "0:39:48", "throughput": 2647.29, "total_tokens": 3890344} {"current_steps": 14535, "total_steps": 38150, "loss": 0.4566, "lr": 3.890957627739058e-05, "epoch": 3.8099606815203146, "percentage": 38.1, "elapsed_time": "0:24:30", "remaining_time": "0:39:48", "throughput": 2647.58, "total_tokens": 3892056} {"current_steps": 14540, "total_steps": 38150, "loss": 0.2756, "lr": 3.890007128781686e-05, "epoch": 3.8112712975098297, "percentage": 38.11, "elapsed_time": "0:24:30", "remaining_time": "0:39:47", "throughput": 2647.63, "total_tokens": 3893304} {"current_steps": 14545, "total_steps": 38150, "loss": 0.2531, "lr": 3.889056338898224e-05, "epoch": 3.812581913499345, "percentage": 38.13, "elapsed_time": "0:24:30", "remaining_time": "0:39:47", "throughput": 2647.83, "total_tokens": 3894872} {"current_steps": 14550, "total_steps": 38150, "loss": 0.5913, "lr": 3.8881052582876695e-05, "epoch": 3.81389252948886, "percentage": 38.14, "elapsed_time": "0:24:31", "remaining_time": "0:39:46", "throughput": 2648.07, "total_tokens": 3896504} {"current_steps": 14555, "total_steps": 38150, "loss": 0.3779, "lr": 3.887153887149084e-05, "epoch": 3.8152031454783746, "percentage": 38.15, "elapsed_time": "0:24:31", "remaining_time": "0:39:46", "throughput": 2648.16, "total_tokens": 3897768} {"current_steps": 14560, "total_steps": 38150, "loss": 0.3325, "lr": 3.8862022256815865e-05, "epoch": 3.81651376146789, "percentage": 38.17, "elapsed_time": "0:24:32", "remaining_time": "0:39:45", "throughput": 2648.16, "total_tokens": 3898872} {"current_steps": 14565, "total_steps": 38150, "loss": 0.3993, "lr": 3.885250274084358e-05, "epoch": 3.8178243774574048, "percentage": 38.18, "elapsed_time": "0:24:32", "remaining_time": "0:39:44", "throughput": 2648.17, "total_tokens": 3900008} {"current_steps": 14570, "total_steps": 38150, "loss": 0.3696, "lr": 3.88429803255664e-05, "epoch": 3.8191349934469203, "percentage": 38.19, "elapsed_time": "0:24:33", "remaining_time": "0:39:44", "throughput": 2648.13, "total_tokens": 3901064} {"current_steps": 14575, "total_steps": 38150, "loss": 0.3467, "lr": 3.883345501297737e-05, "epoch": 3.820445609436435, "percentage": 38.2, "elapsed_time": "0:24:33", "remaining_time": "0:39:43", "throughput": 2648.26, "total_tokens": 3902568} {"current_steps": 14580, "total_steps": 38150, "loss": 0.6545, "lr": 3.88239268050701e-05, "epoch": 3.82175622542595, "percentage": 38.22, "elapsed_time": "0:24:34", "remaining_time": "0:39:43", "throughput": 2648.41, "total_tokens": 3904088} {"current_steps": 14585, "total_steps": 38150, "loss": 0.5891, "lr": 3.881439570383884e-05, "epoch": 3.823066841415465, "percentage": 38.23, "elapsed_time": "0:24:34", "remaining_time": "0:39:42", "throughput": 2648.51, "total_tokens": 3905464} {"current_steps": 14590, "total_steps": 38150, "loss": 0.3781, "lr": 3.8804861711278426e-05, "epoch": 3.8243774574049803, "percentage": 38.24, "elapsed_time": "0:24:35", "remaining_time": "0:39:41", "throughput": 2648.67, "total_tokens": 3906952} {"current_steps": 14595, "total_steps": 38150, "loss": 0.4621, "lr": 3.879532482938431e-05, "epoch": 3.8256880733944953, "percentage": 38.26, "elapsed_time": "0:24:35", "remaining_time": "0:39:41", "throughput": 2648.68, "total_tokens": 3908056} {"current_steps": 14600, "total_steps": 38150, "loss": 0.3516, "lr": 3.878578506015254e-05, "epoch": 3.8269986893840104, "percentage": 38.27, "elapsed_time": "0:24:35", "remaining_time": "0:39:40", "throughput": 2648.71, "total_tokens": 3909256} {"current_steps": 14605, "total_steps": 38150, "loss": 0.5412, "lr": 3.877624240557978e-05, "epoch": 3.8283093053735255, "percentage": 38.28, "elapsed_time": "0:24:36", "remaining_time": "0:39:40", "throughput": 2648.73, "total_tokens": 3910424} {"current_steps": 14610, "total_steps": 38150, "loss": 0.5176, "lr": 3.876669686766329e-05, "epoch": 3.8296199213630406, "percentage": 38.3, "elapsed_time": "0:24:36", "remaining_time": "0:39:39", "throughput": 2649.14, "total_tokens": 3912536} {"current_steps": 14615, "total_steps": 38150, "loss": 0.4006, "lr": 3.875714844840093e-05, "epoch": 3.8309305373525557, "percentage": 38.31, "elapsed_time": "0:24:37", "remaining_time": "0:39:39", "throughput": 2649.15, "total_tokens": 3913688} {"current_steps": 14620, "total_steps": 38150, "loss": 0.3528, "lr": 3.874759714979117e-05, "epoch": 3.832241153342071, "percentage": 38.32, "elapsed_time": "0:24:37", "remaining_time": "0:39:38", "throughput": 2649.03, "total_tokens": 3914616} {"current_steps": 14625, "total_steps": 38150, "loss": 0.4379, "lr": 3.873804297383308e-05, "epoch": 3.833551769331586, "percentage": 38.34, "elapsed_time": "0:24:38", "remaining_time": "0:39:37", "throughput": 2649.2, "total_tokens": 3916120} {"current_steps": 14630, "total_steps": 38150, "loss": 0.3867, "lr": 3.872848592252634e-05, "epoch": 3.834862385321101, "percentage": 38.35, "elapsed_time": "0:24:39", "remaining_time": "0:39:37", "throughput": 2649.88, "total_tokens": 3919400} {"current_steps": 14635, "total_steps": 38150, "loss": 0.4238, "lr": 3.871892599787121e-05, "epoch": 3.836173001310616, "percentage": 38.36, "elapsed_time": "0:24:39", "remaining_time": "0:39:37", "throughput": 2649.8, "total_tokens": 3920408} {"current_steps": 14640, "total_steps": 38150, "loss": 0.4586, "lr": 3.8709363201868576e-05, "epoch": 3.837483617300131, "percentage": 38.37, "elapsed_time": "0:24:39", "remaining_time": "0:39:36", "throughput": 2649.84, "total_tokens": 3921640} {"current_steps": 14645, "total_steps": 38150, "loss": 0.459, "lr": 3.869979753651991e-05, "epoch": 3.8387942332896463, "percentage": 38.39, "elapsed_time": "0:24:40", "remaining_time": "0:39:35", "throughput": 2649.83, "total_tokens": 3922744} {"current_steps": 14650, "total_steps": 38150, "loss": 0.2332, "lr": 3.869022900382729e-05, "epoch": 3.840104849279161, "percentage": 38.4, "elapsed_time": "0:24:40", "remaining_time": "0:39:35", "throughput": 2649.99, "total_tokens": 3924152} {"current_steps": 14655, "total_steps": 38150, "loss": 0.3169, "lr": 3.868065760579339e-05, "epoch": 3.8414154652686765, "percentage": 38.41, "elapsed_time": "0:24:41", "remaining_time": "0:39:34", "throughput": 2650.26, "total_tokens": 3925848} {"current_steps": 14660, "total_steps": 38150, "loss": 0.3904, "lr": 3.86710833444215e-05, "epoch": 3.842726081258191, "percentage": 38.43, "elapsed_time": "0:24:41", "remaining_time": "0:39:34", "throughput": 2650.46, "total_tokens": 3927400} {"current_steps": 14665, "total_steps": 38150, "loss": 0.4672, "lr": 3.866150622171549e-05, "epoch": 3.8440366972477067, "percentage": 38.44, "elapsed_time": "0:24:42", "remaining_time": "0:39:33", "throughput": 2650.47, "total_tokens": 3928536} {"current_steps": 14670, "total_steps": 38150, "loss": 0.5085, "lr": 3.8651926239679824e-05, "epoch": 3.8453473132372213, "percentage": 38.45, "elapsed_time": "0:24:42", "remaining_time": "0:39:33", "throughput": 2650.4, "total_tokens": 3929544} {"current_steps": 14675, "total_steps": 38150, "loss": 0.4574, "lr": 3.8642343400319594e-05, "epoch": 3.8466579292267364, "percentage": 38.47, "elapsed_time": "0:24:43", "remaining_time": "0:39:32", "throughput": 2650.58, "total_tokens": 3931096} {"current_steps": 14680, "total_steps": 38150, "loss": 0.3596, "lr": 3.863275770564046e-05, "epoch": 3.8479685452162515, "percentage": 38.48, "elapsed_time": "0:24:43", "remaining_time": "0:39:31", "throughput": 2650.72, "total_tokens": 3932568} {"current_steps": 14685, "total_steps": 38150, "loss": 0.2575, "lr": 3.862316915764869e-05, "epoch": 3.8492791612057666, "percentage": 38.49, "elapsed_time": "0:24:44", "remaining_time": "0:39:31", "throughput": 2650.74, "total_tokens": 3933752} {"current_steps": 14690, "total_steps": 38150, "loss": 0.4179, "lr": 3.861357775835115e-05, "epoch": 3.8505897771952817, "percentage": 38.51, "elapsed_time": "0:24:44", "remaining_time": "0:39:30", "throughput": 2650.81, "total_tokens": 3935000} {"current_steps": 14695, "total_steps": 38150, "loss": 0.3268, "lr": 3.8603983509755316e-05, "epoch": 3.851900393184797, "percentage": 38.52, "elapsed_time": "0:24:44", "remaining_time": "0:39:30", "throughput": 2650.89, "total_tokens": 3936280} {"current_steps": 14700, "total_steps": 38150, "loss": 0.3301, "lr": 3.8594386413869235e-05, "epoch": 3.853211009174312, "percentage": 38.53, "elapsed_time": "0:24:45", "remaining_time": "0:39:29", "throughput": 2651.09, "total_tokens": 3937912} {"current_steps": 14705, "total_steps": 38150, "loss": 0.4104, "lr": 3.8584786472701575e-05, "epoch": 3.854521625163827, "percentage": 38.55, "elapsed_time": "0:24:45", "remaining_time": "0:39:29", "throughput": 2651.32, "total_tokens": 3939528} {"current_steps": 14710, "total_steps": 38150, "loss": 0.4353, "lr": 3.857518368826157e-05, "epoch": 3.855832241153342, "percentage": 38.56, "elapsed_time": "0:24:46", "remaining_time": "0:39:28", "throughput": 2651.41, "total_tokens": 3940888} {"current_steps": 14715, "total_steps": 38150, "loss": 0.3997, "lr": 3.856557806255908e-05, "epoch": 3.857142857142857, "percentage": 38.57, "elapsed_time": "0:24:46", "remaining_time": "0:39:27", "throughput": 2651.57, "total_tokens": 3942296} {"current_steps": 14720, "total_steps": 38150, "loss": 0.3623, "lr": 3.8555969597604536e-05, "epoch": 3.8584534731323723, "percentage": 38.58, "elapsed_time": "0:24:47", "remaining_time": "0:39:27", "throughput": 2651.59, "total_tokens": 3943432} {"current_steps": 14725, "total_steps": 38150, "loss": 0.2694, "lr": 3.854635829540898e-05, "epoch": 3.8597640891218874, "percentage": 38.6, "elapsed_time": "0:24:47", "remaining_time": "0:39:26", "throughput": 2651.65, "total_tokens": 3944760} {"current_steps": 14730, "total_steps": 38150, "loss": 0.2898, "lr": 3.853674415798404e-05, "epoch": 3.8610747051114025, "percentage": 38.61, "elapsed_time": "0:24:48", "remaining_time": "0:39:26", "throughput": 2652.16, "total_tokens": 3947544} {"current_steps": 14735, "total_steps": 38150, "loss": 0.3183, "lr": 3.8527127187341936e-05, "epoch": 3.8623853211009176, "percentage": 38.62, "elapsed_time": "0:24:48", "remaining_time": "0:39:25", "throughput": 2652.36, "total_tokens": 3949016} {"current_steps": 14740, "total_steps": 38150, "loss": 0.4462, "lr": 3.8517507385495486e-05, "epoch": 3.8636959370904327, "percentage": 38.64, "elapsed_time": "0:24:49", "remaining_time": "0:39:25", "throughput": 2652.56, "total_tokens": 3950584} {"current_steps": 14745, "total_steps": 38150, "loss": 0.5961, "lr": 3.85078847544581e-05, "epoch": 3.8650065530799473, "percentage": 38.65, "elapsed_time": "0:24:49", "remaining_time": "0:39:24", "throughput": 2652.56, "total_tokens": 3951720} {"current_steps": 14750, "total_steps": 38150, "loss": 0.315, "lr": 3.849825929624377e-05, "epoch": 3.866317169069463, "percentage": 38.66, "elapsed_time": "0:24:50", "remaining_time": "0:39:24", "throughput": 2652.65, "total_tokens": 3952984} {"current_steps": 14755, "total_steps": 38150, "loss": 0.4356, "lr": 3.8488631012867095e-05, "epoch": 3.8676277850589775, "percentage": 38.68, "elapsed_time": "0:24:50", "remaining_time": "0:39:23", "throughput": 2652.89, "total_tokens": 3954680} {"current_steps": 14760, "total_steps": 38150, "loss": 0.3284, "lr": 3.847899990634326e-05, "epoch": 3.8689384010484926, "percentage": 38.69, "elapsed_time": "0:24:51", "remaining_time": "0:39:22", "throughput": 2653.01, "total_tokens": 3956024} {"current_steps": 14765, "total_steps": 38150, "loss": 0.4001, "lr": 3.846936597868802e-05, "epoch": 3.8702490170380077, "percentage": 38.7, "elapsed_time": "0:24:51", "remaining_time": "0:39:22", "throughput": 2653.1, "total_tokens": 3957320} {"current_steps": 14770, "total_steps": 38150, "loss": 0.5437, "lr": 3.845972923191776e-05, "epoch": 3.871559633027523, "percentage": 38.72, "elapsed_time": "0:24:52", "remaining_time": "0:39:21", "throughput": 2653.07, "total_tokens": 3958376} {"current_steps": 14775, "total_steps": 38150, "loss": 0.3694, "lr": 3.845008966804944e-05, "epoch": 3.872870249017038, "percentage": 38.73, "elapsed_time": "0:24:52", "remaining_time": "0:39:21", "throughput": 2653.08, "total_tokens": 3959624} {"current_steps": 14780, "total_steps": 38150, "loss": 0.3664, "lr": 3.844044728910058e-05, "epoch": 3.874180865006553, "percentage": 38.74, "elapsed_time": "0:24:52", "remaining_time": "0:39:20", "throughput": 2653.1, "total_tokens": 3960760} {"current_steps": 14785, "total_steps": 38150, "loss": 0.3493, "lr": 3.843080209708933e-05, "epoch": 3.875491480996068, "percentage": 38.75, "elapsed_time": "0:24:53", "remaining_time": "0:39:20", "throughput": 2653.3, "total_tokens": 3962504} {"current_steps": 14790, "total_steps": 38150, "loss": 0.3367, "lr": 3.8421154094034404e-05, "epoch": 3.876802096985583, "percentage": 38.77, "elapsed_time": "0:24:53", "remaining_time": "0:39:19", "throughput": 2653.53, "total_tokens": 3964200} {"current_steps": 14795, "total_steps": 38150, "loss": 0.3157, "lr": 3.841150328195512e-05, "epoch": 3.8781127129750983, "percentage": 38.78, "elapsed_time": "0:24:54", "remaining_time": "0:39:18", "throughput": 2653.46, "total_tokens": 3965192} {"current_steps": 14800, "total_steps": 38150, "loss": 0.4685, "lr": 3.840184966287137e-05, "epoch": 3.8794233289646134, "percentage": 38.79, "elapsed_time": "0:24:54", "remaining_time": "0:39:18", "throughput": 2653.66, "total_tokens": 3966744} {"current_steps": 14805, "total_steps": 38150, "loss": 0.3698, "lr": 3.839219323880365e-05, "epoch": 3.8807339449541285, "percentage": 38.81, "elapsed_time": "0:24:55", "remaining_time": "0:39:17", "throughput": 2653.89, "total_tokens": 3968440} {"current_steps": 14810, "total_steps": 38150, "loss": 0.4473, "lr": 3.838253401177302e-05, "epoch": 3.8820445609436436, "percentage": 38.82, "elapsed_time": "0:24:55", "remaining_time": "0:39:17", "throughput": 2654.08, "total_tokens": 3970072} {"current_steps": 14815, "total_steps": 38150, "loss": 0.3471, "lr": 3.837287198380114e-05, "epoch": 3.8833551769331587, "percentage": 38.83, "elapsed_time": "0:24:56", "remaining_time": "0:39:16", "throughput": 2654.02, "total_tokens": 3971112} {"current_steps": 14820, "total_steps": 38150, "loss": 0.4592, "lr": 3.836320715691027e-05, "epoch": 3.8846657929226738, "percentage": 38.85, "elapsed_time": "0:24:56", "remaining_time": "0:39:16", "throughput": 2653.96, "total_tokens": 3972120} {"current_steps": 14825, "total_steps": 38150, "loss": 0.3803, "lr": 3.835353953312322e-05, "epoch": 3.885976408912189, "percentage": 38.86, "elapsed_time": "0:24:57", "remaining_time": "0:39:15", "throughput": 2654.03, "total_tokens": 3973448} {"current_steps": 14830, "total_steps": 38150, "loss": 0.566, "lr": 3.8343869114463424e-05, "epoch": 3.8872870249017035, "percentage": 38.87, "elapsed_time": "0:24:57", "remaining_time": "0:39:15", "throughput": 2654.3, "total_tokens": 3975192} {"current_steps": 14835, "total_steps": 38150, "loss": 0.458, "lr": 3.8334195902954885e-05, "epoch": 3.888597640891219, "percentage": 38.89, "elapsed_time": "0:24:58", "remaining_time": "0:39:14", "throughput": 2654.32, "total_tokens": 3976344} {"current_steps": 14840, "total_steps": 38150, "loss": 0.4071, "lr": 3.8324519900622175e-05, "epoch": 3.8899082568807337, "percentage": 38.9, "elapsed_time": "0:24:58", "remaining_time": "0:39:13", "throughput": 2654.48, "total_tokens": 3977832} {"current_steps": 14845, "total_steps": 38150, "loss": 0.3831, "lr": 3.8314841109490474e-05, "epoch": 3.8912188728702493, "percentage": 38.91, "elapsed_time": "0:24:58", "remaining_time": "0:39:13", "throughput": 2654.53, "total_tokens": 3979128} {"current_steps": 14850, "total_steps": 38150, "loss": 0.429, "lr": 3.830515953158553e-05, "epoch": 3.892529488859764, "percentage": 38.93, "elapsed_time": "0:24:59", "remaining_time": "0:39:12", "throughput": 2654.53, "total_tokens": 3980248} {"current_steps": 14855, "total_steps": 38150, "loss": 0.3152, "lr": 3.82954751689337e-05, "epoch": 3.893840104849279, "percentage": 38.94, "elapsed_time": "0:24:59", "remaining_time": "0:39:12", "throughput": 2654.45, "total_tokens": 3981320} {"current_steps": 14860, "total_steps": 38150, "loss": 0.5651, "lr": 3.828578802356188e-05, "epoch": 3.895150720838794, "percentage": 38.95, "elapsed_time": "0:25:00", "remaining_time": "0:39:11", "throughput": 2654.52, "total_tokens": 3982584} {"current_steps": 14865, "total_steps": 38150, "loss": 0.3039, "lr": 3.8276098097497584e-05, "epoch": 3.896461336828309, "percentage": 38.96, "elapsed_time": "0:25:00", "remaining_time": "0:39:10", "throughput": 2654.61, "total_tokens": 3983928} {"current_steps": 14870, "total_steps": 38150, "loss": 0.3963, "lr": 3.8266405392768904e-05, "epoch": 3.8977719528178243, "percentage": 38.98, "elapsed_time": "0:25:01", "remaining_time": "0:39:10", "throughput": 2654.93, "total_tokens": 3985816} {"current_steps": 14875, "total_steps": 38150, "loss": 0.4003, "lr": 3.8256709911404484e-05, "epoch": 3.8990825688073394, "percentage": 38.99, "elapsed_time": "0:25:01", "remaining_time": "0:39:09", "throughput": 2655.07, "total_tokens": 3987208} {"current_steps": 14880, "total_steps": 38150, "loss": 0.4305, "lr": 3.82470116554336e-05, "epoch": 3.9003931847968545, "percentage": 39.0, "elapsed_time": "0:25:02", "remaining_time": "0:39:09", "throughput": 2655.13, "total_tokens": 3988440} {"current_steps": 14885, "total_steps": 38150, "loss": 0.3642, "lr": 3.823731062688605e-05, "epoch": 3.9017038007863696, "percentage": 39.02, "elapsed_time": "0:25:02", "remaining_time": "0:39:08", "throughput": 2655.06, "total_tokens": 3989464} {"current_steps": 14890, "total_steps": 38150, "loss": 0.3803, "lr": 3.8227606827792265e-05, "epoch": 3.9030144167758847, "percentage": 39.03, "elapsed_time": "0:25:03", "remaining_time": "0:39:07", "throughput": 2655.22, "total_tokens": 3990872} {"current_steps": 14895, "total_steps": 38150, "loss": 0.3857, "lr": 3.8217900260183224e-05, "epoch": 3.9043250327653998, "percentage": 39.04, "elapsed_time": "0:25:03", "remaining_time": "0:39:07", "throughput": 2655.22, "total_tokens": 3992008} {"current_steps": 14900, "total_steps": 38150, "loss": 0.282, "lr": 3.82081909260905e-05, "epoch": 3.905635648754915, "percentage": 39.06, "elapsed_time": "0:25:03", "remaining_time": "0:39:06", "throughput": 2655.3, "total_tokens": 3993288} {"current_steps": 14905, "total_steps": 38150, "loss": 0.3951, "lr": 3.819847882754623e-05, "epoch": 3.90694626474443, "percentage": 39.07, "elapsed_time": "0:25:04", "remaining_time": "0:39:06", "throughput": 2655.46, "total_tokens": 3994728} {"current_steps": 14910, "total_steps": 38150, "loss": 0.3428, "lr": 3.8188763966583165e-05, "epoch": 3.908256880733945, "percentage": 39.08, "elapsed_time": "0:25:04", "remaining_time": "0:39:05", "throughput": 2655.46, "total_tokens": 3995928} {"current_steps": 14915, "total_steps": 38150, "loss": 0.4426, "lr": 3.817904634523458e-05, "epoch": 3.90956749672346, "percentage": 39.1, "elapsed_time": "0:25:05", "remaining_time": "0:39:04", "throughput": 2655.5, "total_tokens": 3997208} {"current_steps": 14920, "total_steps": 38150, "loss": 0.3621, "lr": 3.816932596553436e-05, "epoch": 3.9108781127129753, "percentage": 39.11, "elapsed_time": "0:25:05", "remaining_time": "0:39:04", "throughput": 2655.71, "total_tokens": 3998808} {"current_steps": 14925, "total_steps": 38150, "loss": 0.4339, "lr": 3.8159602829516975e-05, "epoch": 3.91218872870249, "percentage": 39.12, "elapsed_time": "0:25:06", "remaining_time": "0:39:03", "throughput": 2655.88, "total_tokens": 4000232} {"current_steps": 14930, "total_steps": 38150, "loss": 0.3655, "lr": 3.8149876939217454e-05, "epoch": 3.9134993446920054, "percentage": 39.13, "elapsed_time": "0:25:06", "remaining_time": "0:39:03", "throughput": 2655.82, "total_tokens": 4001256} {"current_steps": 14935, "total_steps": 38150, "loss": 0.3242, "lr": 3.814014829667142e-05, "epoch": 3.91480996068152, "percentage": 39.15, "elapsed_time": "0:25:07", "remaining_time": "0:39:02", "throughput": 2655.93, "total_tokens": 4002568} {"current_steps": 14940, "total_steps": 38150, "loss": 0.3969, "lr": 3.8130416903915045e-05, "epoch": 3.9161205766710356, "percentage": 39.16, "elapsed_time": "0:25:07", "remaining_time": "0:39:02", "throughput": 2656.0, "total_tokens": 4003976} {"current_steps": 14945, "total_steps": 38150, "loss": 0.3615, "lr": 3.812068276298509e-05, "epoch": 3.9174311926605503, "percentage": 39.17, "elapsed_time": "0:25:08", "remaining_time": "0:39:01", "throughput": 2656.35, "total_tokens": 4005848} {"current_steps": 14950, "total_steps": 38150, "loss": 0.3665, "lr": 3.811094587591892e-05, "epoch": 3.9187418086500654, "percentage": 39.19, "elapsed_time": "0:25:08", "remaining_time": "0:39:00", "throughput": 2656.26, "total_tokens": 4006808} {"current_steps": 14955, "total_steps": 38150, "loss": 0.3468, "lr": 3.810120624475443e-05, "epoch": 3.9200524246395805, "percentage": 39.2, "elapsed_time": "0:25:08", "remaining_time": "0:39:00", "throughput": 2656.4, "total_tokens": 4008184} {"current_steps": 14960, "total_steps": 38150, "loss": 0.3887, "lr": 3.809146387153011e-05, "epoch": 3.9213630406290956, "percentage": 39.21, "elapsed_time": "0:25:09", "remaining_time": "0:38:59", "throughput": 2656.55, "total_tokens": 4009656} {"current_steps": 14965, "total_steps": 38150, "loss": 0.5241, "lr": 3.808171875828501e-05, "epoch": 3.9226736566186107, "percentage": 39.23, "elapsed_time": "0:25:09", "remaining_time": "0:38:59", "throughput": 2656.54, "total_tokens": 4010760} {"current_steps": 14970, "total_steps": 38150, "loss": 0.6519, "lr": 3.8071970907058786e-05, "epoch": 3.9239842726081258, "percentage": 39.24, "elapsed_time": "0:25:10", "remaining_time": "0:38:58", "throughput": 2656.47, "total_tokens": 4011752} {"current_steps": 14975, "total_steps": 38150, "loss": 0.4477, "lr": 3.806222031989164e-05, "epoch": 3.925294888597641, "percentage": 39.25, "elapsed_time": "0:25:10", "remaining_time": "0:38:57", "throughput": 2656.47, "total_tokens": 4012872} {"current_steps": 14980, "total_steps": 38150, "loss": 0.2941, "lr": 3.8052466998824344e-05, "epoch": 3.926605504587156, "percentage": 39.27, "elapsed_time": "0:25:11", "remaining_time": "0:38:57", "throughput": 2656.4, "total_tokens": 4013896} {"current_steps": 14985, "total_steps": 38150, "loss": 0.4397, "lr": 3.804271094589826e-05, "epoch": 3.927916120576671, "percentage": 39.28, "elapsed_time": "0:25:11", "remaining_time": "0:38:56", "throughput": 2656.67, "total_tokens": 4015560} {"current_steps": 14990, "total_steps": 38150, "loss": 0.3717, "lr": 3.803295216315532e-05, "epoch": 3.929226736566186, "percentage": 39.29, "elapsed_time": "0:25:11", "remaining_time": "0:38:55", "throughput": 2656.66, "total_tokens": 4016696} {"current_steps": 14995, "total_steps": 38150, "loss": 0.3805, "lr": 3.802319065263801e-05, "epoch": 3.9305373525557012, "percentage": 39.31, "elapsed_time": "0:25:12", "remaining_time": "0:38:55", "throughput": 2656.65, "total_tokens": 4017800} {"current_steps": 15000, "total_steps": 38150, "loss": 0.3815, "lr": 3.8013426416389385e-05, "epoch": 3.9318479685452163, "percentage": 39.32, "elapsed_time": "0:25:12", "remaining_time": "0:38:54", "throughput": 2656.77, "total_tokens": 4019224} {"current_steps": 15005, "total_steps": 38150, "loss": 0.3814, "lr": 3.80036594564531e-05, "epoch": 3.9331585845347314, "percentage": 39.33, "elapsed_time": "0:25:13", "remaining_time": "0:38:54", "throughput": 2656.84, "total_tokens": 4020488} {"current_steps": 15010, "total_steps": 38150, "loss": 0.3393, "lr": 3.799388977487337e-05, "epoch": 3.9344692005242465, "percentage": 39.34, "elapsed_time": "0:25:13", "remaining_time": "0:38:53", "throughput": 2656.82, "total_tokens": 4021592} {"current_steps": 15015, "total_steps": 38150, "loss": 0.3479, "lr": 3.798411737369495e-05, "epoch": 3.9357798165137616, "percentage": 39.36, "elapsed_time": "0:25:14", "remaining_time": "0:38:52", "throughput": 2656.83, "total_tokens": 4022728} {"current_steps": 15020, "total_steps": 38150, "loss": 0.7378, "lr": 3.7974342254963214e-05, "epoch": 3.9370904325032763, "percentage": 39.37, "elapsed_time": "0:25:14", "remaining_time": "0:38:52", "throughput": 2657.04, "total_tokens": 4024328} {"current_steps": 15025, "total_steps": 38150, "loss": 0.4576, "lr": 3.7964564420724044e-05, "epoch": 3.938401048492792, "percentage": 39.38, "elapsed_time": "0:25:15", "remaining_time": "0:38:51", "throughput": 2657.23, "total_tokens": 4025880} {"current_steps": 15030, "total_steps": 38150, "loss": 0.725, "lr": 3.7954783873023955e-05, "epoch": 3.9397116644823065, "percentage": 39.4, "elapsed_time": "0:25:15", "remaining_time": "0:38:51", "throughput": 2657.32, "total_tokens": 4027192} {"current_steps": 15035, "total_steps": 38150, "loss": 0.3187, "lr": 3.7945000613909975e-05, "epoch": 3.941022280471822, "percentage": 39.41, "elapsed_time": "0:25:15", "remaining_time": "0:38:50", "throughput": 2657.39, "total_tokens": 4028536} {"current_steps": 15040, "total_steps": 38150, "loss": 0.4039, "lr": 3.793521464542974e-05, "epoch": 3.9423328964613367, "percentage": 39.42, "elapsed_time": "0:25:16", "remaining_time": "0:38:50", "throughput": 2657.5, "total_tokens": 4029944} {"current_steps": 15045, "total_steps": 38150, "loss": 0.473, "lr": 3.7925425969631435e-05, "epoch": 3.9436435124508518, "percentage": 39.44, "elapsed_time": "0:25:16", "remaining_time": "0:38:49", "throughput": 2657.51, "total_tokens": 4031080} {"current_steps": 15050, "total_steps": 38150, "loss": 0.3016, "lr": 3.7915634588563804e-05, "epoch": 3.944954128440367, "percentage": 39.45, "elapsed_time": "0:25:17", "remaining_time": "0:38:49", "throughput": 2657.85, "total_tokens": 4033128} {"current_steps": 15055, "total_steps": 38150, "loss": 0.4441, "lr": 3.790584050427616e-05, "epoch": 3.946264744429882, "percentage": 39.46, "elapsed_time": "0:25:17", "remaining_time": "0:38:48", "throughput": 2657.97, "total_tokens": 4034472} {"current_steps": 15060, "total_steps": 38150, "loss": 0.4492, "lr": 3.7896043718818406e-05, "epoch": 3.947575360419397, "percentage": 39.48, "elapsed_time": "0:25:18", "remaining_time": "0:38:47", "throughput": 2658.06, "total_tokens": 4035768} {"current_steps": 15065, "total_steps": 38150, "loss": 0.4784, "lr": 3.788624423424099e-05, "epoch": 3.948885976408912, "percentage": 39.49, "elapsed_time": "0:25:18", "remaining_time": "0:38:47", "throughput": 2658.06, "total_tokens": 4036984} {"current_steps": 15070, "total_steps": 38150, "loss": 0.7114, "lr": 3.7876442052594915e-05, "epoch": 3.9501965923984272, "percentage": 39.5, "elapsed_time": "0:25:19", "remaining_time": "0:38:46", "throughput": 2658.11, "total_tokens": 4038184} {"current_steps": 15075, "total_steps": 38150, "loss": 0.3764, "lr": 3.7866637175931774e-05, "epoch": 3.9515072083879423, "percentage": 39.52, "elapsed_time": "0:25:19", "remaining_time": "0:38:46", "throughput": 2658.19, "total_tokens": 4039448} {"current_steps": 15080, "total_steps": 38150, "loss": 0.4428, "lr": 3.7856829606303696e-05, "epoch": 3.9528178243774574, "percentage": 39.53, "elapsed_time": "0:25:20", "remaining_time": "0:38:45", "throughput": 2658.27, "total_tokens": 4040792} {"current_steps": 15085, "total_steps": 38150, "loss": 0.4042, "lr": 3.784701934576339e-05, "epoch": 3.9541284403669725, "percentage": 39.54, "elapsed_time": "0:25:20", "remaining_time": "0:38:44", "throughput": 2658.28, "total_tokens": 4042008} {"current_steps": 15090, "total_steps": 38150, "loss": 0.3299, "lr": 3.783720639636415e-05, "epoch": 3.9554390563564876, "percentage": 39.55, "elapsed_time": "0:25:20", "remaining_time": "0:38:44", "throughput": 2658.41, "total_tokens": 4043368} {"current_steps": 15095, "total_steps": 38150, "loss": 0.4979, "lr": 3.782739076015978e-05, "epoch": 3.9567496723460027, "percentage": 39.57, "elapsed_time": "0:25:21", "remaining_time": "0:38:43", "throughput": 2658.39, "total_tokens": 4044472} {"current_steps": 15100, "total_steps": 38150, "loss": 0.2946, "lr": 3.7817572439204695e-05, "epoch": 3.958060288335518, "percentage": 39.58, "elapsed_time": "0:25:21", "remaining_time": "0:38:43", "throughput": 2658.28, "total_tokens": 4045400} {"current_steps": 15105, "total_steps": 38150, "loss": 0.3135, "lr": 3.780775143555384e-05, "epoch": 3.959370904325033, "percentage": 39.59, "elapsed_time": "0:25:22", "remaining_time": "0:38:42", "throughput": 2658.4, "total_tokens": 4046760} {"current_steps": 15110, "total_steps": 38150, "loss": 0.4704, "lr": 3.779792775126275e-05, "epoch": 3.960681520314548, "percentage": 39.61, "elapsed_time": "0:25:22", "remaining_time": "0:38:41", "throughput": 2658.61, "total_tokens": 4048360} {"current_steps": 15115, "total_steps": 38150, "loss": 0.3108, "lr": 3.778810138838748e-05, "epoch": 3.9619921363040627, "percentage": 39.62, "elapsed_time": "0:25:23", "remaining_time": "0:38:41", "throughput": 2658.64, "total_tokens": 4049528} {"current_steps": 15120, "total_steps": 38150, "loss": 0.5345, "lr": 3.777827234898469e-05, "epoch": 3.963302752293578, "percentage": 39.63, "elapsed_time": "0:25:23", "remaining_time": "0:38:40", "throughput": 2658.65, "total_tokens": 4050664} {"current_steps": 15125, "total_steps": 38150, "loss": 0.4709, "lr": 3.776844063511158e-05, "epoch": 3.964613368283093, "percentage": 39.65, "elapsed_time": "0:25:24", "remaining_time": "0:38:40", "throughput": 2658.85, "total_tokens": 4052216} {"current_steps": 15130, "total_steps": 38150, "loss": 0.4766, "lr": 3.7758606248825914e-05, "epoch": 3.9659239842726084, "percentage": 39.66, "elapsed_time": "0:25:24", "remaining_time": "0:38:39", "throughput": 2659.01, "total_tokens": 4053720} {"current_steps": 15135, "total_steps": 38150, "loss": 0.599, "lr": 3.774876919218599e-05, "epoch": 3.967234600262123, "percentage": 39.67, "elapsed_time": "0:25:24", "remaining_time": "0:38:38", "throughput": 2659.14, "total_tokens": 4055080} {"current_steps": 15140, "total_steps": 38150, "loss": 0.3467, "lr": 3.773892946725071e-05, "epoch": 3.968545216251638, "percentage": 39.69, "elapsed_time": "0:25:25", "remaining_time": "0:38:38", "throughput": 2659.18, "total_tokens": 4056328} {"current_steps": 15145, "total_steps": 38150, "loss": 0.4805, "lr": 3.7729087076079505e-05, "epoch": 3.9698558322411532, "percentage": 39.7, "elapsed_time": "0:25:25", "remaining_time": "0:38:37", "throughput": 2659.4, "total_tokens": 4057944} {"current_steps": 15150, "total_steps": 38150, "loss": 0.4119, "lr": 3.771924202073236e-05, "epoch": 3.9711664482306683, "percentage": 39.71, "elapsed_time": "0:25:26", "remaining_time": "0:38:37", "throughput": 2659.44, "total_tokens": 4059128} {"current_steps": 15155, "total_steps": 38150, "loss": 0.3223, "lr": 3.770939430326985e-05, "epoch": 3.9724770642201834, "percentage": 39.72, "elapsed_time": "0:25:26", "remaining_time": "0:38:36", "throughput": 2659.55, "total_tokens": 4060472} {"current_steps": 15160, "total_steps": 38150, "loss": 0.3399, "lr": 3.7699543925753064e-05, "epoch": 3.9737876802096985, "percentage": 39.74, "elapsed_time": "0:25:27", "remaining_time": "0:38:35", "throughput": 2659.56, "total_tokens": 4061608} {"current_steps": 15165, "total_steps": 38150, "loss": 0.4196, "lr": 3.768969089024368e-05, "epoch": 3.9750982961992136, "percentage": 39.75, "elapsed_time": "0:25:27", "remaining_time": "0:38:35", "throughput": 2659.91, "total_tokens": 4063624} {"current_steps": 15170, "total_steps": 38150, "loss": 0.3225, "lr": 3.767983519880392e-05, "epoch": 3.9764089121887287, "percentage": 39.76, "elapsed_time": "0:25:28", "remaining_time": "0:38:35", "throughput": 2660.42, "total_tokens": 4066152} {"current_steps": 15175, "total_steps": 38150, "loss": 0.4197, "lr": 3.766997685349656e-05, "epoch": 3.977719528178244, "percentage": 39.78, "elapsed_time": "0:25:28", "remaining_time": "0:38:34", "throughput": 2660.42, "total_tokens": 4067304} {"current_steps": 15180, "total_steps": 38150, "loss": 0.3074, "lr": 3.766011585638494e-05, "epoch": 3.979030144167759, "percentage": 39.79, "elapsed_time": "0:25:29", "remaining_time": "0:38:34", "throughput": 2660.43, "total_tokens": 4068456} {"current_steps": 15185, "total_steps": 38150, "loss": 0.2531, "lr": 3.765025220953294e-05, "epoch": 3.980340760157274, "percentage": 39.8, "elapsed_time": "0:25:29", "remaining_time": "0:38:33", "throughput": 2660.55, "total_tokens": 4069864} {"current_steps": 15190, "total_steps": 38150, "loss": 0.3422, "lr": 3.764038591500502e-05, "epoch": 3.981651376146789, "percentage": 39.82, "elapsed_time": "0:25:30", "remaining_time": "0:38:32", "throughput": 2660.57, "total_tokens": 4071096} {"current_steps": 15195, "total_steps": 38150, "loss": 0.6255, "lr": 3.7630516974866166e-05, "epoch": 3.982961992136304, "percentage": 39.83, "elapsed_time": "0:25:30", "remaining_time": "0:38:32", "throughput": 2660.67, "total_tokens": 4072504} {"current_steps": 15200, "total_steps": 38150, "loss": 0.3248, "lr": 3.7620645391181926e-05, "epoch": 3.9842726081258193, "percentage": 39.84, "elapsed_time": "0:25:31", "remaining_time": "0:38:31", "throughput": 2660.77, "total_tokens": 4073880} {"current_steps": 15205, "total_steps": 38150, "loss": 0.38, "lr": 3.761077116601842e-05, "epoch": 3.9855832241153344, "percentage": 39.86, "elapsed_time": "0:25:31", "remaining_time": "0:38:31", "throughput": 2660.82, "total_tokens": 4075096} {"current_steps": 15210, "total_steps": 38150, "loss": 0.6168, "lr": 3.760089430144229e-05, "epoch": 3.986893840104849, "percentage": 39.87, "elapsed_time": "0:25:32", "remaining_time": "0:38:30", "throughput": 2660.98, "total_tokens": 4076648} {"current_steps": 15215, "total_steps": 38150, "loss": 0.4509, "lr": 3.759101479952076e-05, "epoch": 3.9882044560943646, "percentage": 39.88, "elapsed_time": "0:25:32", "remaining_time": "0:38:30", "throughput": 2661.11, "total_tokens": 4078088} {"current_steps": 15220, "total_steps": 38150, "loss": 0.4403, "lr": 3.7581132662321597e-05, "epoch": 3.9895150720838792, "percentage": 39.9, "elapsed_time": "0:25:32", "remaining_time": "0:38:29", "throughput": 2661.17, "total_tokens": 4079416} {"current_steps": 15225, "total_steps": 38150, "loss": 0.3731, "lr": 3.7571247891913095e-05, "epoch": 3.9908256880733948, "percentage": 39.91, "elapsed_time": "0:25:33", "remaining_time": "0:38:29", "throughput": 2661.46, "total_tokens": 4081288} {"current_steps": 15230, "total_steps": 38150, "loss": 0.5849, "lr": 3.756136049036413e-05, "epoch": 3.9921363040629094, "percentage": 39.92, "elapsed_time": "0:25:33", "remaining_time": "0:38:28", "throughput": 2661.56, "total_tokens": 4082584} {"current_steps": 15235, "total_steps": 38150, "loss": 0.3505, "lr": 3.7551470459744126e-05, "epoch": 3.9934469200524245, "percentage": 39.93, "elapsed_time": "0:25:34", "remaining_time": "0:38:27", "throughput": 2661.62, "total_tokens": 4083848} {"current_steps": 15240, "total_steps": 38150, "loss": 0.4316, "lr": 3.754157780212304e-05, "epoch": 3.9947575360419396, "percentage": 39.95, "elapsed_time": "0:25:34", "remaining_time": "0:38:27", "throughput": 2661.67, "total_tokens": 4085160} {"current_steps": 15245, "total_steps": 38150, "loss": 0.2167, "lr": 3.753168251957139e-05, "epoch": 3.9960681520314547, "percentage": 39.96, "elapsed_time": "0:25:35", "remaining_time": "0:38:26", "throughput": 2661.84, "total_tokens": 4086600} {"current_steps": 15250, "total_steps": 38150, "loss": 0.316, "lr": 3.752178461416024e-05, "epoch": 3.99737876802097, "percentage": 39.97, "elapsed_time": "0:25:35", "remaining_time": "0:38:26", "throughput": 2661.84, "total_tokens": 4087736} {"current_steps": 15255, "total_steps": 38150, "loss": 0.4972, "lr": 3.75118840879612e-05, "epoch": 3.998689384010485, "percentage": 39.99, "elapsed_time": "0:25:36", "remaining_time": "0:38:25", "throughput": 2661.9, "total_tokens": 4089000} {"current_steps": 15260, "total_steps": 38150, "loss": 0.5023, "lr": 3.750198094304644e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:25:36", "remaining_time": "0:38:24", "throughput": 2661.57, "total_tokens": 4089872} {"current_steps": 15264, "total_steps": 38150, "eval_loss": 0.5102683901786804, "epoch": 4.001048492791612, "percentage": 40.01, "elapsed_time": "0:25:54", "remaining_time": "0:38:50", "throughput": 2632.34, "total_tokens": 4090736} {"current_steps": 15265, "total_steps": 38150, "loss": 0.4168, "lr": 3.749207518148869e-05, "epoch": 4.001310615989515, "percentage": 40.01, "elapsed_time": "0:25:55", "remaining_time": "0:38:51", "throughput": 2630.19, "total_tokens": 4091024} {"current_steps": 15270, "total_steps": 38150, "loss": 0.2953, "lr": 3.7482166805361175e-05, "epoch": 4.00262123197903, "percentage": 40.03, "elapsed_time": "0:25:55", "remaining_time": "0:38:51", "throughput": 2630.25, "total_tokens": 4092256} {"current_steps": 15275, "total_steps": 38150, "loss": 0.2694, "lr": 3.747225581673771e-05, "epoch": 4.003931847968545, "percentage": 40.04, "elapsed_time": "0:25:56", "remaining_time": "0:38:50", "throughput": 2630.11, "total_tokens": 4093168} {"current_steps": 15280, "total_steps": 38150, "loss": 0.3101, "lr": 3.746234221769266e-05, "epoch": 4.00524246395806, "percentage": 40.05, "elapsed_time": "0:25:56", "remaining_time": "0:38:49", "throughput": 2630.21, "total_tokens": 4094480} {"current_steps": 15285, "total_steps": 38150, "loss": 1.021, "lr": 3.7452426010300915e-05, "epoch": 4.006553079947575, "percentage": 40.07, "elapsed_time": "0:25:57", "remaining_time": "0:38:49", "throughput": 2630.13, "total_tokens": 4095472} {"current_steps": 15290, "total_steps": 38150, "loss": 0.4153, "lr": 3.7442507196637925e-05, "epoch": 4.007863695937091, "percentage": 40.08, "elapsed_time": "0:25:57", "remaining_time": "0:38:48", "throughput": 2630.15, "total_tokens": 4096656} {"current_steps": 15295, "total_steps": 38150, "loss": 0.5239, "lr": 3.743258577877968e-05, "epoch": 4.009174311926605, "percentage": 40.09, "elapsed_time": "0:25:58", "remaining_time": "0:38:48", "throughput": 2630.14, "total_tokens": 4097760} {"current_steps": 15300, "total_steps": 38150, "loss": 0.274, "lr": 3.74226617588027e-05, "epoch": 4.010484927916121, "percentage": 40.1, "elapsed_time": "0:25:58", "remaining_time": "0:38:47", "throughput": 2630.28, "total_tokens": 4099168} {"current_steps": 15305, "total_steps": 38150, "loss": 0.3281, "lr": 3.7412735138784096e-05, "epoch": 4.011795543905635, "percentage": 40.12, "elapsed_time": "0:25:58", "remaining_time": "0:38:46", "throughput": 2630.39, "total_tokens": 4100576} {"current_steps": 15310, "total_steps": 38150, "loss": 0.3521, "lr": 3.740280592080147e-05, "epoch": 4.013106159895151, "percentage": 40.13, "elapsed_time": "0:25:59", "remaining_time": "0:38:46", "throughput": 2630.5, "total_tokens": 4101904} {"current_steps": 15315, "total_steps": 38150, "loss": 0.3271, "lr": 3.7392874106932985e-05, "epoch": 4.014416775884666, "percentage": 40.14, "elapsed_time": "0:25:59", "remaining_time": "0:38:45", "throughput": 2630.72, "total_tokens": 4103584} {"current_steps": 15320, "total_steps": 38150, "loss": 0.3251, "lr": 3.738293969925737e-05, "epoch": 4.015727391874181, "percentage": 40.16, "elapsed_time": "0:26:00", "remaining_time": "0:38:45", "throughput": 2630.68, "total_tokens": 4104640} {"current_steps": 15325, "total_steps": 38150, "loss": 0.3175, "lr": 3.737300269985388e-05, "epoch": 4.017038007863696, "percentage": 40.17, "elapsed_time": "0:26:00", "remaining_time": "0:38:44", "throughput": 2630.88, "total_tokens": 4106272} {"current_steps": 15330, "total_steps": 38150, "loss": 0.3868, "lr": 3.736306311080229e-05, "epoch": 4.018348623853211, "percentage": 40.18, "elapsed_time": "0:26:01", "remaining_time": "0:38:44", "throughput": 2631.08, "total_tokens": 4107808} {"current_steps": 15335, "total_steps": 38150, "loss": 0.5514, "lr": 3.7353120934182956e-05, "epoch": 4.019659239842726, "percentage": 40.2, "elapsed_time": "0:26:01", "remaining_time": "0:38:43", "throughput": 2631.19, "total_tokens": 4109152} {"current_steps": 15340, "total_steps": 38150, "loss": 0.22, "lr": 3.7343176172076755e-05, "epoch": 4.0209698558322415, "percentage": 40.21, "elapsed_time": "0:26:02", "remaining_time": "0:38:42", "throughput": 2631.27, "total_tokens": 4110496} {"current_steps": 15345, "total_steps": 38150, "loss": 0.3097, "lr": 3.7333228826565115e-05, "epoch": 4.022280471821756, "percentage": 40.22, "elapsed_time": "0:26:02", "remaining_time": "0:38:42", "throughput": 2631.39, "total_tokens": 4111824} {"current_steps": 15350, "total_steps": 38150, "loss": 0.3675, "lr": 3.7323278899729986e-05, "epoch": 4.023591087811272, "percentage": 40.24, "elapsed_time": "0:26:03", "remaining_time": "0:38:41", "throughput": 2631.35, "total_tokens": 4112880} {"current_steps": 15355, "total_steps": 38150, "loss": 0.3797, "lr": 3.731332639365387e-05, "epoch": 4.024901703800786, "percentage": 40.25, "elapsed_time": "0:26:03", "remaining_time": "0:38:40", "throughput": 2631.25, "total_tokens": 4113840} {"current_steps": 15360, "total_steps": 38150, "loss": 0.3725, "lr": 3.7303371310419835e-05, "epoch": 4.026212319790301, "percentage": 40.26, "elapsed_time": "0:26:03", "remaining_time": "0:38:40", "throughput": 2631.17, "total_tokens": 4114800} {"current_steps": 15365, "total_steps": 38150, "loss": 0.391, "lr": 3.729341365211143e-05, "epoch": 4.027522935779817, "percentage": 40.28, "elapsed_time": "0:26:04", "remaining_time": "0:38:39", "throughput": 2631.4, "total_tokens": 4116416} {"current_steps": 15370, "total_steps": 38150, "loss": 0.4312, "lr": 3.7283453420812786e-05, "epoch": 4.028833551769331, "percentage": 40.29, "elapsed_time": "0:26:04", "remaining_time": "0:38:39", "throughput": 2631.44, "total_tokens": 4117584} {"current_steps": 15375, "total_steps": 38150, "loss": 0.4443, "lr": 3.727349061860857e-05, "epoch": 4.030144167758847, "percentage": 40.3, "elapsed_time": "0:26:05", "remaining_time": "0:38:38", "throughput": 2631.51, "total_tokens": 4118848} {"current_steps": 15380, "total_steps": 38150, "loss": 0.3164, "lr": 3.726352524758397e-05, "epoch": 4.031454783748361, "percentage": 40.31, "elapsed_time": "0:26:05", "remaining_time": "0:38:37", "throughput": 2631.55, "total_tokens": 4120032} {"current_steps": 15385, "total_steps": 38150, "loss": 0.3099, "lr": 3.725355730982474e-05, "epoch": 4.032765399737877, "percentage": 40.33, "elapsed_time": "0:26:06", "remaining_time": "0:38:37", "throughput": 2631.78, "total_tokens": 4121680} {"current_steps": 15390, "total_steps": 38150, "loss": 0.2075, "lr": 3.724358680741713e-05, "epoch": 4.034076015727392, "percentage": 40.34, "elapsed_time": "0:26:06", "remaining_time": "0:38:36", "throughput": 2631.78, "total_tokens": 4122800} {"current_steps": 15395, "total_steps": 38150, "loss": 0.397, "lr": 3.723361374244795e-05, "epoch": 4.035386631716907, "percentage": 40.35, "elapsed_time": "0:26:07", "remaining_time": "0:38:36", "throughput": 2631.94, "total_tokens": 4124336} {"current_steps": 15400, "total_steps": 38150, "loss": 0.4406, "lr": 3.722363811700455e-05, "epoch": 4.036697247706422, "percentage": 40.37, "elapsed_time": "0:26:07", "remaining_time": "0:38:35", "throughput": 2632.16, "total_tokens": 4125904} {"current_steps": 15405, "total_steps": 38150, "loss": 0.3327, "lr": 3.721365993317482e-05, "epoch": 4.038007863695937, "percentage": 40.38, "elapsed_time": "0:26:07", "remaining_time": "0:38:35", "throughput": 2632.29, "total_tokens": 4127376} {"current_steps": 15410, "total_steps": 38150, "loss": 0.4066, "lr": 3.720367919304717e-05, "epoch": 4.039318479685452, "percentage": 40.39, "elapsed_time": "0:26:08", "remaining_time": "0:38:34", "throughput": 2632.5, "total_tokens": 4128944} {"current_steps": 15415, "total_steps": 38150, "loss": 0.2773, "lr": 3.7193695898710545e-05, "epoch": 4.0406290956749675, "percentage": 40.41, "elapsed_time": "0:26:08", "remaining_time": "0:38:33", "throughput": 2632.53, "total_tokens": 4130176} {"current_steps": 15420, "total_steps": 38150, "loss": 0.3127, "lr": 3.718371005225445e-05, "epoch": 4.041939711664482, "percentage": 40.42, "elapsed_time": "0:26:09", "remaining_time": "0:38:33", "throughput": 2632.71, "total_tokens": 4131680} {"current_steps": 15425, "total_steps": 38150, "loss": 0.3635, "lr": 3.717372165576888e-05, "epoch": 4.043250327653998, "percentage": 40.43, "elapsed_time": "0:26:09", "remaining_time": "0:38:32", "throughput": 2632.68, "total_tokens": 4132736} {"current_steps": 15430, "total_steps": 38150, "loss": 0.2235, "lr": 3.71637307113444e-05, "epoch": 4.044560943643512, "percentage": 40.45, "elapsed_time": "0:26:10", "remaining_time": "0:38:32", "throughput": 2632.81, "total_tokens": 4134240} {"current_steps": 15435, "total_steps": 38150, "loss": 0.3859, "lr": 3.715373722107211e-05, "epoch": 4.045871559633028, "percentage": 40.46, "elapsed_time": "0:26:10", "remaining_time": "0:38:31", "throughput": 2632.95, "total_tokens": 4135616} {"current_steps": 15440, "total_steps": 38150, "loss": 0.3887, "lr": 3.714374118704362e-05, "epoch": 4.047182175622543, "percentage": 40.47, "elapsed_time": "0:26:11", "remaining_time": "0:38:31", "throughput": 2633.19, "total_tokens": 4137376} {"current_steps": 15445, "total_steps": 38150, "loss": 0.5808, "lr": 3.713374261135107e-05, "epoch": 4.048492791612058, "percentage": 40.48, "elapsed_time": "0:26:11", "remaining_time": "0:38:30", "throughput": 2633.26, "total_tokens": 4138640} {"current_steps": 15450, "total_steps": 38150, "loss": 0.3088, "lr": 3.712374149608717e-05, "epoch": 4.049803407601573, "percentage": 40.5, "elapsed_time": "0:26:12", "remaining_time": "0:38:29", "throughput": 2633.4, "total_tokens": 4140032} {"current_steps": 15455, "total_steps": 38150, "loss": 0.5765, "lr": 3.711373784334511e-05, "epoch": 4.051114023591087, "percentage": 40.51, "elapsed_time": "0:26:12", "remaining_time": "0:38:29", "throughput": 2633.54, "total_tokens": 4141488} {"current_steps": 15460, "total_steps": 38150, "loss": 0.5041, "lr": 3.7103731655218664e-05, "epoch": 4.052424639580603, "percentage": 40.52, "elapsed_time": "0:26:13", "remaining_time": "0:38:28", "throughput": 2633.67, "total_tokens": 4142864} {"current_steps": 15465, "total_steps": 38150, "loss": 0.2927, "lr": 3.7093722933802095e-05, "epoch": 4.053735255570118, "percentage": 40.54, "elapsed_time": "0:26:13", "remaining_time": "0:38:28", "throughput": 2634.3, "total_tokens": 4145888} {"current_steps": 15470, "total_steps": 38150, "loss": 0.3363, "lr": 3.70837116811902e-05, "epoch": 4.055045871559633, "percentage": 40.55, "elapsed_time": "0:26:14", "remaining_time": "0:38:27", "throughput": 2634.43, "total_tokens": 4147264} {"current_steps": 15475, "total_steps": 38150, "loss": 0.3501, "lr": 3.707369789947834e-05, "epoch": 4.056356487549148, "percentage": 40.56, "elapsed_time": "0:26:14", "remaining_time": "0:38:27", "throughput": 2634.73, "total_tokens": 4149184} {"current_steps": 15480, "total_steps": 38150, "loss": 0.4669, "lr": 3.706368159076238e-05, "epoch": 4.057667103538663, "percentage": 40.58, "elapsed_time": "0:26:15", "remaining_time": "0:38:26", "throughput": 2634.81, "total_tokens": 4150624} {"current_steps": 15485, "total_steps": 38150, "loss": 0.378, "lr": 3.7053662757138686e-05, "epoch": 4.058977719528178, "percentage": 40.59, "elapsed_time": "0:26:15", "remaining_time": "0:38:26", "throughput": 2635.03, "total_tokens": 4152256} {"current_steps": 15490, "total_steps": 38150, "loss": 0.3569, "lr": 3.704364140070421e-05, "epoch": 4.0602883355176935, "percentage": 40.6, "elapsed_time": "0:26:16", "remaining_time": "0:38:25", "throughput": 2635.08, "total_tokens": 4153552} {"current_steps": 15495, "total_steps": 38150, "loss": 0.3556, "lr": 3.703361752355641e-05, "epoch": 4.061598951507208, "percentage": 40.62, "elapsed_time": "0:26:16", "remaining_time": "0:38:25", "throughput": 2635.16, "total_tokens": 4154800} {"current_steps": 15500, "total_steps": 38150, "loss": 0.2273, "lr": 3.702359112779325e-05, "epoch": 4.062909567496724, "percentage": 40.63, "elapsed_time": "0:26:17", "remaining_time": "0:38:24", "throughput": 2635.13, "total_tokens": 4155872} {"current_steps": 15505, "total_steps": 38150, "loss": 0.3922, "lr": 3.701356221551324e-05, "epoch": 4.064220183486238, "percentage": 40.64, "elapsed_time": "0:26:17", "remaining_time": "0:38:24", "throughput": 2635.21, "total_tokens": 4157200} {"current_steps": 15510, "total_steps": 38150, "loss": 0.2537, "lr": 3.700353078881541e-05, "epoch": 4.065530799475754, "percentage": 40.66, "elapsed_time": "0:26:17", "remaining_time": "0:38:23", "throughput": 2635.27, "total_tokens": 4158416} {"current_steps": 15515, "total_steps": 38150, "loss": 0.3834, "lr": 3.699349684979932e-05, "epoch": 4.066841415465269, "percentage": 40.67, "elapsed_time": "0:26:18", "remaining_time": "0:38:22", "throughput": 2635.44, "total_tokens": 4159888} {"current_steps": 15520, "total_steps": 38150, "loss": 0.1872, "lr": 3.6983460400565086e-05, "epoch": 4.068152031454784, "percentage": 40.68, "elapsed_time": "0:26:18", "remaining_time": "0:38:22", "throughput": 2635.46, "total_tokens": 4161120} {"current_steps": 15525, "total_steps": 38150, "loss": 0.6093, "lr": 3.697342144321329e-05, "epoch": 4.069462647444299, "percentage": 40.69, "elapsed_time": "0:26:19", "remaining_time": "0:38:21", "throughput": 2635.49, "total_tokens": 4162288} {"current_steps": 15530, "total_steps": 38150, "loss": 0.4939, "lr": 3.6963379979845066e-05, "epoch": 4.070773263433814, "percentage": 40.71, "elapsed_time": "0:26:20", "remaining_time": "0:38:21", "throughput": 2635.96, "total_tokens": 4165056} {"current_steps": 15535, "total_steps": 38150, "loss": 0.363, "lr": 3.6953336012562084e-05, "epoch": 4.072083879423329, "percentage": 40.72, "elapsed_time": "0:26:20", "remaining_time": "0:38:20", "throughput": 2636.18, "total_tokens": 4166656} {"current_steps": 15540, "total_steps": 38150, "loss": 0.2511, "lr": 3.6943289543466536e-05, "epoch": 4.073394495412844, "percentage": 40.73, "elapsed_time": "0:26:20", "remaining_time": "0:38:20", "throughput": 2636.15, "total_tokens": 4167728} {"current_steps": 15545, "total_steps": 38150, "loss": 0.4394, "lr": 3.693324057466111e-05, "epoch": 4.074705111402359, "percentage": 40.75, "elapsed_time": "0:26:21", "remaining_time": "0:38:19", "throughput": 2636.25, "total_tokens": 4169120} {"current_steps": 15550, "total_steps": 38150, "loss": 0.2652, "lr": 3.692318910824906e-05, "epoch": 4.076015727391874, "percentage": 40.76, "elapsed_time": "0:26:21", "remaining_time": "0:38:19", "throughput": 2636.5, "total_tokens": 4170864} {"current_steps": 15555, "total_steps": 38150, "loss": 0.4412, "lr": 3.691313514633413e-05, "epoch": 4.077326343381389, "percentage": 40.77, "elapsed_time": "0:26:22", "remaining_time": "0:38:18", "throughput": 2636.42, "total_tokens": 4171824} {"current_steps": 15560, "total_steps": 38150, "loss": 0.3547, "lr": 3.69030786910206e-05, "epoch": 4.078636959370904, "percentage": 40.79, "elapsed_time": "0:26:22", "remaining_time": "0:38:17", "throughput": 2636.47, "total_tokens": 4173056} {"current_steps": 15565, "total_steps": 38150, "loss": 0.2977, "lr": 3.6893019744413265e-05, "epoch": 4.0799475753604195, "percentage": 40.8, "elapsed_time": "0:26:23", "remaining_time": "0:38:17", "throughput": 2636.41, "total_tokens": 4174080} {"current_steps": 15570, "total_steps": 38150, "loss": 0.3341, "lr": 3.688295830861744e-05, "epoch": 4.081258191349934, "percentage": 40.81, "elapsed_time": "0:26:23", "remaining_time": "0:38:16", "throughput": 2636.37, "total_tokens": 4175136} {"current_steps": 15575, "total_steps": 38150, "loss": 0.2839, "lr": 3.687289438573899e-05, "epoch": 4.08256880733945, "percentage": 40.83, "elapsed_time": "0:26:24", "remaining_time": "0:38:16", "throughput": 2636.34, "total_tokens": 4176208} {"current_steps": 15580, "total_steps": 38150, "loss": 0.3901, "lr": 3.6862827977884246e-05, "epoch": 4.083879423328964, "percentage": 40.84, "elapsed_time": "0:26:24", "remaining_time": "0:38:15", "throughput": 2636.48, "total_tokens": 4177680} {"current_steps": 15585, "total_steps": 38150, "loss": 0.339, "lr": 3.6852759087160105e-05, "epoch": 4.08519003931848, "percentage": 40.85, "elapsed_time": "0:26:25", "remaining_time": "0:38:15", "throughput": 2636.83, "total_tokens": 4179632} {"current_steps": 15590, "total_steps": 38150, "loss": 0.3367, "lr": 3.6842687715673977e-05, "epoch": 4.086500655307995, "percentage": 40.87, "elapsed_time": "0:26:25", "remaining_time": "0:38:14", "throughput": 2636.95, "total_tokens": 4180992} {"current_steps": 15595, "total_steps": 38150, "loss": 0.3727, "lr": 3.683261386553376e-05, "epoch": 4.08781127129751, "percentage": 40.88, "elapsed_time": "0:26:26", "remaining_time": "0:38:13", "throughput": 2637.18, "total_tokens": 4182608} {"current_steps": 15600, "total_steps": 38150, "loss": 0.3456, "lr": 3.6822537538847914e-05, "epoch": 4.089121887287025, "percentage": 40.89, "elapsed_time": "0:26:26", "remaining_time": "0:38:13", "throughput": 2637.29, "total_tokens": 4183952} {"current_steps": 15605, "total_steps": 38150, "loss": 0.3727, "lr": 3.6812458737725384e-05, "epoch": 4.09043250327654, "percentage": 40.9, "elapsed_time": "0:26:27", "remaining_time": "0:38:12", "throughput": 2637.58, "total_tokens": 4185920} {"current_steps": 15610, "total_steps": 38150, "loss": 0.3772, "lr": 3.680237746427565e-05, "epoch": 4.091743119266055, "percentage": 40.92, "elapsed_time": "0:26:27", "remaining_time": "0:38:12", "throughput": 2637.51, "total_tokens": 4186896} {"current_steps": 15615, "total_steps": 38150, "loss": 0.3554, "lr": 3.679229372060871e-05, "epoch": 4.0930537352555705, "percentage": 40.93, "elapsed_time": "0:26:27", "remaining_time": "0:38:11", "throughput": 2637.52, "total_tokens": 4188032} {"current_steps": 15620, "total_steps": 38150, "loss": 0.2968, "lr": 3.678220750883507e-05, "epoch": 4.094364351245085, "percentage": 40.94, "elapsed_time": "0:26:28", "remaining_time": "0:38:11", "throughput": 2637.72, "total_tokens": 4189728} {"current_steps": 15625, "total_steps": 38150, "loss": 0.4494, "lr": 3.6772118831065755e-05, "epoch": 4.095674967234601, "percentage": 40.96, "elapsed_time": "0:26:28", "remaining_time": "0:38:10", "throughput": 2637.81, "total_tokens": 4191024} {"current_steps": 15630, "total_steps": 38150, "loss": 0.5334, "lr": 3.6762027689412305e-05, "epoch": 4.096985583224115, "percentage": 40.97, "elapsed_time": "0:26:29", "remaining_time": "0:38:09", "throughput": 2638.01, "total_tokens": 4192672} {"current_steps": 15635, "total_steps": 38150, "loss": 0.435, "lr": 3.675193408598679e-05, "epoch": 4.09829619921363, "percentage": 40.98, "elapsed_time": "0:26:29", "remaining_time": "0:38:09", "throughput": 2638.19, "total_tokens": 4194144} {"current_steps": 15640, "total_steps": 38150, "loss": 0.3627, "lr": 3.674183802290178e-05, "epoch": 4.0996068152031455, "percentage": 41.0, "elapsed_time": "0:26:30", "remaining_time": "0:38:08", "throughput": 2638.48, "total_tokens": 4196128} {"current_steps": 15645, "total_steps": 38150, "loss": 0.3727, "lr": 3.6731739502270344e-05, "epoch": 4.10091743119266, "percentage": 41.01, "elapsed_time": "0:26:30", "remaining_time": "0:38:08", "throughput": 2638.7, "total_tokens": 4197856} {"current_steps": 15650, "total_steps": 38150, "loss": 0.3507, "lr": 3.6721638526206115e-05, "epoch": 4.102228047182176, "percentage": 41.02, "elapsed_time": "0:26:31", "remaining_time": "0:38:07", "throughput": 2638.71, "total_tokens": 4199008} {"current_steps": 15655, "total_steps": 38150, "loss": 0.3323, "lr": 3.671153509682319e-05, "epoch": 4.10353866317169, "percentage": 41.04, "elapsed_time": "0:26:31", "remaining_time": "0:38:07", "throughput": 2638.96, "total_tokens": 4200752} {"current_steps": 15660, "total_steps": 38150, "loss": 0.4535, "lr": 3.67014292162362e-05, "epoch": 4.104849279161206, "percentage": 41.05, "elapsed_time": "0:26:32", "remaining_time": "0:38:06", "throughput": 2638.94, "total_tokens": 4201888} {"current_steps": 15665, "total_steps": 38150, "loss": 0.291, "lr": 3.66913208865603e-05, "epoch": 4.1061598951507206, "percentage": 41.06, "elapsed_time": "0:26:32", "remaining_time": "0:38:06", "throughput": 2638.9, "total_tokens": 4202928} {"current_steps": 15670, "total_steps": 38150, "loss": 0.3099, "lr": 3.668121010991115e-05, "epoch": 4.107470511140236, "percentage": 41.07, "elapsed_time": "0:26:33", "remaining_time": "0:38:05", "throughput": 2639.02, "total_tokens": 4204304} {"current_steps": 15675, "total_steps": 38150, "loss": 0.3396, "lr": 3.66710968884049e-05, "epoch": 4.108781127129751, "percentage": 41.09, "elapsed_time": "0:26:33", "remaining_time": "0:38:04", "throughput": 2639.2, "total_tokens": 4205888} {"current_steps": 15680, "total_steps": 38150, "loss": 0.3335, "lr": 3.666098122415823e-05, "epoch": 4.110091743119266, "percentage": 41.1, "elapsed_time": "0:26:34", "remaining_time": "0:38:04", "throughput": 2639.47, "total_tokens": 4207728} {"current_steps": 15685, "total_steps": 38150, "loss": 0.358, "lr": 3.665086311928834e-05, "epoch": 4.111402359108781, "percentage": 41.11, "elapsed_time": "0:26:34", "remaining_time": "0:38:03", "throughput": 2639.47, "total_tokens": 4208848} {"current_steps": 15690, "total_steps": 38150, "loss": 0.2864, "lr": 3.664074257591293e-05, "epoch": 4.1127129750982965, "percentage": 41.13, "elapsed_time": "0:26:35", "remaining_time": "0:38:03", "throughput": 2639.57, "total_tokens": 4210144} {"current_steps": 15695, "total_steps": 38150, "loss": 0.3717, "lr": 3.6630619596150225e-05, "epoch": 4.114023591087811, "percentage": 41.14, "elapsed_time": "0:26:35", "remaining_time": "0:38:02", "throughput": 2639.64, "total_tokens": 4211488} {"current_steps": 15700, "total_steps": 38150, "loss": 0.3887, "lr": 3.662049418211892e-05, "epoch": 4.115334207077327, "percentage": 41.15, "elapsed_time": "0:26:35", "remaining_time": "0:38:02", "throughput": 2639.87, "total_tokens": 4213184} {"current_steps": 15705, "total_steps": 38150, "loss": 0.5167, "lr": 3.6610366335938266e-05, "epoch": 4.116644823066841, "percentage": 41.17, "elapsed_time": "0:26:36", "remaining_time": "0:38:01", "throughput": 2640.0, "total_tokens": 4214624} {"current_steps": 15710, "total_steps": 38150, "loss": 0.3358, "lr": 3.6600236059728e-05, "epoch": 4.117955439056357, "percentage": 41.18, "elapsed_time": "0:26:36", "remaining_time": "0:38:00", "throughput": 2639.88, "total_tokens": 4215536} {"current_steps": 15715, "total_steps": 38150, "loss": 0.4199, "lr": 3.6590103355608374e-05, "epoch": 4.1192660550458715, "percentage": 41.19, "elapsed_time": "0:26:37", "remaining_time": "0:38:00", "throughput": 2639.86, "total_tokens": 4216624} {"current_steps": 15720, "total_steps": 38150, "loss": 0.4896, "lr": 3.657996822570013e-05, "epoch": 4.120576671035387, "percentage": 41.21, "elapsed_time": "0:26:37", "remaining_time": "0:37:59", "throughput": 2639.98, "total_tokens": 4218048} {"current_steps": 15725, "total_steps": 38150, "loss": 0.3197, "lr": 3.656983067212456e-05, "epoch": 4.121887287024902, "percentage": 41.22, "elapsed_time": "0:26:38", "remaining_time": "0:37:59", "throughput": 2640.16, "total_tokens": 4219552} {"current_steps": 15730, "total_steps": 38150, "loss": 0.3096, "lr": 3.655969069700341e-05, "epoch": 4.123197903014416, "percentage": 41.23, "elapsed_time": "0:26:38", "remaining_time": "0:37:58", "throughput": 2640.08, "total_tokens": 4220528} {"current_steps": 15735, "total_steps": 38150, "loss": 0.3777, "lr": 3.654954830245898e-05, "epoch": 4.124508519003932, "percentage": 41.25, "elapsed_time": "0:26:39", "remaining_time": "0:37:57", "throughput": 2640.04, "total_tokens": 4221552} {"current_steps": 15740, "total_steps": 38150, "loss": 0.3656, "lr": 3.6539403490614046e-05, "epoch": 4.1258191349934465, "percentage": 41.26, "elapsed_time": "0:26:39", "remaining_time": "0:37:57", "throughput": 2640.1, "total_tokens": 4222784} {"current_steps": 15745, "total_steps": 38150, "loss": 0.3299, "lr": 3.6529256263591885e-05, "epoch": 4.127129750982962, "percentage": 41.27, "elapsed_time": "0:26:39", "remaining_time": "0:37:56", "throughput": 2640.08, "total_tokens": 4223840} {"current_steps": 15750, "total_steps": 38150, "loss": 0.5596, "lr": 3.651910662351632e-05, "epoch": 4.128440366972477, "percentage": 41.28, "elapsed_time": "0:26:40", "remaining_time": "0:37:56", "throughput": 2640.44, "total_tokens": 4225728} {"current_steps": 15755, "total_steps": 38150, "loss": 0.3168, "lr": 3.650895457251165e-05, "epoch": 4.129750982961992, "percentage": 41.3, "elapsed_time": "0:26:40", "remaining_time": "0:37:55", "throughput": 2640.58, "total_tokens": 4227120} {"current_steps": 15760, "total_steps": 38150, "loss": 0.3855, "lr": 3.6498800112702664e-05, "epoch": 4.131061598951507, "percentage": 41.31, "elapsed_time": "0:26:41", "remaining_time": "0:37:54", "throughput": 2640.56, "total_tokens": 4228240} {"current_steps": 15765, "total_steps": 38150, "loss": 0.414, "lr": 3.648864324621468e-05, "epoch": 4.1323722149410225, "percentage": 41.32, "elapsed_time": "0:26:41", "remaining_time": "0:37:54", "throughput": 2640.7, "total_tokens": 4229696} {"current_steps": 15770, "total_steps": 38150, "loss": 0.3102, "lr": 3.647848397517353e-05, "epoch": 4.133682830930537, "percentage": 41.34, "elapsed_time": "0:26:42", "remaining_time": "0:37:53", "throughput": 2640.79, "total_tokens": 4231024} {"current_steps": 15775, "total_steps": 38150, "loss": 0.3132, "lr": 3.6468322301705504e-05, "epoch": 4.134993446920053, "percentage": 41.35, "elapsed_time": "0:26:42", "remaining_time": "0:37:53", "throughput": 2641.07, "total_tokens": 4232800} {"current_steps": 15780, "total_steps": 38150, "loss": 0.3735, "lr": 3.6458158227937435e-05, "epoch": 4.136304062909567, "percentage": 41.36, "elapsed_time": "0:26:43", "remaining_time": "0:37:52", "throughput": 2641.17, "total_tokens": 4234192} {"current_steps": 15785, "total_steps": 38150, "loss": 0.3134, "lr": 3.6447991755996654e-05, "epoch": 4.137614678899083, "percentage": 41.38, "elapsed_time": "0:26:43", "remaining_time": "0:37:52", "throughput": 2641.16, "total_tokens": 4235296} {"current_steps": 15790, "total_steps": 38150, "loss": 0.4778, "lr": 3.643782288801098e-05, "epoch": 4.1389252948885975, "percentage": 41.39, "elapsed_time": "0:26:44", "remaining_time": "0:37:51", "throughput": 2641.3, "total_tokens": 4236752} {"current_steps": 15795, "total_steps": 38150, "loss": 0.1812, "lr": 3.642765162610873e-05, "epoch": 4.140235910878113, "percentage": 41.4, "elapsed_time": "0:26:44", "remaining_time": "0:37:50", "throughput": 2641.27, "total_tokens": 4237856} {"current_steps": 15800, "total_steps": 38150, "loss": 0.4212, "lr": 3.6417477972418745e-05, "epoch": 4.141546526867628, "percentage": 41.42, "elapsed_time": "0:26:44", "remaining_time": "0:37:50", "throughput": 2641.38, "total_tokens": 4239280} {"current_steps": 15805, "total_steps": 38150, "loss": 0.4128, "lr": 3.640730192907035e-05, "epoch": 4.142857142857143, "percentage": 41.43, "elapsed_time": "0:26:45", "remaining_time": "0:37:49", "throughput": 2641.59, "total_tokens": 4240912} {"current_steps": 15810, "total_steps": 38150, "loss": 0.1849, "lr": 3.639712349819337e-05, "epoch": 4.144167758846658, "percentage": 41.44, "elapsed_time": "0:26:45", "remaining_time": "0:37:49", "throughput": 2641.47, "total_tokens": 4241808} {"current_steps": 15815, "total_steps": 38150, "loss": 0.364, "lr": 3.6386942681918135e-05, "epoch": 4.145478374836173, "percentage": 41.45, "elapsed_time": "0:26:46", "remaining_time": "0:37:48", "throughput": 2641.46, "total_tokens": 4242928} {"current_steps": 15820, "total_steps": 38150, "loss": 0.2223, "lr": 3.637675948237547e-05, "epoch": 4.146788990825688, "percentage": 41.47, "elapsed_time": "0:26:46", "remaining_time": "0:37:47", "throughput": 2641.46, "total_tokens": 4244048} {"current_steps": 15825, "total_steps": 38150, "loss": 0.1887, "lr": 3.6366573901696704e-05, "epoch": 4.148099606815203, "percentage": 41.48, "elapsed_time": "0:26:47", "remaining_time": "0:37:47", "throughput": 2641.41, "total_tokens": 4245104} {"current_steps": 15830, "total_steps": 38150, "loss": 0.385, "lr": 3.635638594201366e-05, "epoch": 4.149410222804718, "percentage": 41.49, "elapsed_time": "0:26:47", "remaining_time": "0:37:46", "throughput": 2641.4, "total_tokens": 4246192} {"current_steps": 15835, "total_steps": 38150, "loss": 0.299, "lr": 3.6346195605458664e-05, "epoch": 4.150720838794233, "percentage": 41.51, "elapsed_time": "0:26:47", "remaining_time": "0:37:45", "throughput": 2641.4, "total_tokens": 4247312} {"current_steps": 15840, "total_steps": 38150, "loss": 0.2227, "lr": 3.633600289416453e-05, "epoch": 4.1520314547837485, "percentage": 41.52, "elapsed_time": "0:26:48", "remaining_time": "0:37:45", "throughput": 2641.37, "total_tokens": 4248368} {"current_steps": 15845, "total_steps": 38150, "loss": 0.3589, "lr": 3.632580781026457e-05, "epoch": 4.153342070773263, "percentage": 41.53, "elapsed_time": "0:26:48", "remaining_time": "0:37:44", "throughput": 2641.56, "total_tokens": 4249872} {"current_steps": 15850, "total_steps": 38150, "loss": 0.3052, "lr": 3.631561035589262e-05, "epoch": 4.154652686762779, "percentage": 41.55, "elapsed_time": "0:26:49", "remaining_time": "0:37:44", "throughput": 2642.03, "total_tokens": 4252336} {"current_steps": 15855, "total_steps": 38150, "loss": 0.2631, "lr": 3.630541053318297e-05, "epoch": 4.155963302752293, "percentage": 41.56, "elapsed_time": "0:26:49", "remaining_time": "0:37:43", "throughput": 2642.22, "total_tokens": 4253920} {"current_steps": 15860, "total_steps": 38150, "loss": 0.4785, "lr": 3.6295208344270415e-05, "epoch": 4.157273918741809, "percentage": 41.57, "elapsed_time": "0:26:50", "remaining_time": "0:37:43", "throughput": 2642.36, "total_tokens": 4255312} {"current_steps": 15865, "total_steps": 38150, "loss": 0.3564, "lr": 3.628500379129028e-05, "epoch": 4.1585845347313235, "percentage": 41.59, "elapsed_time": "0:26:50", "remaining_time": "0:37:42", "throughput": 2642.35, "total_tokens": 4256400} {"current_steps": 15870, "total_steps": 38150, "loss": 0.2719, "lr": 3.627479687637836e-05, "epoch": 4.159895150720839, "percentage": 41.6, "elapsed_time": "0:26:51", "remaining_time": "0:37:42", "throughput": 2642.88, "total_tokens": 4258896} {"current_steps": 15875, "total_steps": 38150, "loss": 0.3799, "lr": 3.6264587601670924e-05, "epoch": 4.161205766710354, "percentage": 41.61, "elapsed_time": "0:26:51", "remaining_time": "0:37:41", "throughput": 2642.96, "total_tokens": 4260192} {"current_steps": 15880, "total_steps": 38150, "loss": 0.3969, "lr": 3.625437596930476e-05, "epoch": 4.162516382699869, "percentage": 41.63, "elapsed_time": "0:26:52", "remaining_time": "0:37:41", "throughput": 2642.96, "total_tokens": 4261280} {"current_steps": 15885, "total_steps": 38150, "loss": 0.2885, "lr": 3.6244161981417165e-05, "epoch": 4.163826998689384, "percentage": 41.64, "elapsed_time": "0:26:52", "remaining_time": "0:37:40", "throughput": 2642.85, "total_tokens": 4262192} {"current_steps": 15890, "total_steps": 38150, "loss": 0.3233, "lr": 3.62339456401459e-05, "epoch": 4.165137614678899, "percentage": 41.65, "elapsed_time": "0:26:53", "remaining_time": "0:37:39", "throughput": 2642.9, "total_tokens": 4263392} {"current_steps": 15895, "total_steps": 38150, "loss": 0.5739, "lr": 3.622372694762921e-05, "epoch": 4.166448230668414, "percentage": 41.66, "elapsed_time": "0:26:53", "remaining_time": "0:37:39", "throughput": 2643.02, "total_tokens": 4264896} {"current_steps": 15900, "total_steps": 38150, "loss": 0.3867, "lr": 3.621350590600587e-05, "epoch": 4.16775884665793, "percentage": 41.68, "elapsed_time": "0:26:54", "remaining_time": "0:37:38", "throughput": 2643.0, "total_tokens": 4265984} {"current_steps": 15905, "total_steps": 38150, "loss": 0.3354, "lr": 3.6203282517415114e-05, "epoch": 4.169069462647444, "percentage": 41.69, "elapsed_time": "0:26:54", "remaining_time": "0:37:38", "throughput": 2642.87, "total_tokens": 4266864} {"current_steps": 15910, "total_steps": 38150, "loss": 0.3656, "lr": 3.619305678399669e-05, "epoch": 4.17038007863696, "percentage": 41.7, "elapsed_time": "0:26:54", "remaining_time": "0:37:37", "throughput": 2642.97, "total_tokens": 4268208} {"current_steps": 15915, "total_steps": 38150, "loss": 0.4248, "lr": 3.6182828707890816e-05, "epoch": 4.1716906946264745, "percentage": 41.72, "elapsed_time": "0:26:55", "remaining_time": "0:37:36", "throughput": 2643.01, "total_tokens": 4269392} {"current_steps": 15920, "total_steps": 38150, "loss": 0.475, "lr": 3.617259829123822e-05, "epoch": 4.173001310615989, "percentage": 41.73, "elapsed_time": "0:26:55", "remaining_time": "0:37:36", "throughput": 2643.09, "total_tokens": 4270800} {"current_steps": 15925, "total_steps": 38150, "loss": 0.4286, "lr": 3.6162365536180105e-05, "epoch": 4.174311926605505, "percentage": 41.74, "elapsed_time": "0:26:56", "remaining_time": "0:37:35", "throughput": 2643.04, "total_tokens": 4271840} {"current_steps": 15930, "total_steps": 38150, "loss": 0.284, "lr": 3.615213044485817e-05, "epoch": 4.175622542595019, "percentage": 41.76, "elapsed_time": "0:26:56", "remaining_time": "0:37:35", "throughput": 2643.06, "total_tokens": 4273056} {"current_steps": 15935, "total_steps": 38150, "loss": 0.2853, "lr": 3.6141893019414606e-05, "epoch": 4.176933158584535, "percentage": 41.77, "elapsed_time": "0:26:57", "remaining_time": "0:37:34", "throughput": 2643.02, "total_tokens": 4274112} {"current_steps": 15940, "total_steps": 38150, "loss": 0.4569, "lr": 3.6131653261992085e-05, "epoch": 4.1782437745740495, "percentage": 41.78, "elapsed_time": "0:26:57", "remaining_time": "0:37:33", "throughput": 2643.03, "total_tokens": 4275344} {"current_steps": 15945, "total_steps": 38150, "loss": 0.3603, "lr": 3.612141117473377e-05, "epoch": 4.179554390563565, "percentage": 41.8, "elapsed_time": "0:26:58", "remaining_time": "0:37:33", "throughput": 2643.7, "total_tokens": 4278688} {"current_steps": 15950, "total_steps": 38150, "loss": 0.4292, "lr": 3.61111667597833e-05, "epoch": 4.18086500655308, "percentage": 41.81, "elapsed_time": "0:26:58", "remaining_time": "0:37:33", "throughput": 2643.75, "total_tokens": 4279920} {"current_steps": 15955, "total_steps": 38150, "loss": 0.4402, "lr": 3.610092001928484e-05, "epoch": 4.182175622542595, "percentage": 41.82, "elapsed_time": "0:26:59", "remaining_time": "0:37:32", "throughput": 2643.71, "total_tokens": 4280960} {"current_steps": 15960, "total_steps": 38150, "loss": 0.3392, "lr": 3.6090670955383e-05, "epoch": 4.18348623853211, "percentage": 41.83, "elapsed_time": "0:26:59", "remaining_time": "0:37:32", "throughput": 2643.83, "total_tokens": 4282416} {"current_steps": 15965, "total_steps": 38150, "loss": 0.3891, "lr": 3.6080419570222885e-05, "epoch": 4.184796854521625, "percentage": 41.85, "elapsed_time": "0:27:00", "remaining_time": "0:37:31", "throughput": 2643.84, "total_tokens": 4283584} {"current_steps": 15970, "total_steps": 38150, "loss": 0.3512, "lr": 3.60701658659501e-05, "epoch": 4.18610747051114, "percentage": 41.86, "elapsed_time": "0:27:00", "remaining_time": "0:37:30", "throughput": 2643.92, "total_tokens": 4284864} {"current_steps": 15975, "total_steps": 38150, "loss": 0.4118, "lr": 3.605990984471073e-05, "epoch": 4.187418086500656, "percentage": 41.87, "elapsed_time": "0:27:01", "remaining_time": "0:37:30", "throughput": 2644.05, "total_tokens": 4286320} {"current_steps": 15980, "total_steps": 38150, "loss": 0.2068, "lr": 3.6049651508651336e-05, "epoch": 4.18872870249017, "percentage": 41.89, "elapsed_time": "0:27:01", "remaining_time": "0:37:29", "throughput": 2643.92, "total_tokens": 4287200} {"current_steps": 15985, "total_steps": 38150, "loss": 0.3809, "lr": 3.603939085991898e-05, "epoch": 4.190039318479686, "percentage": 41.9, "elapsed_time": "0:27:01", "remaining_time": "0:37:29", "throughput": 2643.94, "total_tokens": 4288368} {"current_steps": 15990, "total_steps": 38150, "loss": 0.292, "lr": 3.6029127900661196e-05, "epoch": 4.1913499344692005, "percentage": 41.91, "elapsed_time": "0:27:02", "remaining_time": "0:37:28", "throughput": 2643.86, "total_tokens": 4289344} {"current_steps": 15995, "total_steps": 38150, "loss": 0.3997, "lr": 3.601886263302599e-05, "epoch": 4.192660550458716, "percentage": 41.93, "elapsed_time": "0:27:02", "remaining_time": "0:37:28", "throughput": 2644.27, "total_tokens": 4291568} {"current_steps": 16000, "total_steps": 38150, "loss": 0.2934, "lr": 3.600859505916187e-05, "epoch": 4.193971166448231, "percentage": 41.94, "elapsed_time": "0:27:03", "remaining_time": "0:37:27", "throughput": 2644.25, "total_tokens": 4292688} {"current_steps": 16005, "total_steps": 38150, "loss": 0.3692, "lr": 3.599832518121784e-05, "epoch": 4.195281782437746, "percentage": 41.95, "elapsed_time": "0:27:03", "remaining_time": "0:37:26", "throughput": 2644.52, "total_tokens": 4294352} {"current_steps": 16010, "total_steps": 38150, "loss": 0.4057, "lr": 3.598805300134334e-05, "epoch": 4.196592398427261, "percentage": 41.97, "elapsed_time": "0:27:04", "remaining_time": "0:37:26", "throughput": 2644.54, "total_tokens": 4295520} {"current_steps": 16015, "total_steps": 38150, "loss": 0.427, "lr": 3.597777852168834e-05, "epoch": 4.1979030144167755, "percentage": 41.98, "elapsed_time": "0:27:04", "remaining_time": "0:37:25", "throughput": 2644.49, "total_tokens": 4296528} {"current_steps": 16020, "total_steps": 38150, "loss": 0.5832, "lr": 3.596750174440326e-05, "epoch": 4.199213630406291, "percentage": 41.99, "elapsed_time": "0:27:05", "remaining_time": "0:37:24", "throughput": 2644.58, "total_tokens": 4297824} {"current_steps": 16025, "total_steps": 38150, "loss": 0.2484, "lr": 3.595722267163901e-05, "epoch": 4.200524246395806, "percentage": 42.01, "elapsed_time": "0:27:05", "remaining_time": "0:37:24", "throughput": 2644.64, "total_tokens": 4299056} {"current_steps": 16030, "total_steps": 38150, "loss": 0.4867, "lr": 3.5946941305547e-05, "epoch": 4.201834862385321, "percentage": 42.02, "elapsed_time": "0:27:06", "remaining_time": "0:37:23", "throughput": 2644.72, "total_tokens": 4300400} {"current_steps": 16035, "total_steps": 38150, "loss": 0.4079, "lr": 3.593665764827908e-05, "epoch": 4.203145478374836, "percentage": 42.03, "elapsed_time": "0:27:06", "remaining_time": "0:37:23", "throughput": 2644.72, "total_tokens": 4301552} {"current_steps": 16040, "total_steps": 38150, "loss": 0.3235, "lr": 3.592637170198762e-05, "epoch": 4.204456094364351, "percentage": 42.04, "elapsed_time": "0:27:06", "remaining_time": "0:37:22", "throughput": 2644.76, "total_tokens": 4302736} {"current_steps": 16045, "total_steps": 38150, "loss": 0.5273, "lr": 3.591608346882543e-05, "epoch": 4.205766710353866, "percentage": 42.06, "elapsed_time": "0:27:07", "remaining_time": "0:37:21", "throughput": 2644.82, "total_tokens": 4304048} {"current_steps": 16050, "total_steps": 38150, "loss": 0.5366, "lr": 3.590579295094584e-05, "epoch": 4.207077326343382, "percentage": 42.07, "elapsed_time": "0:27:07", "remaining_time": "0:37:21", "throughput": 2645.12, "total_tokens": 4305968} {"current_steps": 16055, "total_steps": 38150, "loss": 0.5183, "lr": 3.589550015050263e-05, "epoch": 4.208387942332896, "percentage": 42.08, "elapsed_time": "0:27:08", "remaining_time": "0:37:20", "throughput": 2645.18, "total_tokens": 4307216} {"current_steps": 16060, "total_steps": 38150, "loss": 0.2713, "lr": 3.5885205069650056e-05, "epoch": 4.209698558322412, "percentage": 42.1, "elapsed_time": "0:27:08", "remaining_time": "0:37:20", "throughput": 2645.18, "total_tokens": 4308336} {"current_steps": 16065, "total_steps": 38150, "loss": 0.3436, "lr": 3.587490771054288e-05, "epoch": 4.2110091743119265, "percentage": 42.11, "elapsed_time": "0:27:09", "remaining_time": "0:37:19", "throughput": 2645.33, "total_tokens": 4310016} {"current_steps": 16070, "total_steps": 38150, "loss": 0.8102, "lr": 3.586460807533631e-05, "epoch": 4.212319790301442, "percentage": 42.12, "elapsed_time": "0:27:09", "remaining_time": "0:37:19", "throughput": 2645.35, "total_tokens": 4311136} {"current_steps": 16075, "total_steps": 38150, "loss": 0.3118, "lr": 3.585430616618604e-05, "epoch": 4.213630406290957, "percentage": 42.14, "elapsed_time": "0:27:10", "remaining_time": "0:37:18", "throughput": 2645.41, "total_tokens": 4312384} {"current_steps": 16080, "total_steps": 38150, "loss": 0.3032, "lr": 3.584400198524824e-05, "epoch": 4.214941022280472, "percentage": 42.15, "elapsed_time": "0:27:10", "remaining_time": "0:37:18", "throughput": 2645.76, "total_tokens": 4314544} {"current_steps": 16085, "total_steps": 38150, "loss": 0.294, "lr": 3.583369553467956e-05, "epoch": 4.216251638269987, "percentage": 42.16, "elapsed_time": "0:27:11", "remaining_time": "0:37:17", "throughput": 2645.95, "total_tokens": 4316176} {"current_steps": 16090, "total_steps": 38150, "loss": 0.2531, "lr": 3.582338681663713e-05, "epoch": 4.217562254259502, "percentage": 42.18, "elapsed_time": "0:27:11", "remaining_time": "0:37:17", "throughput": 2645.95, "total_tokens": 4317312} {"current_steps": 16095, "total_steps": 38150, "loss": 0.5061, "lr": 3.581307583327854e-05, "epoch": 4.218872870249017, "percentage": 42.19, "elapsed_time": "0:27:12", "remaining_time": "0:37:16", "throughput": 2646.07, "total_tokens": 4318768} {"current_steps": 16100, "total_steps": 38150, "loss": 0.4635, "lr": 3.580276258676186e-05, "epoch": 4.220183486238533, "percentage": 42.2, "elapsed_time": "0:27:12", "remaining_time": "0:37:15", "throughput": 2646.11, "total_tokens": 4319968} {"current_steps": 16105, "total_steps": 38150, "loss": 0.4661, "lr": 3.579244707924564e-05, "epoch": 4.221494102228047, "percentage": 42.21, "elapsed_time": "0:27:12", "remaining_time": "0:37:15", "throughput": 2646.1, "total_tokens": 4321072} {"current_steps": 16110, "total_steps": 38150, "loss": 0.2692, "lr": 3.5782129312888885e-05, "epoch": 4.222804718217562, "percentage": 42.23, "elapsed_time": "0:27:13", "remaining_time": "0:37:14", "throughput": 2646.09, "total_tokens": 4322192} {"current_steps": 16115, "total_steps": 38150, "loss": 0.4254, "lr": 3.5771809289851097e-05, "epoch": 4.224115334207077, "percentage": 42.24, "elapsed_time": "0:27:13", "remaining_time": "0:37:14", "throughput": 2646.13, "total_tokens": 4323376} {"current_steps": 16120, "total_steps": 38150, "loss": 0.3859, "lr": 3.576148701229224e-05, "epoch": 4.225425950196592, "percentage": 42.25, "elapsed_time": "0:27:14", "remaining_time": "0:37:13", "throughput": 2646.17, "total_tokens": 4324656} {"current_steps": 16125, "total_steps": 38150, "loss": 0.3459, "lr": 3.575116248237275e-05, "epoch": 4.226736566186108, "percentage": 42.27, "elapsed_time": "0:27:14", "remaining_time": "0:37:12", "throughput": 2646.32, "total_tokens": 4326208} {"current_steps": 16130, "total_steps": 38150, "loss": 0.3416, "lr": 3.574083570225352e-05, "epoch": 4.228047182175622, "percentage": 42.28, "elapsed_time": "0:27:15", "remaining_time": "0:37:12", "throughput": 2646.34, "total_tokens": 4327392} {"current_steps": 16135, "total_steps": 38150, "loss": 0.343, "lr": 3.573050667409594e-05, "epoch": 4.229357798165138, "percentage": 42.29, "elapsed_time": "0:27:15", "remaining_time": "0:37:11", "throughput": 2646.56, "total_tokens": 4329024} {"current_steps": 16140, "total_steps": 38150, "loss": 0.3892, "lr": 3.572017540006186e-05, "epoch": 4.2306684141546524, "percentage": 42.31, "elapsed_time": "0:27:16", "remaining_time": "0:37:11", "throughput": 2646.63, "total_tokens": 4330352} {"current_steps": 16145, "total_steps": 38150, "loss": 0.2301, "lr": 3.570984188231359e-05, "epoch": 4.231979030144168, "percentage": 42.32, "elapsed_time": "0:27:16", "remaining_time": "0:37:10", "throughput": 2646.6, "total_tokens": 4331488} {"current_steps": 16150, "total_steps": 38150, "loss": 0.3914, "lr": 3.5699506123013906e-05, "epoch": 4.233289646133683, "percentage": 42.33, "elapsed_time": "0:27:17", "remaining_time": "0:37:10", "throughput": 2646.61, "total_tokens": 4332608} {"current_steps": 16155, "total_steps": 38150, "loss": 0.2776, "lr": 3.568916812432609e-05, "epoch": 4.234600262123198, "percentage": 42.35, "elapsed_time": "0:27:17", "remaining_time": "0:37:09", "throughput": 2646.8, "total_tokens": 4334208} {"current_steps": 16160, "total_steps": 38150, "loss": 0.3225, "lr": 3.5678827888413856e-05, "epoch": 4.235910878112713, "percentage": 42.36, "elapsed_time": "0:27:17", "remaining_time": "0:37:08", "throughput": 2646.84, "total_tokens": 4335424} {"current_steps": 16165, "total_steps": 38150, "loss": 0.3052, "lr": 3.56684854174414e-05, "epoch": 4.237221494102228, "percentage": 42.37, "elapsed_time": "0:27:18", "remaining_time": "0:37:08", "throughput": 2646.82, "total_tokens": 4336512} {"current_steps": 16170, "total_steps": 38150, "loss": 0.1543, "lr": 3.5658140713573365e-05, "epoch": 4.238532110091743, "percentage": 42.39, "elapsed_time": "0:27:18", "remaining_time": "0:37:07", "throughput": 2646.93, "total_tokens": 4337920} {"current_steps": 16175, "total_steps": 38150, "loss": 0.4791, "lr": 3.56477937789749e-05, "epoch": 4.239842726081259, "percentage": 42.4, "elapsed_time": "0:27:19", "remaining_time": "0:37:07", "throughput": 2647.01, "total_tokens": 4339264} {"current_steps": 16180, "total_steps": 38150, "loss": 0.2373, "lr": 3.56374446158116e-05, "epoch": 4.241153342070773, "percentage": 42.41, "elapsed_time": "0:27:19", "remaining_time": "0:37:06", "throughput": 2647.06, "total_tokens": 4340560} {"current_steps": 16185, "total_steps": 38150, "loss": 0.2482, "lr": 3.5627093226249524e-05, "epoch": 4.242463958060289, "percentage": 42.42, "elapsed_time": "0:27:20", "remaining_time": "0:37:05", "throughput": 2647.21, "total_tokens": 4342000} {"current_steps": 16190, "total_steps": 38150, "loss": 0.4551, "lr": 3.5616739612455196e-05, "epoch": 4.243774574049803, "percentage": 42.44, "elapsed_time": "0:27:20", "remaining_time": "0:37:05", "throughput": 2647.43, "total_tokens": 4343568} {"current_steps": 16195, "total_steps": 38150, "loss": 0.3042, "lr": 3.560638377659561e-05, "epoch": 4.245085190039318, "percentage": 42.45, "elapsed_time": "0:27:21", "remaining_time": "0:37:04", "throughput": 2647.65, "total_tokens": 4345136} {"current_steps": 16200, "total_steps": 38150, "loss": 0.2995, "lr": 3.559602572083822e-05, "epoch": 4.246395806028834, "percentage": 42.46, "elapsed_time": "0:27:21", "remaining_time": "0:37:04", "throughput": 2647.64, "total_tokens": 4346240} {"current_steps": 16205, "total_steps": 38150, "loss": 0.3699, "lr": 3.558566544735096e-05, "epoch": 4.247706422018348, "percentage": 42.48, "elapsed_time": "0:27:22", "remaining_time": "0:37:03", "throughput": 2647.81, "total_tokens": 4347728} {"current_steps": 16210, "total_steps": 38150, "loss": 0.4468, "lr": 3.5575302958302214e-05, "epoch": 4.249017038007864, "percentage": 42.49, "elapsed_time": "0:27:22", "remaining_time": "0:37:03", "throughput": 2647.92, "total_tokens": 4349168} {"current_steps": 16215, "total_steps": 38150, "loss": 0.2517, "lr": 3.556493825586083e-05, "epoch": 4.250327653997378, "percentage": 42.5, "elapsed_time": "0:27:22", "remaining_time": "0:37:02", "throughput": 2647.99, "total_tokens": 4350432} {"current_steps": 16220, "total_steps": 38150, "loss": 0.4911, "lr": 3.555457134219613e-05, "epoch": 4.251638269986894, "percentage": 42.52, "elapsed_time": "0:27:23", "remaining_time": "0:37:01", "throughput": 2648.01, "total_tokens": 4351600} {"current_steps": 16225, "total_steps": 38150, "loss": 0.6904, "lr": 3.554420221947788e-05, "epoch": 4.252948885976409, "percentage": 42.53, "elapsed_time": "0:27:23", "remaining_time": "0:37:01", "throughput": 2648.03, "total_tokens": 4352784} {"current_steps": 16230, "total_steps": 38150, "loss": 0.5542, "lr": 3.553383088987632e-05, "epoch": 4.254259501965924, "percentage": 42.54, "elapsed_time": "0:27:24", "remaining_time": "0:37:00", "throughput": 2648.04, "total_tokens": 4353952} {"current_steps": 16235, "total_steps": 38150, "loss": 0.3483, "lr": 3.552345735556216e-05, "epoch": 4.255570117955439, "percentage": 42.56, "elapsed_time": "0:27:24", "remaining_time": "0:37:00", "throughput": 2648.12, "total_tokens": 4355328} {"current_steps": 16240, "total_steps": 38150, "loss": 0.3568, "lr": 3.5513081618706555e-05, "epoch": 4.256880733944954, "percentage": 42.57, "elapsed_time": "0:27:25", "remaining_time": "0:36:59", "throughput": 2648.22, "total_tokens": 4356672} {"current_steps": 16245, "total_steps": 38150, "loss": 0.3782, "lr": 3.550270368148113e-05, "epoch": 4.258191349934469, "percentage": 42.58, "elapsed_time": "0:27:25", "remaining_time": "0:36:58", "throughput": 2648.24, "total_tokens": 4357840} {"current_steps": 16250, "total_steps": 38150, "loss": 0.3746, "lr": 3.549232354605798e-05, "epoch": 4.259501965923985, "percentage": 42.6, "elapsed_time": "0:27:25", "remaining_time": "0:36:58", "throughput": 2648.17, "total_tokens": 4358816} {"current_steps": 16255, "total_steps": 38150, "loss": 0.3762, "lr": 3.548194121460964e-05, "epoch": 4.260812581913499, "percentage": 42.61, "elapsed_time": "0:27:26", "remaining_time": "0:36:57", "throughput": 2648.16, "total_tokens": 4359920} {"current_steps": 16260, "total_steps": 38150, "loss": 0.3764, "lr": 3.547155668930912e-05, "epoch": 4.262123197903015, "percentage": 42.62, "elapsed_time": "0:27:26", "remaining_time": "0:36:57", "throughput": 2648.11, "total_tokens": 4360944} {"current_steps": 16265, "total_steps": 38150, "loss": 0.2993, "lr": 3.546116997232987e-05, "epoch": 4.263433813892529, "percentage": 42.63, "elapsed_time": "0:27:27", "remaining_time": "0:36:56", "throughput": 2648.13, "total_tokens": 4362112} {"current_steps": 16270, "total_steps": 38150, "loss": 0.3334, "lr": 3.545078106584582e-05, "epoch": 4.264744429882045, "percentage": 42.65, "elapsed_time": "0:27:27", "remaining_time": "0:36:55", "throughput": 2648.15, "total_tokens": 4363232} {"current_steps": 16275, "total_steps": 38150, "loss": 0.2426, "lr": 3.544038997203135e-05, "epoch": 4.26605504587156, "percentage": 42.66, "elapsed_time": "0:27:28", "remaining_time": "0:36:55", "throughput": 2648.32, "total_tokens": 4364800} {"current_steps": 16280, "total_steps": 38150, "loss": 0.4962, "lr": 3.5429996693061304e-05, "epoch": 4.267365661861074, "percentage": 42.67, "elapsed_time": "0:27:28", "remaining_time": "0:36:54", "throughput": 2648.4, "total_tokens": 4366096} {"current_steps": 16285, "total_steps": 38150, "loss": 0.2441, "lr": 3.541960123111097e-05, "epoch": 4.26867627785059, "percentage": 42.69, "elapsed_time": "0:27:29", "remaining_time": "0:36:54", "throughput": 2648.63, "total_tokens": 4367744} {"current_steps": 16290, "total_steps": 38150, "loss": 0.3248, "lr": 3.54092035883561e-05, "epoch": 4.269986893840104, "percentage": 42.7, "elapsed_time": "0:27:29", "remaining_time": "0:36:53", "throughput": 2648.68, "total_tokens": 4369040} {"current_steps": 16295, "total_steps": 38150, "loss": 0.5063, "lr": 3.53988037669729e-05, "epoch": 4.27129750982962, "percentage": 42.71, "elapsed_time": "0:27:30", "remaining_time": "0:36:53", "throughput": 2648.93, "total_tokens": 4370784} {"current_steps": 16300, "total_steps": 38150, "loss": 0.2924, "lr": 3.5388401769138053e-05, "epoch": 4.272608125819135, "percentage": 42.73, "elapsed_time": "0:27:30", "remaining_time": "0:36:52", "throughput": 2649.24, "total_tokens": 4372880} {"current_steps": 16305, "total_steps": 38150, "loss": 0.2585, "lr": 3.5377997597028656e-05, "epoch": 4.27391874180865, "percentage": 42.74, "elapsed_time": "0:27:31", "remaining_time": "0:36:52", "throughput": 2649.15, "total_tokens": 4373840} {"current_steps": 16310, "total_steps": 38150, "loss": 0.3419, "lr": 3.53675912528223e-05, "epoch": 4.275229357798165, "percentage": 42.75, "elapsed_time": "0:27:31", "remaining_time": "0:36:51", "throughput": 2649.38, "total_tokens": 4375536} {"current_steps": 16315, "total_steps": 38150, "loss": 0.2677, "lr": 3.535718273869699e-05, "epoch": 4.27653997378768, "percentage": 42.77, "elapsed_time": "0:27:31", "remaining_time": "0:36:50", "throughput": 2649.27, "total_tokens": 4376464} {"current_steps": 16320, "total_steps": 38150, "loss": 0.3415, "lr": 3.534677205683125e-05, "epoch": 4.277850589777195, "percentage": 42.78, "elapsed_time": "0:27:32", "remaining_time": "0:36:50", "throughput": 2649.32, "total_tokens": 4377776} {"current_steps": 16325, "total_steps": 38150, "loss": 0.4136, "lr": 3.533635920940399e-05, "epoch": 4.2791612057667106, "percentage": 42.79, "elapsed_time": "0:27:32", "remaining_time": "0:36:49", "throughput": 2649.43, "total_tokens": 4379120} {"current_steps": 16330, "total_steps": 38150, "loss": 0.3219, "lr": 3.5325944198594607e-05, "epoch": 4.280471821756225, "percentage": 42.8, "elapsed_time": "0:27:33", "remaining_time": "0:36:49", "throughput": 2649.48, "total_tokens": 4380352} {"current_steps": 16335, "total_steps": 38150, "loss": 0.2588, "lr": 3.531552702658294e-05, "epoch": 4.281782437745741, "percentage": 42.82, "elapsed_time": "0:27:33", "remaining_time": "0:36:48", "throughput": 2649.49, "total_tokens": 4381488} {"current_steps": 16340, "total_steps": 38150, "loss": 0.3056, "lr": 3.53051076955493e-05, "epoch": 4.283093053735255, "percentage": 42.83, "elapsed_time": "0:27:34", "remaining_time": "0:36:47", "throughput": 2649.51, "total_tokens": 4382672} {"current_steps": 16345, "total_steps": 38150, "loss": 0.4884, "lr": 3.5294686207674414e-05, "epoch": 4.284403669724771, "percentage": 42.84, "elapsed_time": "0:27:34", "remaining_time": "0:36:47", "throughput": 2649.58, "total_tokens": 4384000} {"current_steps": 16350, "total_steps": 38150, "loss": 0.3466, "lr": 3.5284262565139494e-05, "epoch": 4.285714285714286, "percentage": 42.86, "elapsed_time": "0:27:35", "remaining_time": "0:36:46", "throughput": 2649.61, "total_tokens": 4385168} {"current_steps": 16355, "total_steps": 38150, "loss": 0.3894, "lr": 3.5273836770126204e-05, "epoch": 4.287024901703801, "percentage": 42.87, "elapsed_time": "0:27:35", "remaining_time": "0:36:46", "throughput": 2649.68, "total_tokens": 4386400} {"current_steps": 16360, "total_steps": 38150, "loss": 0.3421, "lr": 3.5263408824816615e-05, "epoch": 4.288335517693316, "percentage": 42.88, "elapsed_time": "0:27:35", "remaining_time": "0:36:45", "throughput": 2649.78, "total_tokens": 4387840} {"current_steps": 16365, "total_steps": 38150, "loss": 0.4295, "lr": 3.52529787313933e-05, "epoch": 4.289646133682831, "percentage": 42.9, "elapsed_time": "0:27:36", "remaining_time": "0:36:45", "throughput": 2649.95, "total_tokens": 4389440} {"current_steps": 16370, "total_steps": 38150, "loss": 0.2494, "lr": 3.524254649203925e-05, "epoch": 4.290956749672346, "percentage": 42.91, "elapsed_time": "0:27:36", "remaining_time": "0:36:44", "throughput": 2650.03, "total_tokens": 4390848} {"current_steps": 16375, "total_steps": 38150, "loss": 0.3937, "lr": 3.5232112108937914e-05, "epoch": 4.292267365661861, "percentage": 42.92, "elapsed_time": "0:27:37", "remaining_time": "0:36:43", "throughput": 2650.15, "total_tokens": 4392208} {"current_steps": 16380, "total_steps": 38150, "loss": 0.5803, "lr": 3.52216755842732e-05, "epoch": 4.293577981651376, "percentage": 42.94, "elapsed_time": "0:27:37", "remaining_time": "0:36:43", "throughput": 2650.39, "total_tokens": 4393968} {"current_steps": 16385, "total_steps": 38150, "loss": 0.4407, "lr": 3.521123692022944e-05, "epoch": 4.294888597640891, "percentage": 42.95, "elapsed_time": "0:27:38", "remaining_time": "0:36:42", "throughput": 2650.31, "total_tokens": 4394944} {"current_steps": 16390, "total_steps": 38150, "loss": 0.328, "lr": 3.520079611899144e-05, "epoch": 4.296199213630406, "percentage": 42.96, "elapsed_time": "0:27:38", "remaining_time": "0:36:42", "throughput": 2650.32, "total_tokens": 4396112} {"current_steps": 16395, "total_steps": 38150, "loss": 0.3313, "lr": 3.519035318274444e-05, "epoch": 4.297509829619921, "percentage": 42.98, "elapsed_time": "0:27:39", "remaining_time": "0:36:41", "throughput": 2650.39, "total_tokens": 4397376} {"current_steps": 16400, "total_steps": 38150, "loss": 0.4583, "lr": 3.517990811367412e-05, "epoch": 4.2988204456094365, "percentage": 42.99, "elapsed_time": "0:27:39", "remaining_time": "0:36:40", "throughput": 2650.45, "total_tokens": 4398624} {"current_steps": 16405, "total_steps": 38150, "loss": 0.4124, "lr": 3.516946091396662e-05, "epoch": 4.300131061598951, "percentage": 43.0, "elapsed_time": "0:27:40", "remaining_time": "0:36:40", "throughput": 2650.44, "total_tokens": 4399744} {"current_steps": 16410, "total_steps": 38150, "loss": 0.5516, "lr": 3.5159011585808525e-05, "epoch": 4.301441677588467, "percentage": 43.01, "elapsed_time": "0:27:40", "remaining_time": "0:36:39", "throughput": 2650.37, "total_tokens": 4400720} {"current_steps": 16415, "total_steps": 38150, "loss": 0.4549, "lr": 3.5148560131386867e-05, "epoch": 4.302752293577981, "percentage": 43.03, "elapsed_time": "0:27:40", "remaining_time": "0:36:39", "throughput": 2650.58, "total_tokens": 4402464} {"current_steps": 16420, "total_steps": 38150, "loss": 0.3271, "lr": 3.5138106552889106e-05, "epoch": 4.304062909567497, "percentage": 43.04, "elapsed_time": "0:27:41", "remaining_time": "0:36:38", "throughput": 2650.77, "total_tokens": 4403968} {"current_steps": 16425, "total_steps": 38150, "loss": 0.233, "lr": 3.5127650852503156e-05, "epoch": 4.305373525557012, "percentage": 43.05, "elapsed_time": "0:27:41", "remaining_time": "0:36:38", "throughput": 2650.83, "total_tokens": 4405200} {"current_steps": 16430, "total_steps": 38150, "loss": 0.2064, "lr": 3.511719303241738e-05, "epoch": 4.306684141546527, "percentage": 43.07, "elapsed_time": "0:27:42", "remaining_time": "0:36:37", "throughput": 2650.89, "total_tokens": 4406432} {"current_steps": 16435, "total_steps": 38150, "loss": 0.4822, "lr": 3.5106733094820586e-05, "epoch": 4.307994757536042, "percentage": 43.08, "elapsed_time": "0:27:42", "remaining_time": "0:36:36", "throughput": 2650.93, "total_tokens": 4407648} {"current_steps": 16440, "total_steps": 38150, "loss": 0.3385, "lr": 3.509627104190202e-05, "epoch": 4.309305373525557, "percentage": 43.09, "elapsed_time": "0:27:43", "remaining_time": "0:36:36", "throughput": 2650.92, "total_tokens": 4408736} {"current_steps": 16445, "total_steps": 38150, "loss": 0.3794, "lr": 3.5085806875851365e-05, "epoch": 4.310615989515072, "percentage": 43.11, "elapsed_time": "0:27:43", "remaining_time": "0:36:35", "throughput": 2650.97, "total_tokens": 4409984} {"current_steps": 16450, "total_steps": 38150, "loss": 0.3326, "lr": 3.507534059885876e-05, "epoch": 4.3119266055045875, "percentage": 43.12, "elapsed_time": "0:27:43", "remaining_time": "0:36:34", "throughput": 2650.9, "total_tokens": 4410960} {"current_steps": 16455, "total_steps": 38150, "loss": 0.413, "lr": 3.5064872213114784e-05, "epoch": 4.313237221494102, "percentage": 43.13, "elapsed_time": "0:27:44", "remaining_time": "0:36:34", "throughput": 2650.85, "total_tokens": 4412016} {"current_steps": 16460, "total_steps": 38150, "loss": 0.3325, "lr": 3.505440172081044e-05, "epoch": 4.314547837483618, "percentage": 43.15, "elapsed_time": "0:27:44", "remaining_time": "0:36:33", "throughput": 2651.08, "total_tokens": 4413776} {"current_steps": 16465, "total_steps": 38150, "loss": 0.2539, "lr": 3.504392912413719e-05, "epoch": 4.315858453473132, "percentage": 43.16, "elapsed_time": "0:27:45", "remaining_time": "0:36:33", "throughput": 2650.99, "total_tokens": 4414720} {"current_steps": 16470, "total_steps": 38150, "loss": 0.341, "lr": 3.503345442528692e-05, "epoch": 4.317169069462647, "percentage": 43.17, "elapsed_time": "0:27:45", "remaining_time": "0:36:32", "throughput": 2650.97, "total_tokens": 4415824} {"current_steps": 16475, "total_steps": 38150, "loss": 0.2146, "lr": 3.5022977626451985e-05, "epoch": 4.3184796854521625, "percentage": 43.18, "elapsed_time": "0:27:46", "remaining_time": "0:36:32", "throughput": 2650.91, "total_tokens": 4416832} {"current_steps": 16480, "total_steps": 38150, "loss": 0.4066, "lr": 3.501249872982515e-05, "epoch": 4.319790301441677, "percentage": 43.2, "elapsed_time": "0:27:46", "remaining_time": "0:36:31", "throughput": 2651.01, "total_tokens": 4418176} {"current_steps": 16485, "total_steps": 38150, "loss": 0.382, "lr": 3.500201773759963e-05, "epoch": 4.321100917431193, "percentage": 43.21, "elapsed_time": "0:27:47", "remaining_time": "0:36:30", "throughput": 2651.11, "total_tokens": 4419504} {"current_steps": 16490, "total_steps": 38150, "loss": 0.6246, "lr": 3.499153465196907e-05, "epoch": 4.322411533420707, "percentage": 43.22, "elapsed_time": "0:27:47", "remaining_time": "0:36:30", "throughput": 2651.19, "total_tokens": 4420784} {"current_steps": 16495, "total_steps": 38150, "loss": 0.4408, "lr": 3.4981049475127584e-05, "epoch": 4.323722149410223, "percentage": 43.24, "elapsed_time": "0:27:47", "remaining_time": "0:36:29", "throughput": 2651.21, "total_tokens": 4421968} {"current_steps": 16500, "total_steps": 38150, "loss": 0.2405, "lr": 3.4970562209269684e-05, "epoch": 4.325032765399738, "percentage": 43.25, "elapsed_time": "0:27:48", "remaining_time": "0:36:29", "throughput": 2651.16, "total_tokens": 4423088} {"current_steps": 16505, "total_steps": 38150, "loss": 0.5313, "lr": 3.496007285659034e-05, "epoch": 4.326343381389253, "percentage": 43.26, "elapsed_time": "0:27:48", "remaining_time": "0:36:28", "throughput": 2651.32, "total_tokens": 4424672} {"current_steps": 16510, "total_steps": 38150, "loss": 0.2374, "lr": 3.494958141928496e-05, "epoch": 4.327653997378768, "percentage": 43.28, "elapsed_time": "0:27:49", "remaining_time": "0:36:27", "throughput": 2651.23, "total_tokens": 4425632} {"current_steps": 16515, "total_steps": 38150, "loss": 0.3351, "lr": 3.4939087899549386e-05, "epoch": 4.328964613368283, "percentage": 43.29, "elapsed_time": "0:27:49", "remaining_time": "0:36:27", "throughput": 2651.29, "total_tokens": 4426960} {"current_steps": 16520, "total_steps": 38150, "loss": 0.3295, "lr": 3.4928592299579874e-05, "epoch": 4.330275229357798, "percentage": 43.3, "elapsed_time": "0:27:50", "remaining_time": "0:36:26", "throughput": 2651.57, "total_tokens": 4428816} {"current_steps": 16525, "total_steps": 38150, "loss": 0.3757, "lr": 3.4918094621573164e-05, "epoch": 4.3315858453473135, "percentage": 43.32, "elapsed_time": "0:27:50", "remaining_time": "0:36:26", "throughput": 2651.54, "total_tokens": 4429888} {"current_steps": 16530, "total_steps": 38150, "loss": 0.3723, "lr": 3.490759486772637e-05, "epoch": 4.332896461336828, "percentage": 43.33, "elapsed_time": "0:27:51", "remaining_time": "0:36:25", "throughput": 2651.67, "total_tokens": 4431424} {"current_steps": 16535, "total_steps": 38150, "loss": 0.2813, "lr": 3.48970930402371e-05, "epoch": 4.334207077326344, "percentage": 43.34, "elapsed_time": "0:27:51", "remaining_time": "0:36:25", "throughput": 2651.8, "total_tokens": 4432880} {"current_steps": 16540, "total_steps": 38150, "loss": 0.2878, "lr": 3.488658914130336e-05, "epoch": 4.335517693315858, "percentage": 43.36, "elapsed_time": "0:27:52", "remaining_time": "0:36:24", "throughput": 2651.76, "total_tokens": 4433920} {"current_steps": 16545, "total_steps": 38150, "loss": 0.3528, "lr": 3.487608317312358e-05, "epoch": 4.336828309305374, "percentage": 43.37, "elapsed_time": "0:27:52", "remaining_time": "0:36:24", "throughput": 2651.79, "total_tokens": 4435104} {"current_steps": 16550, "total_steps": 38150, "loss": 0.3744, "lr": 3.486557513789668e-05, "epoch": 4.3381389252948885, "percentage": 43.38, "elapsed_time": "0:27:52", "remaining_time": "0:36:23", "throughput": 2651.87, "total_tokens": 4436416} {"current_steps": 16555, "total_steps": 38150, "loss": 0.3684, "lr": 3.485506503782194e-05, "epoch": 4.339449541284404, "percentage": 43.39, "elapsed_time": "0:27:53", "remaining_time": "0:36:22", "throughput": 2651.9, "total_tokens": 4437600} {"current_steps": 16560, "total_steps": 38150, "loss": 0.3311, "lr": 3.484455287509911e-05, "epoch": 4.340760157273919, "percentage": 43.41, "elapsed_time": "0:27:53", "remaining_time": "0:36:22", "throughput": 2651.97, "total_tokens": 4438928} {"current_steps": 16565, "total_steps": 38150, "loss": 0.4488, "lr": 3.483403865192838e-05, "epoch": 4.342070773263433, "percentage": 43.42, "elapsed_time": "0:27:54", "remaining_time": "0:36:21", "throughput": 2652.11, "total_tokens": 4440400} {"current_steps": 16570, "total_steps": 38150, "loss": 0.4396, "lr": 3.482352237051035e-05, "epoch": 4.343381389252949, "percentage": 43.43, "elapsed_time": "0:27:54", "remaining_time": "0:36:21", "throughput": 2652.16, "total_tokens": 4441728} {"current_steps": 16575, "total_steps": 38150, "loss": 0.3744, "lr": 3.481300403304606e-05, "epoch": 4.344692005242464, "percentage": 43.45, "elapsed_time": "0:27:55", "remaining_time": "0:36:20", "throughput": 2652.12, "total_tokens": 4442768} {"current_steps": 16580, "total_steps": 38150, "loss": 0.3073, "lr": 3.480248364173698e-05, "epoch": 4.346002621231979, "percentage": 43.46, "elapsed_time": "0:27:55", "remaining_time": "0:36:19", "throughput": 2652.36, "total_tokens": 4444448} {"current_steps": 16585, "total_steps": 38150, "loss": 0.261, "lr": 3.4791961198785014e-05, "epoch": 4.347313237221494, "percentage": 43.47, "elapsed_time": "0:27:56", "remaining_time": "0:36:19", "throughput": 2652.37, "total_tokens": 4445568} {"current_steps": 16590, "total_steps": 38150, "loss": 0.3954, "lr": 3.478143670639248e-05, "epoch": 4.348623853211009, "percentage": 43.49, "elapsed_time": "0:27:56", "remaining_time": "0:36:18", "throughput": 2652.46, "total_tokens": 4446896} {"current_steps": 16595, "total_steps": 38150, "loss": 0.3284, "lr": 3.477091016676216e-05, "epoch": 4.349934469200524, "percentage": 43.5, "elapsed_time": "0:27:56", "remaining_time": "0:36:18", "throughput": 2652.53, "total_tokens": 4448192} {"current_steps": 16600, "total_steps": 38150, "loss": 0.3918, "lr": 3.476038158209722e-05, "epoch": 4.3512450851900395, "percentage": 43.51, "elapsed_time": "0:27:57", "remaining_time": "0:36:17", "throughput": 2652.52, "total_tokens": 4449296} {"current_steps": 16605, "total_steps": 38150, "loss": 0.3135, "lr": 3.4749850954601274e-05, "epoch": 4.352555701179554, "percentage": 43.53, "elapsed_time": "0:27:57", "remaining_time": "0:36:17", "throughput": 2652.74, "total_tokens": 4451136} {"current_steps": 16610, "total_steps": 38150, "loss": 0.2657, "lr": 3.473931828647837e-05, "epoch": 4.35386631716907, "percentage": 43.54, "elapsed_time": "0:27:58", "remaining_time": "0:36:16", "throughput": 2652.8, "total_tokens": 4452480} {"current_steps": 16615, "total_steps": 38150, "loss": 0.3522, "lr": 3.472878357993298e-05, "epoch": 4.355176933158584, "percentage": 43.55, "elapsed_time": "0:27:58", "remaining_time": "0:36:15", "throughput": 2652.76, "total_tokens": 4453536} {"current_steps": 16620, "total_steps": 38150, "loss": 0.5574, "lr": 3.4718246837169996e-05, "epoch": 4.3564875491481, "percentage": 43.56, "elapsed_time": "0:27:59", "remaining_time": "0:36:15", "throughput": 2653.1, "total_tokens": 4455712} {"current_steps": 16625, "total_steps": 38150, "loss": 0.3752, "lr": 3.470770806039474e-05, "epoch": 4.3577981651376145, "percentage": 43.58, "elapsed_time": "0:27:59", "remaining_time": "0:36:15", "throughput": 2653.16, "total_tokens": 4457056} {"current_steps": 16630, "total_steps": 38150, "loss": 0.3317, "lr": 3.469716725181296e-05, "epoch": 4.35910878112713, "percentage": 43.59, "elapsed_time": "0:28:00", "remaining_time": "0:36:14", "throughput": 2653.25, "total_tokens": 4458352} {"current_steps": 16635, "total_steps": 38150, "loss": 0.3502, "lr": 3.468662441363083e-05, "epoch": 4.360419397116645, "percentage": 43.6, "elapsed_time": "0:28:00", "remaining_time": "0:36:13", "throughput": 2653.23, "total_tokens": 4459456} {"current_steps": 16640, "total_steps": 38150, "loss": 0.5103, "lr": 3.467607954805495e-05, "epoch": 4.36173001310616, "percentage": 43.62, "elapsed_time": "0:28:01", "remaining_time": "0:36:13", "throughput": 2653.24, "total_tokens": 4460704} {"current_steps": 16645, "total_steps": 38150, "loss": 0.2875, "lr": 3.466553265729233e-05, "epoch": 4.363040629095675, "percentage": 43.63, "elapsed_time": "0:28:01", "remaining_time": "0:36:12", "throughput": 2653.37, "total_tokens": 4462192} {"current_steps": 16650, "total_steps": 38150, "loss": 0.4002, "lr": 3.465498374355044e-05, "epoch": 4.3643512450851905, "percentage": 43.64, "elapsed_time": "0:28:02", "remaining_time": "0:36:12", "throughput": 2653.39, "total_tokens": 4463328} {"current_steps": 16655, "total_steps": 38150, "loss": 0.2635, "lr": 3.4644432809037134e-05, "epoch": 4.365661861074705, "percentage": 43.66, "elapsed_time": "0:28:02", "remaining_time": "0:36:11", "throughput": 2653.35, "total_tokens": 4464384} {"current_steps": 16660, "total_steps": 38150, "loss": 0.4116, "lr": 3.463387985596069e-05, "epoch": 4.36697247706422, "percentage": 43.67, "elapsed_time": "0:28:02", "remaining_time": "0:36:10", "throughput": 2653.5, "total_tokens": 4465808} {"current_steps": 16665, "total_steps": 38150, "loss": 0.421, "lr": 3.462332488652985e-05, "epoch": 4.368283093053735, "percentage": 43.68, "elapsed_time": "0:28:03", "remaining_time": "0:36:10", "throughput": 2653.59, "total_tokens": 4467200} {"current_steps": 16670, "total_steps": 38150, "loss": 0.3111, "lr": 3.461276790295374e-05, "epoch": 4.36959370904325, "percentage": 43.7, "elapsed_time": "0:28:03", "remaining_time": "0:36:09", "throughput": 2653.7, "total_tokens": 4468608} {"current_steps": 16675, "total_steps": 38150, "loss": 0.2945, "lr": 3.4602208907441915e-05, "epoch": 4.3709043250327655, "percentage": 43.71, "elapsed_time": "0:28:04", "remaining_time": "0:36:09", "throughput": 2653.79, "total_tokens": 4469920} {"current_steps": 16680, "total_steps": 38150, "loss": 0.4997, "lr": 3.4591647902204355e-05, "epoch": 4.37221494102228, "percentage": 43.72, "elapsed_time": "0:28:04", "remaining_time": "0:36:08", "throughput": 2653.72, "total_tokens": 4470896} {"current_steps": 16685, "total_steps": 38150, "loss": 0.4688, "lr": 3.4581084889451466e-05, "epoch": 4.373525557011796, "percentage": 43.74, "elapsed_time": "0:28:05", "remaining_time": "0:36:08", "throughput": 2654.04, "total_tokens": 4472864} {"current_steps": 16690, "total_steps": 38150, "loss": 0.3674, "lr": 3.457051987139406e-05, "epoch": 4.37483617300131, "percentage": 43.75, "elapsed_time": "0:28:05", "remaining_time": "0:36:07", "throughput": 2654.05, "total_tokens": 4474032} {"current_steps": 16695, "total_steps": 38150, "loss": 0.4606, "lr": 3.455995285024338e-05, "epoch": 4.376146788990826, "percentage": 43.76, "elapsed_time": "0:28:06", "remaining_time": "0:36:07", "throughput": 2654.27, "total_tokens": 4475728} {"current_steps": 16700, "total_steps": 38150, "loss": 0.5578, "lr": 3.454938382821109e-05, "epoch": 4.3774574049803405, "percentage": 43.77, "elapsed_time": "0:28:06", "remaining_time": "0:36:06", "throughput": 2654.48, "total_tokens": 4477344} {"current_steps": 16705, "total_steps": 38150, "loss": 0.3505, "lr": 3.453881280750927e-05, "epoch": 4.378768020969856, "percentage": 43.79, "elapsed_time": "0:28:07", "remaining_time": "0:36:05", "throughput": 2654.48, "total_tokens": 4478480} {"current_steps": 16710, "total_steps": 38150, "loss": 0.3172, "lr": 3.452823979035041e-05, "epoch": 4.380078636959371, "percentage": 43.8, "elapsed_time": "0:28:07", "remaining_time": "0:36:05", "throughput": 2654.46, "total_tokens": 4479552} {"current_steps": 16715, "total_steps": 38150, "loss": 0.4082, "lr": 3.451766477894742e-05, "epoch": 4.381389252948886, "percentage": 43.81, "elapsed_time": "0:28:07", "remaining_time": "0:36:04", "throughput": 2654.48, "total_tokens": 4480704} {"current_steps": 16720, "total_steps": 38150, "loss": 0.4096, "lr": 3.450708777551364e-05, "epoch": 4.382699868938401, "percentage": 43.83, "elapsed_time": "0:28:08", "remaining_time": "0:36:04", "throughput": 2654.61, "total_tokens": 4482176} {"current_steps": 16725, "total_steps": 38150, "loss": 0.3224, "lr": 3.4496508782262804e-05, "epoch": 4.3840104849279165, "percentage": 43.84, "elapsed_time": "0:28:08", "remaining_time": "0:36:03", "throughput": 2654.65, "total_tokens": 4483376} {"current_steps": 16730, "total_steps": 38150, "loss": 0.3459, "lr": 3.4485927801409105e-05, "epoch": 4.385321100917431, "percentage": 43.85, "elapsed_time": "0:28:09", "remaining_time": "0:36:02", "throughput": 2654.68, "total_tokens": 4484656} {"current_steps": 16735, "total_steps": 38150, "loss": 0.3204, "lr": 3.44753448351671e-05, "epoch": 4.386631716906947, "percentage": 43.87, "elapsed_time": "0:28:09", "remaining_time": "0:36:02", "throughput": 2654.76, "total_tokens": 4485968} {"current_steps": 16740, "total_steps": 38150, "loss": 0.3591, "lr": 3.4464759885751796e-05, "epoch": 4.387942332896461, "percentage": 43.88, "elapsed_time": "0:28:10", "remaining_time": "0:36:01", "throughput": 2655.06, "total_tokens": 4487888} {"current_steps": 16745, "total_steps": 38150, "loss": 0.3396, "lr": 3.4454172955378595e-05, "epoch": 4.389252948885977, "percentage": 43.89, "elapsed_time": "0:28:10", "remaining_time": "0:36:01", "throughput": 2655.02, "total_tokens": 4488944} {"current_steps": 16750, "total_steps": 38150, "loss": 0.3313, "lr": 3.444358404626335e-05, "epoch": 4.3905635648754915, "percentage": 43.91, "elapsed_time": "0:28:11", "remaining_time": "0:36:00", "throughput": 2655.15, "total_tokens": 4490336} {"current_steps": 16755, "total_steps": 38150, "loss": 0.2999, "lr": 3.4432993160622256e-05, "epoch": 4.391874180865006, "percentage": 43.92, "elapsed_time": "0:28:11", "remaining_time": "0:36:00", "throughput": 2655.13, "total_tokens": 4491504} {"current_steps": 16760, "total_steps": 38150, "loss": 0.4308, "lr": 3.4422400300672e-05, "epoch": 4.393184796854522, "percentage": 43.93, "elapsed_time": "0:28:12", "remaining_time": "0:35:59", "throughput": 2655.27, "total_tokens": 4492976} {"current_steps": 16765, "total_steps": 38150, "loss": 0.4989, "lr": 3.441180546862965e-05, "epoch": 4.394495412844036, "percentage": 43.94, "elapsed_time": "0:28:12", "remaining_time": "0:35:58", "throughput": 2655.2, "total_tokens": 4493968} {"current_steps": 16770, "total_steps": 38150, "loss": 0.5287, "lr": 3.440120866671268e-05, "epoch": 4.395806028833552, "percentage": 43.96, "elapsed_time": "0:28:12", "remaining_time": "0:35:58", "throughput": 2655.24, "total_tokens": 4495168} {"current_steps": 16775, "total_steps": 38150, "loss": 0.3499, "lr": 3.4390609897138965e-05, "epoch": 4.3971166448230665, "percentage": 43.97, "elapsed_time": "0:28:13", "remaining_time": "0:35:57", "throughput": 2655.22, "total_tokens": 4496256} {"current_steps": 16780, "total_steps": 38150, "loss": 0.2674, "lr": 3.438000916212683e-05, "epoch": 4.398427260812582, "percentage": 43.98, "elapsed_time": "0:28:13", "remaining_time": "0:35:57", "throughput": 2655.12, "total_tokens": 4497216} {"current_steps": 16785, "total_steps": 38150, "loss": 0.2457, "lr": 3.436940646389499e-05, "epoch": 4.399737876802097, "percentage": 44.0, "elapsed_time": "0:28:14", "remaining_time": "0:35:56", "throughput": 2655.17, "total_tokens": 4498448} {"current_steps": 16790, "total_steps": 38150, "loss": 0.3353, "lr": 3.435880180466257e-05, "epoch": 4.401048492791612, "percentage": 44.01, "elapsed_time": "0:28:14", "remaining_time": "0:35:55", "throughput": 2655.26, "total_tokens": 4499776} {"current_steps": 16795, "total_steps": 38150, "loss": 0.3804, "lr": 3.434819518664909e-05, "epoch": 4.402359108781127, "percentage": 44.02, "elapsed_time": "0:28:15", "remaining_time": "0:35:55", "throughput": 2655.32, "total_tokens": 4501104} {"current_steps": 16800, "total_steps": 38150, "loss": 0.3949, "lr": 3.4337586612074515e-05, "epoch": 4.4036697247706424, "percentage": 44.04, "elapsed_time": "0:28:15", "remaining_time": "0:35:55", "throughput": 2655.84, "total_tokens": 4504208} {"current_steps": 16805, "total_steps": 38150, "loss": 0.3852, "lr": 3.4326976083159194e-05, "epoch": 4.404980340760157, "percentage": 44.05, "elapsed_time": "0:28:16", "remaining_time": "0:35:54", "throughput": 2656.06, "total_tokens": 4505920} {"current_steps": 16810, "total_steps": 38150, "loss": 0.4092, "lr": 3.43163636021239e-05, "epoch": 4.406290956749673, "percentage": 44.06, "elapsed_time": "0:28:16", "remaining_time": "0:35:54", "throughput": 2656.26, "total_tokens": 4507536} {"current_steps": 16815, "total_steps": 38150, "loss": 0.3021, "lr": 3.43057491711898e-05, "epoch": 4.407601572739187, "percentage": 44.08, "elapsed_time": "0:28:17", "remaining_time": "0:35:53", "throughput": 2656.31, "total_tokens": 4508768} {"current_steps": 16820, "total_steps": 38150, "loss": 0.3312, "lr": 3.429513279257848e-05, "epoch": 4.408912188728703, "percentage": 44.09, "elapsed_time": "0:28:17", "remaining_time": "0:35:53", "throughput": 2656.48, "total_tokens": 4510336} {"current_steps": 16825, "total_steps": 38150, "loss": 0.36, "lr": 3.428451446851192e-05, "epoch": 4.4102228047182175, "percentage": 44.1, "elapsed_time": "0:28:18", "remaining_time": "0:35:52", "throughput": 2656.62, "total_tokens": 4511840} {"current_steps": 16830, "total_steps": 38150, "loss": 0.3445, "lr": 3.427389420121253e-05, "epoch": 4.411533420707733, "percentage": 44.12, "elapsed_time": "0:28:18", "remaining_time": "0:35:51", "throughput": 2656.65, "total_tokens": 4513008} {"current_steps": 16835, "total_steps": 38150, "loss": 0.2621, "lr": 3.42632719929031e-05, "epoch": 4.412844036697248, "percentage": 44.13, "elapsed_time": "0:28:19", "remaining_time": "0:35:51", "throughput": 2656.72, "total_tokens": 4514352} {"current_steps": 16840, "total_steps": 38150, "loss": 0.3844, "lr": 3.425264784580686e-05, "epoch": 4.414154652686763, "percentage": 44.14, "elapsed_time": "0:28:19", "remaining_time": "0:35:50", "throughput": 2656.87, "total_tokens": 4515792} {"current_steps": 16845, "total_steps": 38150, "loss": 0.2682, "lr": 3.424202176214741e-05, "epoch": 4.415465268676278, "percentage": 44.15, "elapsed_time": "0:28:20", "remaining_time": "0:35:50", "throughput": 2656.79, "total_tokens": 4516752} {"current_steps": 16850, "total_steps": 38150, "loss": 0.2936, "lr": 3.423139374414877e-05, "epoch": 4.4167758846657925, "percentage": 44.17, "elapsed_time": "0:28:20", "remaining_time": "0:35:49", "throughput": 2656.76, "total_tokens": 4517808} {"current_steps": 16855, "total_steps": 38150, "loss": 0.4362, "lr": 3.422076379403537e-05, "epoch": 4.418086500655308, "percentage": 44.18, "elapsed_time": "0:28:20", "remaining_time": "0:35:48", "throughput": 2656.76, "total_tokens": 4518944} {"current_steps": 16860, "total_steps": 38150, "loss": 0.2964, "lr": 3.421013191403203e-05, "epoch": 4.419397116644823, "percentage": 44.19, "elapsed_time": "0:28:21", "remaining_time": "0:35:48", "throughput": 2656.8, "total_tokens": 4520160} {"current_steps": 16865, "total_steps": 38150, "loss": 0.3035, "lr": 3.419949810636401e-05, "epoch": 4.420707732634338, "percentage": 44.21, "elapsed_time": "0:28:21", "remaining_time": "0:35:47", "throughput": 2656.79, "total_tokens": 4521264} {"current_steps": 16870, "total_steps": 38150, "loss": 0.4034, "lr": 3.418886237325693e-05, "epoch": 4.422018348623853, "percentage": 44.22, "elapsed_time": "0:28:22", "remaining_time": "0:35:47", "throughput": 2656.72, "total_tokens": 4522272} {"current_steps": 16875, "total_steps": 38150, "loss": 0.4091, "lr": 3.417822471693683e-05, "epoch": 4.423328964613368, "percentage": 44.23, "elapsed_time": "0:28:22", "remaining_time": "0:35:46", "throughput": 2656.7, "total_tokens": 4523344} {"current_steps": 16880, "total_steps": 38150, "loss": 0.3875, "lr": 3.4167585139630156e-05, "epoch": 4.424639580602883, "percentage": 44.25, "elapsed_time": "0:28:23", "remaining_time": "0:35:46", "throughput": 2656.88, "total_tokens": 4524944} {"current_steps": 16885, "total_steps": 38150, "loss": 0.4026, "lr": 3.415694364356375e-05, "epoch": 4.425950196592399, "percentage": 44.26, "elapsed_time": "0:28:23", "remaining_time": "0:35:45", "throughput": 2656.9, "total_tokens": 4526112} {"current_steps": 16890, "total_steps": 38150, "loss": 0.3814, "lr": 3.414630023096486e-05, "epoch": 4.427260812581913, "percentage": 44.27, "elapsed_time": "0:28:24", "remaining_time": "0:35:44", "throughput": 2657.12, "total_tokens": 4527920} {"current_steps": 16895, "total_steps": 38150, "loss": 0.2913, "lr": 3.413565490406114e-05, "epoch": 4.428571428571429, "percentage": 44.29, "elapsed_time": "0:28:24", "remaining_time": "0:35:44", "throughput": 2657.24, "total_tokens": 4529280} {"current_steps": 16900, "total_steps": 38150, "loss": 0.3354, "lr": 3.412500766508063e-05, "epoch": 4.4298820445609435, "percentage": 44.3, "elapsed_time": "0:28:24", "remaining_time": "0:35:43", "throughput": 2657.39, "total_tokens": 4530736} {"current_steps": 16905, "total_steps": 38150, "loss": 0.4041, "lr": 3.411435851625179e-05, "epoch": 4.431192660550459, "percentage": 44.31, "elapsed_time": "0:28:25", "remaining_time": "0:35:43", "throughput": 2657.58, "total_tokens": 4532336} {"current_steps": 16910, "total_steps": 38150, "loss": 0.3551, "lr": 3.4103707459803456e-05, "epoch": 4.432503276539974, "percentage": 44.33, "elapsed_time": "0:28:25", "remaining_time": "0:35:42", "throughput": 2657.69, "total_tokens": 4533728} {"current_steps": 16915, "total_steps": 38150, "loss": 0.368, "lr": 3.4093054497964884e-05, "epoch": 4.433813892529489, "percentage": 44.34, "elapsed_time": "0:28:26", "remaining_time": "0:35:42", "throughput": 2657.71, "total_tokens": 4534992} {"current_steps": 16920, "total_steps": 38150, "loss": 0.3017, "lr": 3.40823996329657e-05, "epoch": 4.435124508519004, "percentage": 44.35, "elapsed_time": "0:28:26", "remaining_time": "0:35:41", "throughput": 2657.84, "total_tokens": 4536512} {"current_steps": 16925, "total_steps": 38150, "loss": 0.4736, "lr": 3.4071742867035985e-05, "epoch": 4.436435124508519, "percentage": 44.36, "elapsed_time": "0:28:27", "remaining_time": "0:35:41", "throughput": 2657.98, "total_tokens": 4537984} {"current_steps": 16930, "total_steps": 38150, "loss": 0.2645, "lr": 3.4061084202406154e-05, "epoch": 4.437745740498034, "percentage": 44.38, "elapsed_time": "0:28:27", "remaining_time": "0:35:40", "throughput": 2658.32, "total_tokens": 4540032} {"current_steps": 16935, "total_steps": 38150, "loss": 0.2923, "lr": 3.405042364130706e-05, "epoch": 4.43905635648755, "percentage": 44.39, "elapsed_time": "0:28:28", "remaining_time": "0:35:40", "throughput": 2658.5, "total_tokens": 4541792} {"current_steps": 16940, "total_steps": 38150, "loss": 0.384, "lr": 3.403976118596994e-05, "epoch": 4.440366972477064, "percentage": 44.4, "elapsed_time": "0:28:28", "remaining_time": "0:35:39", "throughput": 2658.51, "total_tokens": 4542976} {"current_steps": 16945, "total_steps": 38150, "loss": 0.364, "lr": 3.4029096838626415e-05, "epoch": 4.441677588466579, "percentage": 44.42, "elapsed_time": "0:28:29", "remaining_time": "0:35:38", "throughput": 2658.64, "total_tokens": 4544368} {"current_steps": 16950, "total_steps": 38150, "loss": 0.3048, "lr": 3.401843060150853e-05, "epoch": 4.442988204456094, "percentage": 44.43, "elapsed_time": "0:28:29", "remaining_time": "0:35:38", "throughput": 2658.68, "total_tokens": 4545648} {"current_steps": 16955, "total_steps": 38150, "loss": 0.2863, "lr": 3.400776247684869e-05, "epoch": 4.444298820445609, "percentage": 44.44, "elapsed_time": "0:28:30", "remaining_time": "0:35:37", "throughput": 2658.61, "total_tokens": 4546624} {"current_steps": 16960, "total_steps": 38150, "loss": 0.2703, "lr": 3.399709246687974e-05, "epoch": 4.445609436435125, "percentage": 44.46, "elapsed_time": "0:28:30", "remaining_time": "0:35:37", "throughput": 2658.7, "total_tokens": 4547968} {"current_steps": 16965, "total_steps": 38150, "loss": 0.3523, "lr": 3.398642057383488e-05, "epoch": 4.446920052424639, "percentage": 44.47, "elapsed_time": "0:28:31", "remaining_time": "0:35:36", "throughput": 2658.95, "total_tokens": 4549872} {"current_steps": 16970, "total_steps": 38150, "loss": 0.2991, "lr": 3.397574679994772e-05, "epoch": 4.448230668414155, "percentage": 44.48, "elapsed_time": "0:28:31", "remaining_time": "0:35:36", "throughput": 2659.06, "total_tokens": 4551216} {"current_steps": 16975, "total_steps": 38150, "loss": 0.3483, "lr": 3.396507114745226e-05, "epoch": 4.4495412844036695, "percentage": 44.5, "elapsed_time": "0:28:32", "remaining_time": "0:35:35", "throughput": 2659.03, "total_tokens": 4552288} {"current_steps": 16980, "total_steps": 38150, "loss": 0.3322, "lr": 3.3954393618582905e-05, "epoch": 4.450851900393185, "percentage": 44.51, "elapsed_time": "0:28:32", "remaining_time": "0:35:35", "throughput": 2659.12, "total_tokens": 4553664} {"current_steps": 16985, "total_steps": 38150, "loss": 0.4882, "lr": 3.394371421557444e-05, "epoch": 4.4521625163827, "percentage": 44.52, "elapsed_time": "0:28:32", "remaining_time": "0:35:34", "throughput": 2659.21, "total_tokens": 4555104} {"current_steps": 16990, "total_steps": 38150, "loss": 0.3861, "lr": 3.3933032940662034e-05, "epoch": 4.453473132372215, "percentage": 44.53, "elapsed_time": "0:28:33", "remaining_time": "0:35:34", "throughput": 2659.39, "total_tokens": 4556752} {"current_steps": 16995, "total_steps": 38150, "loss": 0.3212, "lr": 3.392234979608128e-05, "epoch": 4.45478374836173, "percentage": 44.55, "elapsed_time": "0:28:33", "remaining_time": "0:35:33", "throughput": 2659.31, "total_tokens": 4557728} {"current_steps": 17000, "total_steps": 38150, "loss": 0.251, "lr": 3.391166478406812e-05, "epoch": 4.456094364351245, "percentage": 44.56, "elapsed_time": "0:28:34", "remaining_time": "0:35:32", "throughput": 2659.4, "total_tokens": 4559088} {"current_steps": 17005, "total_steps": 38150, "loss": 0.3803, "lr": 3.390097790685892e-05, "epoch": 4.45740498034076, "percentage": 44.57, "elapsed_time": "0:28:34", "remaining_time": "0:35:32", "throughput": 2659.41, "total_tokens": 4560304} {"current_steps": 17010, "total_steps": 38150, "loss": 0.3078, "lr": 3.3890289166690425e-05, "epoch": 4.458715596330276, "percentage": 44.59, "elapsed_time": "0:28:35", "remaining_time": "0:35:31", "throughput": 2659.52, "total_tokens": 4561808} {"current_steps": 17015, "total_steps": 38150, "loss": 0.3896, "lr": 3.387959856579977e-05, "epoch": 4.46002621231979, "percentage": 44.6, "elapsed_time": "0:28:35", "remaining_time": "0:35:31", "throughput": 2659.87, "total_tokens": 4563984} {"current_steps": 17020, "total_steps": 38150, "loss": 0.5568, "lr": 3.386890610642448e-05, "epoch": 4.461336828309306, "percentage": 44.61, "elapsed_time": "0:28:36", "remaining_time": "0:35:30", "throughput": 2660.12, "total_tokens": 4565744} {"current_steps": 17025, "total_steps": 38150, "loss": 0.311, "lr": 3.3858211790802466e-05, "epoch": 4.46264744429882, "percentage": 44.63, "elapsed_time": "0:28:36", "remaining_time": "0:35:30", "throughput": 2660.07, "total_tokens": 4566768} {"current_steps": 17030, "total_steps": 38150, "loss": 0.3382, "lr": 3.384751562117203e-05, "epoch": 4.463958060288336, "percentage": 44.64, "elapsed_time": "0:28:37", "remaining_time": "0:35:29", "throughput": 2660.1, "total_tokens": 4567952} {"current_steps": 17035, "total_steps": 38150, "loss": 0.364, "lr": 3.3836817599771854e-05, "epoch": 4.465268676277851, "percentage": 44.65, "elapsed_time": "0:28:37", "remaining_time": "0:35:29", "throughput": 2660.12, "total_tokens": 4569120} {"current_steps": 17040, "total_steps": 38150, "loss": 0.4608, "lr": 3.382611772884103e-05, "epoch": 4.466579292267365, "percentage": 44.67, "elapsed_time": "0:28:38", "remaining_time": "0:35:28", "throughput": 2660.21, "total_tokens": 4570448} {"current_steps": 17045, "total_steps": 38150, "loss": 0.3148, "lr": 3.3815416010619013e-05, "epoch": 4.467889908256881, "percentage": 44.68, "elapsed_time": "0:28:38", "remaining_time": "0:35:27", "throughput": 2660.43, "total_tokens": 4572144} {"current_steps": 17050, "total_steps": 38150, "loss": 0.2438, "lr": 3.380471244734566e-05, "epoch": 4.4692005242463955, "percentage": 44.69, "elapsed_time": "0:28:38", "remaining_time": "0:35:27", "throughput": 2660.44, "total_tokens": 4573296} {"current_steps": 17055, "total_steps": 38150, "loss": 0.261, "lr": 3.3794007041261205e-05, "epoch": 4.470511140235911, "percentage": 44.71, "elapsed_time": "0:28:39", "remaining_time": "0:35:26", "throughput": 2660.38, "total_tokens": 4574336} {"current_steps": 17060, "total_steps": 38150, "loss": 0.3559, "lr": 3.378329979460627e-05, "epoch": 4.471821756225426, "percentage": 44.72, "elapsed_time": "0:28:39", "remaining_time": "0:35:26", "throughput": 2660.52, "total_tokens": 4575840} {"current_steps": 17065, "total_steps": 38150, "loss": 0.256, "lr": 3.3772590709621864e-05, "epoch": 4.473132372214941, "percentage": 44.73, "elapsed_time": "0:28:40", "remaining_time": "0:35:25", "throughput": 2660.56, "total_tokens": 4577072} {"current_steps": 17070, "total_steps": 38150, "loss": 0.3377, "lr": 3.376187978854938e-05, "epoch": 4.474442988204456, "percentage": 44.74, "elapsed_time": "0:28:40", "remaining_time": "0:35:25", "throughput": 2660.61, "total_tokens": 4578384} {"current_steps": 17075, "total_steps": 38150, "loss": 0.2584, "lr": 3.3751167033630596e-05, "epoch": 4.475753604193971, "percentage": 44.76, "elapsed_time": "0:28:41", "remaining_time": "0:35:24", "throughput": 2660.73, "total_tokens": 4579808} {"current_steps": 17080, "total_steps": 38150, "loss": 0.4071, "lr": 3.374045244710767e-05, "epoch": 4.477064220183486, "percentage": 44.77, "elapsed_time": "0:28:41", "remaining_time": "0:35:23", "throughput": 2660.63, "total_tokens": 4580736} {"current_steps": 17085, "total_steps": 38150, "loss": 0.2945, "lr": 3.372973603122316e-05, "epoch": 4.478374836173002, "percentage": 44.78, "elapsed_time": "0:28:42", "remaining_time": "0:35:23", "throughput": 2660.59, "total_tokens": 4581792} {"current_steps": 17090, "total_steps": 38150, "loss": 0.3223, "lr": 3.371901778821997e-05, "epoch": 4.479685452162516, "percentage": 44.8, "elapsed_time": "0:28:42", "remaining_time": "0:35:22", "throughput": 2660.64, "total_tokens": 4583040} {"current_steps": 17095, "total_steps": 38150, "loss": 0.3793, "lr": 3.3708297720341425e-05, "epoch": 4.480996068152032, "percentage": 44.81, "elapsed_time": "0:28:42", "remaining_time": "0:35:22", "throughput": 2660.7, "total_tokens": 4584320} {"current_steps": 17100, "total_steps": 38150, "loss": 0.4335, "lr": 3.369757582983122e-05, "epoch": 4.482306684141546, "percentage": 44.82, "elapsed_time": "0:28:43", "remaining_time": "0:35:21", "throughput": 2660.77, "total_tokens": 4585584} {"current_steps": 17105, "total_steps": 38150, "loss": 0.4685, "lr": 3.368685211893342e-05, "epoch": 4.483617300131062, "percentage": 44.84, "elapsed_time": "0:28:43", "remaining_time": "0:35:20", "throughput": 2660.92, "total_tokens": 4587136} {"current_steps": 17110, "total_steps": 38150, "loss": 0.3875, "lr": 3.367612658989247e-05, "epoch": 4.484927916120577, "percentage": 44.85, "elapsed_time": "0:28:44", "remaining_time": "0:35:20", "throughput": 2661.06, "total_tokens": 4588624} {"current_steps": 17115, "total_steps": 38150, "loss": 0.2905, "lr": 3.3665399244953236e-05, "epoch": 4.486238532110092, "percentage": 44.86, "elapsed_time": "0:28:44", "remaining_time": "0:35:19", "throughput": 2660.99, "total_tokens": 4589632} {"current_steps": 17120, "total_steps": 38150, "loss": 0.3091, "lr": 3.36546700863609e-05, "epoch": 4.487549148099607, "percentage": 44.88, "elapsed_time": "0:28:45", "remaining_time": "0:35:19", "throughput": 2660.86, "total_tokens": 4590512} {"current_steps": 17125, "total_steps": 38150, "loss": 0.3269, "lr": 3.364393911636107e-05, "epoch": 4.488859764089122, "percentage": 44.89, "elapsed_time": "0:28:45", "remaining_time": "0:35:18", "throughput": 2660.83, "total_tokens": 4591600} {"current_steps": 17130, "total_steps": 38150, "loss": 0.3797, "lr": 3.363320633719972e-05, "epoch": 4.490170380078637, "percentage": 44.9, "elapsed_time": "0:28:46", "remaining_time": "0:35:18", "throughput": 2660.77, "total_tokens": 4592640} {"current_steps": 17135, "total_steps": 38150, "loss": 0.5637, "lr": 3.3622471751123196e-05, "epoch": 4.491480996068152, "percentage": 44.91, "elapsed_time": "0:28:46", "remaining_time": "0:35:17", "throughput": 2660.94, "total_tokens": 4594224} {"current_steps": 17140, "total_steps": 38150, "loss": 0.2937, "lr": 3.361173536037824e-05, "epoch": 4.492791612057667, "percentage": 44.93, "elapsed_time": "0:28:47", "remaining_time": "0:35:16", "throughput": 2661.12, "total_tokens": 4595808} {"current_steps": 17145, "total_steps": 38150, "loss": 0.3161, "lr": 3.360099716721195e-05, "epoch": 4.494102228047182, "percentage": 44.94, "elapsed_time": "0:28:47", "remaining_time": "0:35:16", "throughput": 2661.25, "total_tokens": 4597264} {"current_steps": 17150, "total_steps": 38150, "loss": 0.3574, "lr": 3.3590257173871807e-05, "epoch": 4.495412844036697, "percentage": 44.95, "elapsed_time": "0:28:47", "remaining_time": "0:35:15", "throughput": 2661.27, "total_tokens": 4598544} {"current_steps": 17155, "total_steps": 38150, "loss": 0.433, "lr": 3.357951538260569e-05, "epoch": 4.496723460026212, "percentage": 44.97, "elapsed_time": "0:28:48", "remaining_time": "0:35:15", "throughput": 2661.3, "total_tokens": 4599728} {"current_steps": 17160, "total_steps": 38150, "loss": 0.3047, "lr": 3.356877179566183e-05, "epoch": 4.498034076015728, "percentage": 44.98, "elapsed_time": "0:28:48", "remaining_time": "0:35:14", "throughput": 2661.47, "total_tokens": 4601216} {"current_steps": 17165, "total_steps": 38150, "loss": 0.4204, "lr": 3.355802641528883e-05, "epoch": 4.499344692005242, "percentage": 44.99, "elapsed_time": "0:28:49", "remaining_time": "0:35:14", "throughput": 2661.55, "total_tokens": 4602576} {"current_steps": 17170, "total_steps": 38150, "loss": 0.3171, "lr": 3.3547279243735695e-05, "epoch": 4.500655307994758, "percentage": 45.01, "elapsed_time": "0:28:49", "remaining_time": "0:35:13", "throughput": 2661.65, "total_tokens": 4603984} {"current_steps": 17172, "total_steps": 38150, "eval_loss": 0.5279697775840759, "epoch": 4.501179554390563, "percentage": 45.01, "elapsed_time": "0:29:06", "remaining_time": "0:35:33", "throughput": 2636.01, "total_tokens": 4604416} {"current_steps": 17175, "total_steps": 38150, "loss": 0.3837, "lr": 3.3536530283251784e-05, "epoch": 4.501965923984272, "percentage": 45.02, "elapsed_time": "0:29:08", "remaining_time": "0:35:35", "throughput": 2634.04, "total_tokens": 4605232} {"current_steps": 17180, "total_steps": 38150, "loss": 0.2866, "lr": 3.3525779536086826e-05, "epoch": 4.503276539973788, "percentage": 45.03, "elapsed_time": "0:29:08", "remaining_time": "0:35:34", "throughput": 2634.04, "total_tokens": 4606368} {"current_steps": 17185, "total_steps": 38150, "loss": 0.4816, "lr": 3.351502700449095e-05, "epoch": 4.504587155963303, "percentage": 45.05, "elapsed_time": "0:29:09", "remaining_time": "0:35:33", "throughput": 2634.09, "total_tokens": 4607600} {"current_steps": 17190, "total_steps": 38150, "loss": 0.3181, "lr": 3.350427269071463e-05, "epoch": 4.505897771952818, "percentage": 45.06, "elapsed_time": "0:29:09", "remaining_time": "0:35:33", "throughput": 2634.12, "total_tokens": 4608800} {"current_steps": 17195, "total_steps": 38150, "loss": 0.3577, "lr": 3.3493516597008734e-05, "epoch": 4.507208387942333, "percentage": 45.07, "elapsed_time": "0:29:10", "remaining_time": "0:35:32", "throughput": 2633.99, "total_tokens": 4609696} {"current_steps": 17200, "total_steps": 38150, "loss": 0.2513, "lr": 3.348275872562449e-05, "epoch": 4.508519003931848, "percentage": 45.09, "elapsed_time": "0:29:10", "remaining_time": "0:35:32", "throughput": 2634.05, "total_tokens": 4610944} {"current_steps": 17205, "total_steps": 38150, "loss": 0.3427, "lr": 3.34719990788135e-05, "epoch": 4.509829619921363, "percentage": 45.1, "elapsed_time": "0:29:10", "remaining_time": "0:35:31", "throughput": 2634.17, "total_tokens": 4612368} {"current_steps": 17210, "total_steps": 38150, "loss": 0.2995, "lr": 3.346123765882774e-05, "epoch": 4.511140235910878, "percentage": 45.11, "elapsed_time": "0:29:11", "remaining_time": "0:35:30", "throughput": 2634.17, "total_tokens": 4613472} {"current_steps": 17215, "total_steps": 38150, "loss": 0.4784, "lr": 3.345047446791956e-05, "epoch": 4.512450851900393, "percentage": 45.12, "elapsed_time": "0:29:11", "remaining_time": "0:35:30", "throughput": 2634.21, "total_tokens": 4614688} {"current_steps": 17220, "total_steps": 38150, "loss": 0.3078, "lr": 3.3439709508341676e-05, "epoch": 4.513761467889909, "percentage": 45.14, "elapsed_time": "0:29:12", "remaining_time": "0:35:29", "throughput": 2634.34, "total_tokens": 4616160} {"current_steps": 17225, "total_steps": 38150, "loss": 0.2536, "lr": 3.342894278234717e-05, "epoch": 4.515072083879423, "percentage": 45.15, "elapsed_time": "0:29:12", "remaining_time": "0:35:29", "throughput": 2634.35, "total_tokens": 4617264} {"current_steps": 17230, "total_steps": 38150, "loss": 0.3764, "lr": 3.341817429218951e-05, "epoch": 4.516382699868938, "percentage": 45.16, "elapsed_time": "0:29:13", "remaining_time": "0:35:28", "throughput": 2634.72, "total_tokens": 4619456} {"current_steps": 17235, "total_steps": 38150, "loss": 0.2881, "lr": 3.340740404012251e-05, "epoch": 4.517693315858454, "percentage": 45.18, "elapsed_time": "0:29:13", "remaining_time": "0:35:28", "throughput": 2634.83, "total_tokens": 4620960} {"current_steps": 17240, "total_steps": 38150, "loss": 0.2579, "lr": 3.339663202840038e-05, "epoch": 4.519003931847968, "percentage": 45.19, "elapsed_time": "0:29:14", "remaining_time": "0:35:27", "throughput": 2634.88, "total_tokens": 4622176} {"current_steps": 17245, "total_steps": 38150, "loss": 0.37, "lr": 3.3385858259277666e-05, "epoch": 4.520314547837484, "percentage": 45.2, "elapsed_time": "0:29:14", "remaining_time": "0:35:27", "throughput": 2635.07, "total_tokens": 4623808} {"current_steps": 17250, "total_steps": 38150, "loss": 0.404, "lr": 3.337508273500931e-05, "epoch": 4.521625163826998, "percentage": 45.22, "elapsed_time": "0:29:15", "remaining_time": "0:35:26", "throughput": 2635.54, "total_tokens": 4626640} {"current_steps": 17255, "total_steps": 38150, "loss": 0.2523, "lr": 3.336430545785061e-05, "epoch": 4.522935779816514, "percentage": 45.23, "elapsed_time": "0:29:15", "remaining_time": "0:35:26", "throughput": 2635.57, "total_tokens": 4627824} {"current_steps": 17260, "total_steps": 38150, "loss": 0.2844, "lr": 3.335352643005723e-05, "epoch": 4.524246395806029, "percentage": 45.24, "elapsed_time": "0:29:16", "remaining_time": "0:35:25", "throughput": 2635.67, "total_tokens": 4629232} {"current_steps": 17265, "total_steps": 38150, "loss": 0.4962, "lr": 3.33427456538852e-05, "epoch": 4.525557011795544, "percentage": 45.26, "elapsed_time": "0:29:16", "remaining_time": "0:35:25", "throughput": 2635.69, "total_tokens": 4630416} {"current_steps": 17270, "total_steps": 38150, "loss": 0.4714, "lr": 3.3331963131590916e-05, "epoch": 4.526867627785059, "percentage": 45.27, "elapsed_time": "0:29:17", "remaining_time": "0:35:24", "throughput": 2635.87, "total_tokens": 4631984} {"current_steps": 17275, "total_steps": 38150, "loss": 0.2323, "lr": 3.3321178865431155e-05, "epoch": 4.528178243774574, "percentage": 45.28, "elapsed_time": "0:29:17", "remaining_time": "0:35:24", "throughput": 2635.87, "total_tokens": 4633104} {"current_steps": 17280, "total_steps": 38150, "loss": 0.4396, "lr": 3.331039285766303e-05, "epoch": 4.529488859764089, "percentage": 45.29, "elapsed_time": "0:29:18", "remaining_time": "0:35:23", "throughput": 2636.05, "total_tokens": 4634656} {"current_steps": 17285, "total_steps": 38150, "loss": 0.4718, "lr": 3.329960511054404e-05, "epoch": 4.5307994757536045, "percentage": 45.31, "elapsed_time": "0:29:18", "remaining_time": "0:35:22", "throughput": 2635.97, "total_tokens": 4635616} {"current_steps": 17290, "total_steps": 38150, "loss": 0.2231, "lr": 3.3288815626332035e-05, "epoch": 4.532110091743119, "percentage": 45.32, "elapsed_time": "0:29:19", "remaining_time": "0:35:22", "throughput": 2635.97, "total_tokens": 4636720} {"current_steps": 17295, "total_steps": 38150, "loss": 0.389, "lr": 3.327802440728526e-05, "epoch": 4.533420707732635, "percentage": 45.33, "elapsed_time": "0:29:19", "remaining_time": "0:35:21", "throughput": 2636.0, "total_tokens": 4637904} {"current_steps": 17300, "total_steps": 38150, "loss": 0.3614, "lr": 3.3267231455662265e-05, "epoch": 4.534731323722149, "percentage": 45.35, "elapsed_time": "0:29:19", "remaining_time": "0:35:21", "throughput": 2636.12, "total_tokens": 4639264} {"current_steps": 17305, "total_steps": 38150, "loss": 0.2648, "lr": 3.325643677372201e-05, "epoch": 4.536041939711664, "percentage": 45.36, "elapsed_time": "0:29:20", "remaining_time": "0:35:20", "throughput": 2636.01, "total_tokens": 4640176} {"current_steps": 17310, "total_steps": 38150, "loss": 0.4249, "lr": 3.324564036372381e-05, "epoch": 4.53735255570118, "percentage": 45.37, "elapsed_time": "0:29:20", "remaining_time": "0:35:19", "throughput": 2636.09, "total_tokens": 4641440} {"current_steps": 17315, "total_steps": 38150, "loss": 0.3616, "lr": 3.323484222792732e-05, "epoch": 4.538663171690695, "percentage": 45.39, "elapsed_time": "0:29:21", "remaining_time": "0:35:19", "throughput": 2636.05, "total_tokens": 4642496} {"current_steps": 17320, "total_steps": 38150, "loss": 0.4466, "lr": 3.322404236859259e-05, "epoch": 4.53997378768021, "percentage": 45.4, "elapsed_time": "0:29:21", "remaining_time": "0:35:18", "throughput": 2636.11, "total_tokens": 4643744} {"current_steps": 17325, "total_steps": 38150, "loss": 0.2892, "lr": 3.321324078798e-05, "epoch": 4.541284403669724, "percentage": 45.41, "elapsed_time": "0:29:22", "remaining_time": "0:35:17", "throughput": 2636.18, "total_tokens": 4645024} {"current_steps": 17330, "total_steps": 38150, "loss": 0.2813, "lr": 3.32024374883503e-05, "epoch": 4.54259501965924, "percentage": 45.43, "elapsed_time": "0:29:22", "remaining_time": "0:35:17", "throughput": 2636.11, "total_tokens": 4645984} {"current_steps": 17335, "total_steps": 38150, "loss": 0.4431, "lr": 3.319163247196462e-05, "epoch": 4.543905635648755, "percentage": 45.44, "elapsed_time": "0:29:22", "remaining_time": "0:35:16", "throughput": 2636.09, "total_tokens": 4647072} {"current_steps": 17340, "total_steps": 38150, "loss": 0.3084, "lr": 3.318082574108441e-05, "epoch": 4.54521625163827, "percentage": 45.45, "elapsed_time": "0:29:23", "remaining_time": "0:35:16", "throughput": 2636.14, "total_tokens": 4648304} {"current_steps": 17345, "total_steps": 38150, "loss": 0.305, "lr": 3.31700172979715e-05, "epoch": 4.546526867627785, "percentage": 45.47, "elapsed_time": "0:29:23", "remaining_time": "0:35:15", "throughput": 2636.23, "total_tokens": 4649728} {"current_steps": 17350, "total_steps": 38150, "loss": 0.273, "lr": 3.315920714488808e-05, "epoch": 4.5478374836173, "percentage": 45.48, "elapsed_time": "0:29:24", "remaining_time": "0:35:14", "throughput": 2636.23, "total_tokens": 4650816} {"current_steps": 17355, "total_steps": 38150, "loss": 0.4184, "lr": 3.314839528409672e-05, "epoch": 4.549148099606815, "percentage": 45.49, "elapsed_time": "0:29:24", "remaining_time": "0:35:14", "throughput": 2636.2, "total_tokens": 4651888} {"current_steps": 17360, "total_steps": 38150, "loss": 0.4103, "lr": 3.313758171786031e-05, "epoch": 4.5504587155963305, "percentage": 45.5, "elapsed_time": "0:29:25", "remaining_time": "0:35:13", "throughput": 2636.2, "total_tokens": 4653008} {"current_steps": 17365, "total_steps": 38150, "loss": 0.4605, "lr": 3.3126766448442095e-05, "epoch": 4.551769331585845, "percentage": 45.52, "elapsed_time": "0:29:25", "remaining_time": "0:35:13", "throughput": 2636.38, "total_tokens": 4654560} {"current_steps": 17370, "total_steps": 38150, "loss": 0.3433, "lr": 3.311594947810571e-05, "epoch": 4.553079947575361, "percentage": 45.53, "elapsed_time": "0:29:25", "remaining_time": "0:35:12", "throughput": 2636.32, "total_tokens": 4655552} {"current_steps": 17375, "total_steps": 38150, "loss": 0.5154, "lr": 3.310513080911512e-05, "epoch": 4.554390563564875, "percentage": 45.54, "elapsed_time": "0:29:26", "remaining_time": "0:35:12", "throughput": 2636.37, "total_tokens": 4656800} {"current_steps": 17380, "total_steps": 38150, "loss": 0.3977, "lr": 3.309431044373465e-05, "epoch": 4.555701179554391, "percentage": 45.56, "elapsed_time": "0:29:26", "remaining_time": "0:35:11", "throughput": 2636.47, "total_tokens": 4658208} {"current_steps": 17385, "total_steps": 38150, "loss": 0.2255, "lr": 3.3083488384228995e-05, "epoch": 4.557011795543906, "percentage": 45.57, "elapsed_time": "0:29:27", "remaining_time": "0:35:10", "throughput": 2636.43, "total_tokens": 4659248} {"current_steps": 17390, "total_steps": 38150, "loss": 0.3152, "lr": 3.3072664632863195e-05, "epoch": 4.558322411533421, "percentage": 45.58, "elapsed_time": "0:29:27", "remaining_time": "0:35:10", "throughput": 2636.45, "total_tokens": 4660480} {"current_steps": 17395, "total_steps": 38150, "loss": 0.3314, "lr": 3.3061839191902635e-05, "epoch": 4.559633027522936, "percentage": 45.6, "elapsed_time": "0:29:28", "remaining_time": "0:35:09", "throughput": 2636.36, "total_tokens": 4661408} {"current_steps": 17400, "total_steps": 38150, "loss": 0.2387, "lr": 3.3051012063613054e-05, "epoch": 4.56094364351245, "percentage": 45.61, "elapsed_time": "0:29:28", "remaining_time": "0:35:09", "throughput": 2636.32, "total_tokens": 4662464} {"current_steps": 17405, "total_steps": 38150, "loss": 0.4977, "lr": 3.3040183250260556e-05, "epoch": 4.562254259501966, "percentage": 45.62, "elapsed_time": "0:29:28", "remaining_time": "0:35:08", "throughput": 2636.4, "total_tokens": 4663744} {"current_steps": 17410, "total_steps": 38150, "loss": 0.3673, "lr": 3.30293527541116e-05, "epoch": 4.5635648754914815, "percentage": 45.64, "elapsed_time": "0:29:29", "remaining_time": "0:35:07", "throughput": 2636.43, "total_tokens": 4665008} {"current_steps": 17415, "total_steps": 38150, "loss": 0.3312, "lr": 3.3018520577432996e-05, "epoch": 4.564875491480996, "percentage": 45.65, "elapsed_time": "0:29:29", "remaining_time": "0:35:07", "throughput": 2636.62, "total_tokens": 4666672} {"current_steps": 17420, "total_steps": 38150, "loss": 0.3048, "lr": 3.3007686722491885e-05, "epoch": 4.566186107470511, "percentage": 45.66, "elapsed_time": "0:29:30", "remaining_time": "0:35:06", "throughput": 2636.48, "total_tokens": 4667552} {"current_steps": 17425, "total_steps": 38150, "loss": 0.418, "lr": 3.299685119155577e-05, "epoch": 4.567496723460026, "percentage": 45.67, "elapsed_time": "0:29:30", "remaining_time": "0:35:06", "throughput": 2636.44, "total_tokens": 4668592} {"current_steps": 17430, "total_steps": 38150, "loss": 0.2386, "lr": 3.298601398689253e-05, "epoch": 4.568807339449541, "percentage": 45.69, "elapsed_time": "0:29:31", "remaining_time": "0:35:05", "throughput": 2636.52, "total_tokens": 4669984} {"current_steps": 17435, "total_steps": 38150, "loss": 0.5244, "lr": 3.297517511077035e-05, "epoch": 4.5701179554390565, "percentage": 45.7, "elapsed_time": "0:29:31", "remaining_time": "0:35:04", "throughput": 2636.56, "total_tokens": 4671168} {"current_steps": 17440, "total_steps": 38150, "loss": 0.3672, "lr": 3.296433456545781e-05, "epoch": 4.571428571428571, "percentage": 45.71, "elapsed_time": "0:29:32", "remaining_time": "0:35:04", "throughput": 2636.73, "total_tokens": 4672768} {"current_steps": 17445, "total_steps": 38150, "loss": 0.3425, "lr": 3.2953492353223805e-05, "epoch": 4.572739187418087, "percentage": 45.73, "elapsed_time": "0:29:32", "remaining_time": "0:35:03", "throughput": 2636.97, "total_tokens": 4674544} {"current_steps": 17450, "total_steps": 38150, "loss": 0.4289, "lr": 3.294264847633759e-05, "epoch": 4.574049803407601, "percentage": 45.74, "elapsed_time": "0:29:33", "remaining_time": "0:35:03", "throughput": 2636.93, "total_tokens": 4675584} {"current_steps": 17455, "total_steps": 38150, "loss": 0.6242, "lr": 3.2931802937068776e-05, "epoch": 4.575360419397117, "percentage": 45.75, "elapsed_time": "0:29:33", "remaining_time": "0:35:02", "throughput": 2636.97, "total_tokens": 4676784} {"current_steps": 17460, "total_steps": 38150, "loss": 0.3184, "lr": 3.292095573768731e-05, "epoch": 4.576671035386632, "percentage": 45.77, "elapsed_time": "0:29:33", "remaining_time": "0:35:02", "throughput": 2636.95, "total_tokens": 4677856} {"current_steps": 17465, "total_steps": 38150, "loss": 0.315, "lr": 3.2910106880463486e-05, "epoch": 4.577981651376147, "percentage": 45.78, "elapsed_time": "0:29:34", "remaining_time": "0:35:01", "throughput": 2636.98, "total_tokens": 4679040} {"current_steps": 17470, "total_steps": 38150, "loss": 0.3083, "lr": 3.289925636766797e-05, "epoch": 4.579292267365662, "percentage": 45.79, "elapsed_time": "0:29:34", "remaining_time": "0:35:00", "throughput": 2637.07, "total_tokens": 4680400} {"current_steps": 17475, "total_steps": 38150, "loss": 0.3716, "lr": 3.2888404201571743e-05, "epoch": 4.580602883355177, "percentage": 45.81, "elapsed_time": "0:29:35", "remaining_time": "0:35:00", "throughput": 2637.2, "total_tokens": 4681888} {"current_steps": 17480, "total_steps": 38150, "loss": 0.3805, "lr": 3.2877550384446146e-05, "epoch": 4.581913499344692, "percentage": 45.82, "elapsed_time": "0:29:35", "remaining_time": "0:34:59", "throughput": 2637.12, "total_tokens": 4682848} {"current_steps": 17485, "total_steps": 38150, "loss": 0.3764, "lr": 3.2866694918562866e-05, "epoch": 4.5832241153342075, "percentage": 45.83, "elapsed_time": "0:29:36", "remaining_time": "0:34:59", "throughput": 2637.15, "total_tokens": 4684096} {"current_steps": 17490, "total_steps": 38150, "loss": 0.2697, "lr": 3.285583780619394e-05, "epoch": 4.584534731323722, "percentage": 45.85, "elapsed_time": "0:29:36", "remaining_time": "0:34:58", "throughput": 2637.22, "total_tokens": 4685344} {"current_steps": 17495, "total_steps": 38150, "loss": 0.3557, "lr": 3.284497904961172e-05, "epoch": 4.585845347313237, "percentage": 45.86, "elapsed_time": "0:29:37", "remaining_time": "0:34:58", "throughput": 2637.31, "total_tokens": 4686768} {"current_steps": 17500, "total_steps": 38150, "loss": 0.4009, "lr": 3.283411865108894e-05, "epoch": 4.587155963302752, "percentage": 45.87, "elapsed_time": "0:29:37", "remaining_time": "0:34:57", "throughput": 2637.26, "total_tokens": 4687776} {"current_steps": 17505, "total_steps": 38150, "loss": 0.3891, "lr": 3.2823256612898676e-05, "epoch": 4.588466579292267, "percentage": 45.88, "elapsed_time": "0:29:37", "remaining_time": "0:34:56", "throughput": 2637.2, "total_tokens": 4688752} {"current_steps": 17510, "total_steps": 38150, "loss": 0.3017, "lr": 3.2812392937314316e-05, "epoch": 4.5897771952817825, "percentage": 45.9, "elapsed_time": "0:29:38", "remaining_time": "0:34:56", "throughput": 2637.27, "total_tokens": 4690128} {"current_steps": 17515, "total_steps": 38150, "loss": 0.3322, "lr": 3.2801527626609606e-05, "epoch": 4.591087811271297, "percentage": 45.91, "elapsed_time": "0:29:38", "remaining_time": "0:34:55", "throughput": 2637.3, "total_tokens": 4691312} {"current_steps": 17520, "total_steps": 38150, "loss": 0.3666, "lr": 3.2790660683058646e-05, "epoch": 4.592398427260813, "percentage": 45.92, "elapsed_time": "0:29:39", "remaining_time": "0:34:55", "throughput": 2637.54, "total_tokens": 4693120} {"current_steps": 17525, "total_steps": 38150, "loss": 0.3553, "lr": 3.277979210893587e-05, "epoch": 4.593709043250327, "percentage": 45.94, "elapsed_time": "0:29:39", "remaining_time": "0:34:54", "throughput": 2637.7, "total_tokens": 4694640} {"current_steps": 17530, "total_steps": 38150, "loss": 0.2765, "lr": 3.276892190651605e-05, "epoch": 4.595019659239843, "percentage": 45.95, "elapsed_time": "0:29:40", "remaining_time": "0:34:54", "throughput": 2637.76, "total_tokens": 4695888} {"current_steps": 17535, "total_steps": 38150, "loss": 0.3136, "lr": 3.275805007807429e-05, "epoch": 4.5963302752293576, "percentage": 45.96, "elapsed_time": "0:29:40", "remaining_time": "0:34:53", "throughput": 2637.72, "total_tokens": 4696928} {"current_steps": 17540, "total_steps": 38150, "loss": 0.4569, "lr": 3.274717662588606e-05, "epoch": 4.597640891218873, "percentage": 45.98, "elapsed_time": "0:29:41", "remaining_time": "0:34:52", "throughput": 2637.92, "total_tokens": 4698608} {"current_steps": 17545, "total_steps": 38150, "loss": 0.2121, "lr": 3.273630155222715e-05, "epoch": 4.598951507208388, "percentage": 45.99, "elapsed_time": "0:29:41", "remaining_time": "0:34:52", "throughput": 2637.98, "total_tokens": 4699856} {"current_steps": 17550, "total_steps": 38150, "loss": 0.326, "lr": 3.272542485937369e-05, "epoch": 4.600262123197903, "percentage": 46.0, "elapsed_time": "0:29:42", "remaining_time": "0:34:51", "throughput": 2638.18, "total_tokens": 4701488} {"current_steps": 17555, "total_steps": 38150, "loss": 0.4373, "lr": 3.271454654960215e-05, "epoch": 4.601572739187418, "percentage": 46.02, "elapsed_time": "0:29:42", "remaining_time": "0:34:51", "throughput": 2638.31, "total_tokens": 4702960} {"current_steps": 17560, "total_steps": 38150, "loss": 0.276, "lr": 3.270366662518936e-05, "epoch": 4.6028833551769335, "percentage": 46.03, "elapsed_time": "0:29:43", "remaining_time": "0:34:50", "throughput": 2638.36, "total_tokens": 4704208} {"current_steps": 17565, "total_steps": 38150, "loss": 0.1696, "lr": 3.2692785088412444e-05, "epoch": 4.604193971166448, "percentage": 46.04, "elapsed_time": "0:29:43", "remaining_time": "0:34:50", "throughput": 2638.42, "total_tokens": 4705440} {"current_steps": 17570, "total_steps": 38150, "loss": 0.3825, "lr": 3.268190194154891e-05, "epoch": 4.605504587155964, "percentage": 46.06, "elapsed_time": "0:29:43", "remaining_time": "0:34:49", "throughput": 2638.52, "total_tokens": 4706944} {"current_steps": 17575, "total_steps": 38150, "loss": 0.3459, "lr": 3.267101718687657e-05, "epoch": 4.606815203145478, "percentage": 46.07, "elapsed_time": "0:29:44", "remaining_time": "0:34:48", "throughput": 2638.6, "total_tokens": 4708304} {"current_steps": 17580, "total_steps": 38150, "loss": 0.1923, "lr": 3.266013082667357e-05, "epoch": 4.608125819134994, "percentage": 46.08, "elapsed_time": "0:29:44", "remaining_time": "0:34:48", "throughput": 2638.61, "total_tokens": 4709424} {"current_steps": 17585, "total_steps": 38150, "loss": 0.3787, "lr": 3.2649242863218446e-05, "epoch": 4.6094364351245085, "percentage": 46.09, "elapsed_time": "0:29:45", "remaining_time": "0:34:47", "throughput": 2638.71, "total_tokens": 4710832} {"current_steps": 17590, "total_steps": 38150, "loss": 0.332, "lr": 3.2638353298790005e-05, "epoch": 4.610747051114023, "percentage": 46.11, "elapsed_time": "0:29:45", "remaining_time": "0:34:47", "throughput": 2638.8, "total_tokens": 4712144} {"current_steps": 17595, "total_steps": 38150, "loss": 0.4826, "lr": 3.2627462135667405e-05, "epoch": 4.612057667103539, "percentage": 46.12, "elapsed_time": "0:29:46", "remaining_time": "0:34:46", "throughput": 2638.96, "total_tokens": 4713648} {"current_steps": 17600, "total_steps": 38150, "loss": 0.2266, "lr": 3.2616569376130175e-05, "epoch": 4.613368283093053, "percentage": 46.13, "elapsed_time": "0:29:46", "remaining_time": "0:34:46", "throughput": 2639.1, "total_tokens": 4715168} {"current_steps": 17605, "total_steps": 38150, "loss": 0.5748, "lr": 3.260567502245813e-05, "epoch": 4.614678899082569, "percentage": 46.15, "elapsed_time": "0:29:47", "remaining_time": "0:34:45", "throughput": 2639.09, "total_tokens": 4716272} {"current_steps": 17610, "total_steps": 38150, "loss": 0.3167, "lr": 3.259477907693144e-05, "epoch": 4.6159895150720835, "percentage": 46.16, "elapsed_time": "0:29:47", "remaining_time": "0:34:44", "throughput": 2639.11, "total_tokens": 4717504} {"current_steps": 17615, "total_steps": 38150, "loss": 0.3883, "lr": 3.2583881541830604e-05, "epoch": 4.617300131061599, "percentage": 46.17, "elapsed_time": "0:29:47", "remaining_time": "0:34:44", "throughput": 2639.14, "total_tokens": 4718768} {"current_steps": 17620, "total_steps": 38150, "loss": 0.3418, "lr": 3.257298241943648e-05, "epoch": 4.618610747051114, "percentage": 46.19, "elapsed_time": "0:29:48", "remaining_time": "0:34:43", "throughput": 2639.22, "total_tokens": 4720160} {"current_steps": 17625, "total_steps": 38150, "loss": 0.359, "lr": 3.256208171203021e-05, "epoch": 4.619921363040629, "percentage": 46.2, "elapsed_time": "0:29:48", "remaining_time": "0:34:43", "throughput": 2639.18, "total_tokens": 4721168} {"current_steps": 17630, "total_steps": 38150, "loss": 0.3088, "lr": 3.255117942189331e-05, "epoch": 4.621231979030144, "percentage": 46.21, "elapsed_time": "0:29:49", "remaining_time": "0:34:42", "throughput": 2639.15, "total_tokens": 4722304} {"current_steps": 17635, "total_steps": 38150, "loss": 0.2622, "lr": 3.2540275551307605e-05, "epoch": 4.6225425950196595, "percentage": 46.23, "elapsed_time": "0:29:49", "remaining_time": "0:34:42", "throughput": 2639.27, "total_tokens": 4723792} {"current_steps": 17640, "total_steps": 38150, "loss": 0.3361, "lr": 3.252937010255525e-05, "epoch": 4.623853211009174, "percentage": 46.24, "elapsed_time": "0:29:50", "remaining_time": "0:34:41", "throughput": 2639.33, "total_tokens": 4725312} {"current_steps": 17645, "total_steps": 38150, "loss": 0.2513, "lr": 3.2518463077918746e-05, "epoch": 4.62516382699869, "percentage": 46.25, "elapsed_time": "0:29:50", "remaining_time": "0:34:41", "throughput": 2639.31, "total_tokens": 4726400} {"current_steps": 17650, "total_steps": 38150, "loss": 0.3911, "lr": 3.250755447968091e-05, "epoch": 4.626474442988204, "percentage": 46.26, "elapsed_time": "0:29:51", "remaining_time": "0:34:40", "throughput": 2639.62, "total_tokens": 4728416} {"current_steps": 17655, "total_steps": 38150, "loss": 0.4441, "lr": 3.24966443101249e-05, "epoch": 4.62778505897772, "percentage": 46.28, "elapsed_time": "0:29:51", "remaining_time": "0:34:39", "throughput": 2639.58, "total_tokens": 4729472} {"current_steps": 17660, "total_steps": 38150, "loss": 0.4202, "lr": 3.248573257153418e-05, "epoch": 4.6290956749672345, "percentage": 46.29, "elapsed_time": "0:29:52", "remaining_time": "0:34:39", "throughput": 2639.73, "total_tokens": 4730912} {"current_steps": 17665, "total_steps": 38150, "loss": 0.2136, "lr": 3.2474819266192574e-05, "epoch": 4.63040629095675, "percentage": 46.3, "elapsed_time": "0:29:52", "remaining_time": "0:34:38", "throughput": 2639.73, "total_tokens": 4732064} {"current_steps": 17670, "total_steps": 38150, "loss": 0.3932, "lr": 3.24639043963842e-05, "epoch": 4.631716906946265, "percentage": 46.32, "elapsed_time": "0:29:53", "remaining_time": "0:34:38", "throughput": 2639.87, "total_tokens": 4733536} {"current_steps": 17675, "total_steps": 38150, "loss": 0.1977, "lr": 3.245298796439354e-05, "epoch": 4.63302752293578, "percentage": 46.33, "elapsed_time": "0:29:53", "remaining_time": "0:34:37", "throughput": 2640.02, "total_tokens": 4734992} {"current_steps": 17680, "total_steps": 38150, "loss": 0.3628, "lr": 3.244206997250538e-05, "epoch": 4.634338138925295, "percentage": 46.34, "elapsed_time": "0:29:54", "remaining_time": "0:34:37", "throughput": 2640.12, "total_tokens": 4736480} {"current_steps": 17685, "total_steps": 38150, "loss": 0.3232, "lr": 3.243115042300483e-05, "epoch": 4.6356487549148095, "percentage": 46.36, "elapsed_time": "0:29:54", "remaining_time": "0:34:36", "throughput": 2640.22, "total_tokens": 4737936} {"current_steps": 17690, "total_steps": 38150, "loss": 0.3259, "lr": 3.242022931817734e-05, "epoch": 4.636959370904325, "percentage": 46.37, "elapsed_time": "0:29:54", "remaining_time": "0:34:36", "throughput": 2640.24, "total_tokens": 4739088} {"current_steps": 17695, "total_steps": 38150, "loss": 0.3469, "lr": 3.240930666030867e-05, "epoch": 4.63826998689384, "percentage": 46.38, "elapsed_time": "0:29:55", "remaining_time": "0:34:35", "throughput": 2640.3, "total_tokens": 4740352} {"current_steps": 17700, "total_steps": 38150, "loss": 0.3541, "lr": 3.239838245168492e-05, "epoch": 4.639580602883355, "percentage": 46.4, "elapsed_time": "0:29:55", "remaining_time": "0:34:34", "throughput": 2640.33, "total_tokens": 4741520} {"current_steps": 17705, "total_steps": 38150, "loss": 0.3272, "lr": 3.238745669459251e-05, "epoch": 4.64089121887287, "percentage": 46.41, "elapsed_time": "0:29:56", "remaining_time": "0:34:34", "throughput": 2640.34, "total_tokens": 4742672} {"current_steps": 17710, "total_steps": 38150, "loss": 0.4202, "lr": 3.237652939131818e-05, "epoch": 4.6422018348623855, "percentage": 46.42, "elapsed_time": "0:29:56", "remaining_time": "0:34:33", "throughput": 2640.41, "total_tokens": 4743920} {"current_steps": 17715, "total_steps": 38150, "loss": 0.3645, "lr": 3.236560054414899e-05, "epoch": 4.6435124508519, "percentage": 46.44, "elapsed_time": "0:29:57", "remaining_time": "0:34:33", "throughput": 2640.57, "total_tokens": 4745472} {"current_steps": 17720, "total_steps": 38150, "loss": 0.5206, "lr": 3.2354670155372326e-05, "epoch": 4.644823066841416, "percentage": 46.45, "elapsed_time": "0:29:57", "remaining_time": "0:34:32", "throughput": 2640.55, "total_tokens": 4746528} {"current_steps": 17725, "total_steps": 38150, "loss": 0.5343, "lr": 3.234373822727591e-05, "epoch": 4.64613368283093, "percentage": 46.46, "elapsed_time": "0:29:58", "remaining_time": "0:34:31", "throughput": 2640.56, "total_tokens": 4747744} {"current_steps": 17730, "total_steps": 38150, "loss": 0.2836, "lr": 3.233280476214778e-05, "epoch": 4.647444298820446, "percentage": 46.47, "elapsed_time": "0:29:58", "remaining_time": "0:34:31", "throughput": 2640.59, "total_tokens": 4748992} {"current_steps": 17735, "total_steps": 38150, "loss": 0.4292, "lr": 3.232186976227628e-05, "epoch": 4.6487549148099605, "percentage": 46.49, "elapsed_time": "0:29:58", "remaining_time": "0:34:30", "throughput": 2640.62, "total_tokens": 4750240} {"current_steps": 17740, "total_steps": 38150, "loss": 0.3531, "lr": 3.231093322995008e-05, "epoch": 4.650065530799476, "percentage": 46.5, "elapsed_time": "0:29:59", "remaining_time": "0:34:30", "throughput": 2640.62, "total_tokens": 4751376} {"current_steps": 17745, "total_steps": 38150, "loss": 0.2668, "lr": 3.2299995167458196e-05, "epoch": 4.651376146788991, "percentage": 46.51, "elapsed_time": "0:29:59", "remaining_time": "0:34:29", "throughput": 2640.73, "total_tokens": 4752720} {"current_steps": 17750, "total_steps": 38150, "loss": 0.4106, "lr": 3.2289055577089936e-05, "epoch": 4.652686762778506, "percentage": 46.53, "elapsed_time": "0:30:00", "remaining_time": "0:34:28", "throughput": 2640.87, "total_tokens": 4754144} {"current_steps": 17755, "total_steps": 38150, "loss": 0.4221, "lr": 3.227811446113494e-05, "epoch": 4.653997378768021, "percentage": 46.54, "elapsed_time": "0:30:00", "remaining_time": "0:34:28", "throughput": 2640.97, "total_tokens": 4755568} {"current_steps": 17760, "total_steps": 38150, "loss": 0.4273, "lr": 3.226717182188316e-05, "epoch": 4.655307994757536, "percentage": 46.55, "elapsed_time": "0:30:01", "remaining_time": "0:34:27", "throughput": 2641.02, "total_tokens": 4756816} {"current_steps": 17765, "total_steps": 38150, "loss": 0.5992, "lr": 3.2256227661624874e-05, "epoch": 4.656618610747051, "percentage": 46.57, "elapsed_time": "0:30:01", "remaining_time": "0:34:27", "throughput": 2641.08, "total_tokens": 4758080} {"current_steps": 17770, "total_steps": 38150, "loss": 0.5591, "lr": 3.2245281982650683e-05, "epoch": 4.657929226736567, "percentage": 46.58, "elapsed_time": "0:30:01", "remaining_time": "0:34:26", "throughput": 2641.11, "total_tokens": 4759248} {"current_steps": 17775, "total_steps": 38150, "loss": 0.4024, "lr": 3.2234334787251487e-05, "epoch": 4.659239842726081, "percentage": 46.59, "elapsed_time": "0:30:02", "remaining_time": "0:34:26", "throughput": 2641.21, "total_tokens": 4760720} {"current_steps": 17780, "total_steps": 38150, "loss": 0.3253, "lr": 3.222338607771851e-05, "epoch": 4.660550458715596, "percentage": 46.61, "elapsed_time": "0:30:02", "remaining_time": "0:34:25", "throughput": 2641.36, "total_tokens": 4762256} {"current_steps": 17785, "total_steps": 38150, "loss": 0.4095, "lr": 3.221243585634333e-05, "epoch": 4.6618610747051115, "percentage": 46.62, "elapsed_time": "0:30:03", "remaining_time": "0:34:25", "throughput": 2641.45, "total_tokens": 4763632} {"current_steps": 17790, "total_steps": 38150, "loss": 0.2255, "lr": 3.2201484125417766e-05, "epoch": 4.663171690694626, "percentage": 46.63, "elapsed_time": "0:30:03", "remaining_time": "0:34:24", "throughput": 2641.66, "total_tokens": 4765456} {"current_steps": 17795, "total_steps": 38150, "loss": 0.3291, "lr": 3.219053088723403e-05, "epoch": 4.664482306684142, "percentage": 46.64, "elapsed_time": "0:30:04", "remaining_time": "0:34:23", "throughput": 2641.57, "total_tokens": 4766400} {"current_steps": 17800, "total_steps": 38150, "loss": 0.4237, "lr": 3.21795761440846e-05, "epoch": 4.665792922673656, "percentage": 46.66, "elapsed_time": "0:30:04", "remaining_time": "0:34:23", "throughput": 2641.57, "total_tokens": 4767552} {"current_steps": 17805, "total_steps": 38150, "loss": 0.3564, "lr": 3.2168619898262294e-05, "epoch": 4.667103538663172, "percentage": 46.67, "elapsed_time": "0:30:05", "remaining_time": "0:34:22", "throughput": 2641.56, "total_tokens": 4768656} {"current_steps": 17810, "total_steps": 38150, "loss": 0.5361, "lr": 3.215766215206022e-05, "epoch": 4.6684141546526865, "percentage": 46.68, "elapsed_time": "0:30:05", "remaining_time": "0:34:22", "throughput": 2641.76, "total_tokens": 4770288} {"current_steps": 17815, "total_steps": 38150, "loss": 0.4249, "lr": 3.2146702907771824e-05, "epoch": 4.669724770642202, "percentage": 46.7, "elapsed_time": "0:30:06", "remaining_time": "0:34:21", "throughput": 2641.87, "total_tokens": 4771744} {"current_steps": 17820, "total_steps": 38150, "loss": 0.3876, "lr": 3.2135742167690866e-05, "epoch": 4.671035386631717, "percentage": 46.71, "elapsed_time": "0:30:06", "remaining_time": "0:34:21", "throughput": 2642.01, "total_tokens": 4773232} {"current_steps": 17825, "total_steps": 38150, "loss": 0.635, "lr": 3.212477993411141e-05, "epoch": 4.672346002621232, "percentage": 46.72, "elapsed_time": "0:30:07", "remaining_time": "0:34:20", "throughput": 2642.23, "total_tokens": 4774832} {"current_steps": 17830, "total_steps": 38150, "loss": 0.4328, "lr": 3.211381620932781e-05, "epoch": 4.673656618610747, "percentage": 46.74, "elapsed_time": "0:30:07", "remaining_time": "0:34:20", "throughput": 2642.38, "total_tokens": 4776352} {"current_steps": 17835, "total_steps": 38150, "loss": 0.379, "lr": 3.2102850995634765e-05, "epoch": 4.674967234600262, "percentage": 46.75, "elapsed_time": "0:30:08", "remaining_time": "0:34:19", "throughput": 2642.58, "total_tokens": 4777968} {"current_steps": 17840, "total_steps": 38150, "loss": 0.3511, "lr": 3.209188429532729e-05, "epoch": 4.676277850589777, "percentage": 46.76, "elapsed_time": "0:30:08", "remaining_time": "0:34:18", "throughput": 2642.65, "total_tokens": 4779248} {"current_steps": 17845, "total_steps": 38150, "loss": 0.2264, "lr": 3.2080916110700684e-05, "epoch": 4.677588466579293, "percentage": 46.78, "elapsed_time": "0:30:08", "remaining_time": "0:34:18", "throughput": 2642.64, "total_tokens": 4780368} {"current_steps": 17850, "total_steps": 38150, "loss": 0.4027, "lr": 3.206994644405057e-05, "epoch": 4.678899082568807, "percentage": 46.79, "elapsed_time": "0:30:09", "remaining_time": "0:34:17", "throughput": 2642.9, "total_tokens": 4782304} {"current_steps": 17855, "total_steps": 38150, "loss": 0.3022, "lr": 3.2058975297672874e-05, "epoch": 4.680209698558322, "percentage": 46.8, "elapsed_time": "0:30:09", "remaining_time": "0:34:17", "throughput": 2642.8, "total_tokens": 4783232} {"current_steps": 17860, "total_steps": 38150, "loss": 0.304, "lr": 3.204800267386385e-05, "epoch": 4.6815203145478375, "percentage": 46.82, "elapsed_time": "0:30:10", "remaining_time": "0:34:16", "throughput": 2642.84, "total_tokens": 4784448} {"current_steps": 17865, "total_steps": 38150, "loss": 0.2507, "lr": 3.203702857492005e-05, "epoch": 4.682830930537353, "percentage": 46.83, "elapsed_time": "0:30:10", "remaining_time": "0:34:16", "throughput": 2642.74, "total_tokens": 4785376} {"current_steps": 17870, "total_steps": 38150, "loss": 0.4365, "lr": 3.202605300313833e-05, "epoch": 4.684141546526868, "percentage": 46.84, "elapsed_time": "0:30:11", "remaining_time": "0:34:15", "throughput": 2642.92, "total_tokens": 4786992} {"current_steps": 17875, "total_steps": 38150, "loss": 0.2885, "lr": 3.201507596081585e-05, "epoch": 4.685452162516382, "percentage": 46.85, "elapsed_time": "0:30:11", "remaining_time": "0:34:14", "throughput": 2642.82, "total_tokens": 4787920} {"current_steps": 17880, "total_steps": 38150, "loss": 0.287, "lr": 3.200409745025009e-05, "epoch": 4.686762778505898, "percentage": 46.87, "elapsed_time": "0:30:12", "remaining_time": "0:34:14", "throughput": 2642.94, "total_tokens": 4789392} {"current_steps": 17885, "total_steps": 38150, "loss": 0.4524, "lr": 3.199311747373885e-05, "epoch": 4.6880733944954125, "percentage": 46.88, "elapsed_time": "0:30:12", "remaining_time": "0:34:14", "throughput": 2643.37, "total_tokens": 4791888} {"current_steps": 17890, "total_steps": 38150, "loss": 0.2922, "lr": 3.198213603358019e-05, "epoch": 4.689384010484928, "percentage": 46.89, "elapsed_time": "0:30:13", "remaining_time": "0:34:13", "throughput": 2643.37, "total_tokens": 4793008} {"current_steps": 17895, "total_steps": 38150, "loss": 0.2953, "lr": 3.197115313207252e-05, "epoch": 4.690694626474443, "percentage": 46.91, "elapsed_time": "0:30:13", "remaining_time": "0:34:12", "throughput": 2643.43, "total_tokens": 4794272} {"current_steps": 17900, "total_steps": 38150, "loss": 0.4123, "lr": 3.1960168771514565e-05, "epoch": 4.692005242463958, "percentage": 46.92, "elapsed_time": "0:30:14", "remaining_time": "0:34:12", "throughput": 2643.51, "total_tokens": 4795552} {"current_steps": 17905, "total_steps": 38150, "loss": 0.2065, "lr": 3.1949182954205295e-05, "epoch": 4.693315858453473, "percentage": 46.93, "elapsed_time": "0:30:14", "remaining_time": "0:34:11", "throughput": 2643.55, "total_tokens": 4796832} {"current_steps": 17910, "total_steps": 38150, "loss": 0.4119, "lr": 3.193819568244405e-05, "epoch": 4.694626474442988, "percentage": 46.95, "elapsed_time": "0:30:15", "remaining_time": "0:34:11", "throughput": 2643.71, "total_tokens": 4798432} {"current_steps": 17915, "total_steps": 38150, "loss": 0.3347, "lr": 3.192720695853043e-05, "epoch": 4.695937090432503, "percentage": 46.96, "elapsed_time": "0:30:15", "remaining_time": "0:34:10", "throughput": 2643.77, "total_tokens": 4799792} {"current_steps": 17920, "total_steps": 38150, "loss": 0.3941, "lr": 3.1916216784764365e-05, "epoch": 4.697247706422019, "percentage": 46.97, "elapsed_time": "0:30:15", "remaining_time": "0:34:10", "throughput": 2643.75, "total_tokens": 4800864} {"current_steps": 17925, "total_steps": 38150, "loss": 0.3232, "lr": 3.1905225163446075e-05, "epoch": 4.698558322411533, "percentage": 46.99, "elapsed_time": "0:30:16", "remaining_time": "0:34:09", "throughput": 2643.84, "total_tokens": 4802176} {"current_steps": 17930, "total_steps": 38150, "loss": 0.4085, "lr": 3.189423209687609e-05, "epoch": 4.699868938401049, "percentage": 47.0, "elapsed_time": "0:30:16", "remaining_time": "0:34:08", "throughput": 2643.96, "total_tokens": 4803568} {"current_steps": 17935, "total_steps": 38150, "loss": 0.3275, "lr": 3.188323758735524e-05, "epoch": 4.7011795543905635, "percentage": 47.01, "elapsed_time": "0:30:17", "remaining_time": "0:34:08", "throughput": 2644.0, "total_tokens": 4804784} {"current_steps": 17940, "total_steps": 38150, "loss": 0.4444, "lr": 3.187224163718466e-05, "epoch": 4.702490170380079, "percentage": 47.02, "elapsed_time": "0:30:17", "remaining_time": "0:34:07", "throughput": 2644.01, "total_tokens": 4805920} {"current_steps": 17945, "total_steps": 38150, "loss": 0.3112, "lr": 3.186124424866578e-05, "epoch": 4.703800786369594, "percentage": 47.04, "elapsed_time": "0:30:18", "remaining_time": "0:34:07", "throughput": 2644.17, "total_tokens": 4807472} {"current_steps": 17950, "total_steps": 38150, "loss": 0.3725, "lr": 3.185024542410033e-05, "epoch": 4.705111402359108, "percentage": 47.05, "elapsed_time": "0:30:18", "remaining_time": "0:34:06", "throughput": 2644.24, "total_tokens": 4808912} {"current_steps": 17955, "total_steps": 38150, "loss": 0.3045, "lr": 3.183924516579034e-05, "epoch": 4.706422018348624, "percentage": 47.06, "elapsed_time": "0:30:19", "remaining_time": "0:34:05", "throughput": 2644.25, "total_tokens": 4810016} {"current_steps": 17960, "total_steps": 38150, "loss": 0.2659, "lr": 3.182824347603818e-05, "epoch": 4.707732634338139, "percentage": 47.08, "elapsed_time": "0:30:19", "remaining_time": "0:34:05", "throughput": 2644.36, "total_tokens": 4811392} {"current_steps": 17965, "total_steps": 38150, "loss": 0.4178, "lr": 3.181724035714644e-05, "epoch": 4.709043250327654, "percentage": 47.09, "elapsed_time": "0:30:19", "remaining_time": "0:34:04", "throughput": 2644.49, "total_tokens": 4812944} {"current_steps": 17970, "total_steps": 38150, "loss": 0.432, "lr": 3.1806235811418074e-05, "epoch": 4.710353866317169, "percentage": 47.1, "elapsed_time": "0:30:20", "remaining_time": "0:34:04", "throughput": 2644.61, "total_tokens": 4814448} {"current_steps": 17975, "total_steps": 38150, "loss": 0.3548, "lr": 3.179522984115632e-05, "epoch": 4.711664482306684, "percentage": 47.12, "elapsed_time": "0:30:20", "remaining_time": "0:34:03", "throughput": 2644.64, "total_tokens": 4815632} {"current_steps": 17980, "total_steps": 38150, "loss": 0.4047, "lr": 3.178422244866469e-05, "epoch": 4.712975098296199, "percentage": 47.13, "elapsed_time": "0:30:21", "remaining_time": "0:34:03", "throughput": 2644.79, "total_tokens": 4817120} {"current_steps": 17985, "total_steps": 38150, "loss": 0.2401, "lr": 3.177321363624703e-05, "epoch": 4.714285714285714, "percentage": 47.14, "elapsed_time": "0:30:21", "remaining_time": "0:34:02", "throughput": 2644.77, "total_tokens": 4818208} {"current_steps": 17990, "total_steps": 38150, "loss": 0.2611, "lr": 3.176220340620746e-05, "epoch": 4.715596330275229, "percentage": 47.16, "elapsed_time": "0:30:22", "remaining_time": "0:34:02", "throughput": 2644.87, "total_tokens": 4819600} {"current_steps": 17995, "total_steps": 38150, "loss": 0.2894, "lr": 3.17511917608504e-05, "epoch": 4.716906946264745, "percentage": 47.17, "elapsed_time": "0:30:22", "remaining_time": "0:34:01", "throughput": 2644.85, "total_tokens": 4820672} {"current_steps": 18000, "total_steps": 38150, "loss": 0.3411, "lr": 3.174017870248057e-05, "epoch": 4.718217562254259, "percentage": 47.18, "elapsed_time": "0:30:23", "remaining_time": "0:34:00", "throughput": 2644.88, "total_tokens": 4821888} {"current_steps": 18005, "total_steps": 38150, "loss": 0.3261, "lr": 3.172916423340299e-05, "epoch": 4.719528178243775, "percentage": 47.2, "elapsed_time": "0:30:23", "remaining_time": "0:34:00", "throughput": 2645.07, "total_tokens": 4823504} {"current_steps": 18010, "total_steps": 38150, "loss": 0.3392, "lr": 3.171814835592294e-05, "epoch": 4.7208387942332894, "percentage": 47.21, "elapsed_time": "0:30:24", "remaining_time": "0:33:59", "throughput": 2645.27, "total_tokens": 4825136} {"current_steps": 18015, "total_steps": 38150, "loss": 0.5669, "lr": 3.170713107234607e-05, "epoch": 4.722149410222805, "percentage": 47.22, "elapsed_time": "0:30:24", "remaining_time": "0:33:59", "throughput": 2645.43, "total_tokens": 4826672} {"current_steps": 18020, "total_steps": 38150, "loss": 0.2781, "lr": 3.169611238497825e-05, "epoch": 4.72346002621232, "percentage": 47.23, "elapsed_time": "0:30:25", "remaining_time": "0:33:58", "throughput": 2645.6, "total_tokens": 4828496} {"current_steps": 18025, "total_steps": 38150, "loss": 0.5109, "lr": 3.168509229612568e-05, "epoch": 4.724770642201835, "percentage": 47.25, "elapsed_time": "0:30:25", "remaining_time": "0:33:58", "throughput": 2645.68, "total_tokens": 4829792} {"current_steps": 18030, "total_steps": 38150, "loss": 0.3996, "lr": 3.167407080809484e-05, "epoch": 4.72608125819135, "percentage": 47.26, "elapsed_time": "0:30:26", "remaining_time": "0:33:57", "throughput": 2645.78, "total_tokens": 4831216} {"current_steps": 18035, "total_steps": 38150, "loss": 0.2152, "lr": 3.166304792319251e-05, "epoch": 4.727391874180865, "percentage": 47.27, "elapsed_time": "0:30:26", "remaining_time": "0:33:57", "throughput": 2645.73, "total_tokens": 4832208} {"current_steps": 18040, "total_steps": 38150, "loss": 0.3311, "lr": 3.165202364372577e-05, "epoch": 4.72870249017038, "percentage": 47.29, "elapsed_time": "0:30:26", "remaining_time": "0:33:56", "throughput": 2645.82, "total_tokens": 4833616} {"current_steps": 18045, "total_steps": 38150, "loss": 0.3487, "lr": 3.164099797200197e-05, "epoch": 4.730013106159895, "percentage": 47.3, "elapsed_time": "0:30:27", "remaining_time": "0:33:55", "throughput": 2645.89, "total_tokens": 4834928} {"current_steps": 18050, "total_steps": 38150, "loss": 0.5269, "lr": 3.162997091032876e-05, "epoch": 4.73132372214941, "percentage": 47.31, "elapsed_time": "0:30:27", "remaining_time": "0:33:55", "throughput": 2645.93, "total_tokens": 4836128} {"current_steps": 18055, "total_steps": 38150, "loss": 0.3095, "lr": 3.161894246101411e-05, "epoch": 4.732634338138926, "percentage": 47.33, "elapsed_time": "0:30:28", "remaining_time": "0:33:54", "throughput": 2646.02, "total_tokens": 4837504} {"current_steps": 18060, "total_steps": 38150, "loss": 0.3948, "lr": 3.160791262636624e-05, "epoch": 4.73394495412844, "percentage": 47.34, "elapsed_time": "0:30:28", "remaining_time": "0:33:54", "throughput": 2646.04, "total_tokens": 4838720} {"current_steps": 18065, "total_steps": 38150, "loss": 0.3831, "lr": 3.159688140869366e-05, "epoch": 4.735255570117955, "percentage": 47.35, "elapsed_time": "0:30:29", "remaining_time": "0:33:53", "throughput": 2646.23, "total_tokens": 4840336} {"current_steps": 18070, "total_steps": 38150, "loss": 0.3427, "lr": 3.158584881030521e-05, "epoch": 4.736566186107471, "percentage": 47.37, "elapsed_time": "0:30:29", "remaining_time": "0:33:53", "throughput": 2646.22, "total_tokens": 4841424} {"current_steps": 18075, "total_steps": 38150, "loss": 0.489, "lr": 3.157481483350998e-05, "epoch": 4.737876802096985, "percentage": 47.38, "elapsed_time": "0:30:30", "remaining_time": "0:33:52", "throughput": 2646.26, "total_tokens": 4842704} {"current_steps": 18080, "total_steps": 38150, "loss": 0.4666, "lr": 3.156377948061737e-05, "epoch": 4.739187418086501, "percentage": 47.39, "elapsed_time": "0:30:30", "remaining_time": "0:33:51", "throughput": 2646.28, "total_tokens": 4843888} {"current_steps": 18085, "total_steps": 38150, "loss": 0.2482, "lr": 3.155274275393705e-05, "epoch": 4.740498034076015, "percentage": 47.4, "elapsed_time": "0:30:30", "remaining_time": "0:33:51", "throughput": 2646.25, "total_tokens": 4844960} {"current_steps": 18090, "total_steps": 38150, "loss": 0.374, "lr": 3.1541704655779e-05, "epoch": 4.741808650065531, "percentage": 47.42, "elapsed_time": "0:30:31", "remaining_time": "0:33:50", "throughput": 2646.33, "total_tokens": 4846272} {"current_steps": 18095, "total_steps": 38150, "loss": 0.491, "lr": 3.1530665188453464e-05, "epoch": 4.743119266055046, "percentage": 47.43, "elapsed_time": "0:30:31", "remaining_time": "0:33:50", "throughput": 2646.36, "total_tokens": 4847456} {"current_steps": 18100, "total_steps": 38150, "loss": 0.3397, "lr": 3.151962435427099e-05, "epoch": 4.744429882044561, "percentage": 47.44, "elapsed_time": "0:30:32", "remaining_time": "0:33:49", "throughput": 2646.35, "total_tokens": 4848560} {"current_steps": 18105, "total_steps": 38150, "loss": 0.3121, "lr": 3.15085821555424e-05, "epoch": 4.745740498034076, "percentage": 47.46, "elapsed_time": "0:30:32", "remaining_time": "0:33:49", "throughput": 2646.53, "total_tokens": 4850160} {"current_steps": 18110, "total_steps": 38150, "loss": 0.3551, "lr": 3.1497538594578814e-05, "epoch": 4.747051114023591, "percentage": 47.47, "elapsed_time": "0:30:33", "remaining_time": "0:33:48", "throughput": 2646.68, "total_tokens": 4851696} {"current_steps": 18115, "total_steps": 38150, "loss": 0.3689, "lr": 3.1486493673691624e-05, "epoch": 4.748361730013106, "percentage": 47.48, "elapsed_time": "0:30:33", "remaining_time": "0:33:47", "throughput": 2646.74, "total_tokens": 4853008} {"current_steps": 18120, "total_steps": 38150, "loss": 0.4082, "lr": 3.147544739519253e-05, "epoch": 4.749672346002622, "percentage": 47.5, "elapsed_time": "0:30:34", "remaining_time": "0:33:47", "throughput": 2646.83, "total_tokens": 4854352} {"current_steps": 18125, "total_steps": 38150, "loss": 0.2625, "lr": 3.1464399761393465e-05, "epoch": 4.750982961992136, "percentage": 47.51, "elapsed_time": "0:30:34", "remaining_time": "0:33:46", "throughput": 2647.02, "total_tokens": 4855904} {"current_steps": 18130, "total_steps": 38150, "loss": 0.341, "lr": 3.145335077460671e-05, "epoch": 4.752293577981652, "percentage": 47.52, "elapsed_time": "0:30:34", "remaining_time": "0:33:46", "throughput": 2647.22, "total_tokens": 4857536} {"current_steps": 18135, "total_steps": 38150, "loss": 0.2493, "lr": 3.144230043714479e-05, "epoch": 4.753604193971166, "percentage": 47.54, "elapsed_time": "0:30:35", "remaining_time": "0:33:45", "throughput": 2647.13, "total_tokens": 4858480} {"current_steps": 18140, "total_steps": 38150, "loss": 0.243, "lr": 3.143124875132052e-05, "epoch": 4.754914809960681, "percentage": 47.55, "elapsed_time": "0:30:35", "remaining_time": "0:33:45", "throughput": 2647.16, "total_tokens": 4859664} {"current_steps": 18145, "total_steps": 38150, "loss": 0.2937, "lr": 3.142019571944699e-05, "epoch": 4.756225425950197, "percentage": 47.56, "elapsed_time": "0:30:36", "remaining_time": "0:33:44", "throughput": 2647.39, "total_tokens": 4861472} {"current_steps": 18150, "total_steps": 38150, "loss": 0.4404, "lr": 3.140914134383759e-05, "epoch": 4.757536041939712, "percentage": 47.58, "elapsed_time": "0:30:36", "remaining_time": "0:33:43", "throughput": 2647.39, "total_tokens": 4862592} {"current_steps": 18155, "total_steps": 38150, "loss": 0.5672, "lr": 3.139808562680599e-05, "epoch": 4.758846657929227, "percentage": 47.59, "elapsed_time": "0:30:37", "remaining_time": "0:33:43", "throughput": 2647.39, "total_tokens": 4863696} {"current_steps": 18160, "total_steps": 38150, "loss": 0.2841, "lr": 3.138702857066612e-05, "epoch": 4.760157273918741, "percentage": 47.6, "elapsed_time": "0:30:37", "remaining_time": "0:33:42", "throughput": 2647.37, "total_tokens": 4864768} {"current_steps": 18165, "total_steps": 38150, "loss": 0.3204, "lr": 3.137597017773221e-05, "epoch": 4.761467889908257, "percentage": 47.61, "elapsed_time": "0:30:38", "remaining_time": "0:33:42", "throughput": 2647.43, "total_tokens": 4866112} {"current_steps": 18170, "total_steps": 38150, "loss": 0.2606, "lr": 3.136491045031875e-05, "epoch": 4.762778505897772, "percentage": 47.63, "elapsed_time": "0:30:38", "remaining_time": "0:33:41", "throughput": 2647.52, "total_tokens": 4867456} {"current_steps": 18175, "total_steps": 38150, "loss": 0.3781, "lr": 3.135384939074054e-05, "epoch": 4.764089121887287, "percentage": 47.64, "elapsed_time": "0:30:38", "remaining_time": "0:33:41", "throughput": 2647.52, "total_tokens": 4868592} {"current_steps": 18180, "total_steps": 38150, "loss": 0.406, "lr": 3.1342787001312615e-05, "epoch": 4.765399737876802, "percentage": 47.65, "elapsed_time": "0:30:39", "remaining_time": "0:33:40", "throughput": 2647.56, "total_tokens": 4869824} {"current_steps": 18185, "total_steps": 38150, "loss": 0.3229, "lr": 3.133172328435034e-05, "epoch": 4.766710353866317, "percentage": 47.67, "elapsed_time": "0:30:39", "remaining_time": "0:33:39", "throughput": 2647.67, "total_tokens": 4871200} {"current_steps": 18190, "total_steps": 38150, "loss": 0.3253, "lr": 3.132065824216932e-05, "epoch": 4.768020969855832, "percentage": 47.68, "elapsed_time": "0:30:40", "remaining_time": "0:33:39", "throughput": 2647.63, "total_tokens": 4872224} {"current_steps": 18195, "total_steps": 38150, "loss": 0.557, "lr": 3.1309591877085464e-05, "epoch": 4.7693315858453476, "percentage": 47.69, "elapsed_time": "0:30:40", "remaining_time": "0:33:38", "throughput": 2647.67, "total_tokens": 4873520} {"current_steps": 18200, "total_steps": 38150, "loss": 0.3565, "lr": 3.1298524191414915e-05, "epoch": 4.770642201834862, "percentage": 47.71, "elapsed_time": "0:30:41", "remaining_time": "0:33:38", "throughput": 2647.77, "total_tokens": 4874992} {"current_steps": 18205, "total_steps": 38150, "loss": 0.2462, "lr": 3.128745518747414e-05, "epoch": 4.771952817824378, "percentage": 47.72, "elapsed_time": "0:30:41", "remaining_time": "0:33:37", "throughput": 2647.77, "total_tokens": 4876112} {"current_steps": 18210, "total_steps": 38150, "loss": 0.1992, "lr": 3.127638486757985e-05, "epoch": 4.773263433813892, "percentage": 47.73, "elapsed_time": "0:30:42", "remaining_time": "0:33:37", "throughput": 2647.72, "total_tokens": 4877136} {"current_steps": 18215, "total_steps": 38150, "loss": 0.2401, "lr": 3.126531323404907e-05, "epoch": 4.774574049803408, "percentage": 47.75, "elapsed_time": "0:30:42", "remaining_time": "0:33:36", "throughput": 2647.92, "total_tokens": 4878848} {"current_steps": 18220, "total_steps": 38150, "loss": 0.2499, "lr": 3.125424028919904e-05, "epoch": 4.775884665792923, "percentage": 47.76, "elapsed_time": "0:30:43", "remaining_time": "0:33:36", "throughput": 2648.2, "total_tokens": 4880912} {"current_steps": 18225, "total_steps": 38150, "loss": 0.3984, "lr": 3.1243166035347335e-05, "epoch": 4.777195281782438, "percentage": 47.77, "elapsed_time": "0:30:43", "remaining_time": "0:33:35", "throughput": 2648.36, "total_tokens": 4882448} {"current_steps": 18230, "total_steps": 38150, "loss": 0.5212, "lr": 3.123209047481177e-05, "epoch": 4.778505897771953, "percentage": 47.79, "elapsed_time": "0:30:44", "remaining_time": "0:33:34", "throughput": 2648.43, "total_tokens": 4883792} {"current_steps": 18235, "total_steps": 38150, "loss": 0.4415, "lr": 3.1221013609910424e-05, "epoch": 4.779816513761467, "percentage": 47.8, "elapsed_time": "0:30:44", "remaining_time": "0:33:34", "throughput": 2648.42, "total_tokens": 4884928} {"current_steps": 18240, "total_steps": 38150, "loss": 0.4318, "lr": 3.120993544296168e-05, "epoch": 4.781127129750983, "percentage": 47.81, "elapsed_time": "0:30:44", "remaining_time": "0:33:33", "throughput": 2648.49, "total_tokens": 4886288} {"current_steps": 18245, "total_steps": 38150, "loss": 0.3677, "lr": 3.119885597628418e-05, "epoch": 4.7824377457404985, "percentage": 47.82, "elapsed_time": "0:30:45", "remaining_time": "0:33:33", "throughput": 2648.58, "total_tokens": 4887712} {"current_steps": 18250, "total_steps": 38150, "loss": 0.2729, "lr": 3.1187775212196835e-05, "epoch": 4.783748361730013, "percentage": 47.84, "elapsed_time": "0:30:45", "remaining_time": "0:33:32", "throughput": 2648.56, "total_tokens": 4888880} {"current_steps": 18255, "total_steps": 38150, "loss": 0.4057, "lr": 3.117669315301883e-05, "epoch": 4.785058977719528, "percentage": 47.85, "elapsed_time": "0:30:46", "remaining_time": "0:33:32", "throughput": 2648.62, "total_tokens": 4890208} {"current_steps": 18260, "total_steps": 38150, "loss": 0.2814, "lr": 3.116560980106962e-05, "epoch": 4.786369593709043, "percentage": 47.86, "elapsed_time": "0:30:46", "remaining_time": "0:33:31", "throughput": 2648.66, "total_tokens": 4891440} {"current_steps": 18265, "total_steps": 38150, "loss": 0.3121, "lr": 3.115452515866893e-05, "epoch": 4.787680209698558, "percentage": 47.88, "elapsed_time": "0:30:47", "remaining_time": "0:33:31", "throughput": 2648.68, "total_tokens": 4892592} {"current_steps": 18270, "total_steps": 38150, "loss": 0.2922, "lr": 3.114343922813677e-05, "epoch": 4.7889908256880735, "percentage": 47.89, "elapsed_time": "0:30:47", "remaining_time": "0:33:30", "throughput": 2648.73, "total_tokens": 4893856} {"current_steps": 18275, "total_steps": 38150, "loss": 0.3539, "lr": 3.1132352011793384e-05, "epoch": 4.790301441677588, "percentage": 47.9, "elapsed_time": "0:30:48", "remaining_time": "0:33:29", "throughput": 2648.76, "total_tokens": 4895120} {"current_steps": 18280, "total_steps": 38150, "loss": 0.3062, "lr": 3.112126351195932e-05, "epoch": 4.791612057667104, "percentage": 47.92, "elapsed_time": "0:30:48", "remaining_time": "0:33:29", "throughput": 2648.87, "total_tokens": 4896512} {"current_steps": 18285, "total_steps": 38150, "loss": 0.4392, "lr": 3.1110173730955374e-05, "epoch": 4.792922673656618, "percentage": 47.93, "elapsed_time": "0:30:48", "remaining_time": "0:33:28", "throughput": 2648.94, "total_tokens": 4897824} {"current_steps": 18290, "total_steps": 38150, "loss": 0.4336, "lr": 3.109908267110263e-05, "epoch": 4.794233289646134, "percentage": 47.94, "elapsed_time": "0:30:49", "remaining_time": "0:33:28", "throughput": 2649.04, "total_tokens": 4899184} {"current_steps": 18295, "total_steps": 38150, "loss": 0.3874, "lr": 3.108799033472242e-05, "epoch": 4.795543905635649, "percentage": 47.96, "elapsed_time": "0:30:49", "remaining_time": "0:33:27", "throughput": 2649.26, "total_tokens": 4900976} {"current_steps": 18300, "total_steps": 38150, "loss": 0.2782, "lr": 3.107689672413636e-05, "epoch": 4.796854521625164, "percentage": 47.97, "elapsed_time": "0:30:50", "remaining_time": "0:33:27", "throughput": 2649.4, "total_tokens": 4902480} {"current_steps": 18305, "total_steps": 38150, "loss": 0.2393, "lr": 3.10658018416663e-05, "epoch": 4.798165137614679, "percentage": 47.98, "elapsed_time": "0:30:50", "remaining_time": "0:33:26", "throughput": 2649.47, "total_tokens": 4903744} {"current_steps": 18310, "total_steps": 38150, "loss": 0.2647, "lr": 3.1054705689634405e-05, "epoch": 4.799475753604194, "percentage": 47.99, "elapsed_time": "0:30:51", "remaining_time": "0:33:26", "throughput": 2649.59, "total_tokens": 4905216} {"current_steps": 18315, "total_steps": 38150, "loss": 0.3005, "lr": 3.1043608270363075e-05, "epoch": 4.800786369593709, "percentage": 48.01, "elapsed_time": "0:30:51", "remaining_time": "0:33:25", "throughput": 2649.68, "total_tokens": 4906512} {"current_steps": 18320, "total_steps": 38150, "loss": 0.3023, "lr": 3.103250958617497e-05, "epoch": 4.8020969855832245, "percentage": 48.02, "elapsed_time": "0:30:52", "remaining_time": "0:33:24", "throughput": 2649.76, "total_tokens": 4907808} {"current_steps": 18325, "total_steps": 38150, "loss": 0.4699, "lr": 3.102140963939303e-05, "epoch": 4.803407601572739, "percentage": 48.03, "elapsed_time": "0:30:52", "remaining_time": "0:33:24", "throughput": 2650.04, "total_tokens": 4909728} {"current_steps": 18330, "total_steps": 38150, "loss": 0.3518, "lr": 3.101030843234046e-05, "epoch": 4.804718217562254, "percentage": 48.05, "elapsed_time": "0:30:53", "remaining_time": "0:33:23", "throughput": 2650.05, "total_tokens": 4910896} {"current_steps": 18335, "total_steps": 38150, "loss": 0.5141, "lr": 3.099920596734073e-05, "epoch": 4.806028833551769, "percentage": 48.06, "elapsed_time": "0:30:53", "remaining_time": "0:33:23", "throughput": 2650.17, "total_tokens": 4912288} {"current_steps": 18340, "total_steps": 38150, "loss": 0.2021, "lr": 3.0988102246717544e-05, "epoch": 4.807339449541285, "percentage": 48.07, "elapsed_time": "0:30:53", "remaining_time": "0:33:22", "throughput": 2650.13, "total_tokens": 4913312} {"current_steps": 18345, "total_steps": 38150, "loss": 0.2819, "lr": 3.0976997272794906e-05, "epoch": 4.8086500655307995, "percentage": 48.09, "elapsed_time": "0:30:54", "remaining_time": "0:33:22", "throughput": 2650.15, "total_tokens": 4914544} {"current_steps": 18350, "total_steps": 38150, "loss": 0.3158, "lr": 3.096589104789707e-05, "epoch": 4.809960681520314, "percentage": 48.1, "elapsed_time": "0:30:54", "remaining_time": "0:33:21", "throughput": 2650.2, "total_tokens": 4915776} {"current_steps": 18355, "total_steps": 38150, "loss": 0.481, "lr": 3.095478357434854e-05, "epoch": 4.81127129750983, "percentage": 48.11, "elapsed_time": "0:30:55", "remaining_time": "0:33:20", "throughput": 2650.24, "total_tokens": 4917008} {"current_steps": 18360, "total_steps": 38150, "loss": 0.2442, "lr": 3.09436748544741e-05, "epoch": 4.812581913499344, "percentage": 48.13, "elapsed_time": "0:30:55", "remaining_time": "0:33:20", "throughput": 2650.2, "total_tokens": 4918032} {"current_steps": 18365, "total_steps": 38150, "loss": 0.3597, "lr": 3.093256489059878e-05, "epoch": 4.81389252948886, "percentage": 48.14, "elapsed_time": "0:30:56", "remaining_time": "0:33:19", "throughput": 2650.33, "total_tokens": 4919568} {"current_steps": 18370, "total_steps": 38150, "loss": 0.3711, "lr": 3.092145368504789e-05, "epoch": 4.815203145478375, "percentage": 48.15, "elapsed_time": "0:30:56", "remaining_time": "0:33:19", "throughput": 2650.39, "total_tokens": 4920912} {"current_steps": 18375, "total_steps": 38150, "loss": 0.3503, "lr": 3.0910341240146966e-05, "epoch": 4.81651376146789, "percentage": 48.17, "elapsed_time": "0:30:57", "remaining_time": "0:33:18", "throughput": 2650.45, "total_tokens": 4922160} {"current_steps": 18380, "total_steps": 38150, "loss": 0.4129, "lr": 3.089922755822183e-05, "epoch": 4.817824377457405, "percentage": 48.18, "elapsed_time": "0:30:57", "remaining_time": "0:33:18", "throughput": 2650.53, "total_tokens": 4923472} {"current_steps": 18385, "total_steps": 38150, "loss": 0.4643, "lr": 3.088811264159856e-05, "epoch": 4.81913499344692, "percentage": 48.19, "elapsed_time": "0:30:57", "remaining_time": "0:33:17", "throughput": 2650.49, "total_tokens": 4924528} {"current_steps": 18390, "total_steps": 38150, "loss": 0.3075, "lr": 3.08769964926035e-05, "epoch": 4.820445609436435, "percentage": 48.2, "elapsed_time": "0:30:58", "remaining_time": "0:33:16", "throughput": 2650.58, "total_tokens": 4925936} {"current_steps": 18395, "total_steps": 38150, "loss": 0.4863, "lr": 3.086587911356322e-05, "epoch": 4.8217562254259505, "percentage": 48.22, "elapsed_time": "0:30:58", "remaining_time": "0:33:16", "throughput": 2650.72, "total_tokens": 4927504} {"current_steps": 18400, "total_steps": 38150, "loss": 0.3834, "lr": 3.085476050680458e-05, "epoch": 4.823066841415465, "percentage": 48.23, "elapsed_time": "0:30:59", "remaining_time": "0:33:15", "throughput": 2650.8, "total_tokens": 4928800} {"current_steps": 18405, "total_steps": 38150, "loss": 0.3166, "lr": 3.0843640674654675e-05, "epoch": 4.824377457404981, "percentage": 48.24, "elapsed_time": "0:30:59", "remaining_time": "0:33:15", "throughput": 2651.0, "total_tokens": 4930480} {"current_steps": 18410, "total_steps": 38150, "loss": 0.3434, "lr": 3.083251961944088e-05, "epoch": 4.825688073394495, "percentage": 48.26, "elapsed_time": "0:31:00", "remaining_time": "0:33:14", "throughput": 2651.13, "total_tokens": 4931904} {"current_steps": 18415, "total_steps": 38150, "loss": 0.3121, "lr": 3.08213973434908e-05, "epoch": 4.826998689384011, "percentage": 48.27, "elapsed_time": "0:31:00", "remaining_time": "0:33:14", "throughput": 2651.4, "total_tokens": 4933728} {"current_steps": 18420, "total_steps": 38150, "loss": 0.486, "lr": 3.081027384913232e-05, "epoch": 4.8283093053735255, "percentage": 48.28, "elapsed_time": "0:31:01", "remaining_time": "0:33:13", "throughput": 2651.53, "total_tokens": 4935264} {"current_steps": 18425, "total_steps": 38150, "loss": 0.415, "lr": 3.079914913869356e-05, "epoch": 4.82961992136304, "percentage": 48.3, "elapsed_time": "0:31:01", "remaining_time": "0:33:13", "throughput": 2651.66, "total_tokens": 4936736} {"current_steps": 18430, "total_steps": 38150, "loss": 0.3625, "lr": 3.0788023214502915e-05, "epoch": 4.830930537352556, "percentage": 48.31, "elapsed_time": "0:31:02", "remaining_time": "0:33:12", "throughput": 2651.87, "total_tokens": 4938448} {"current_steps": 18435, "total_steps": 38150, "loss": 0.304, "lr": 3.0776896078889e-05, "epoch": 4.832241153342071, "percentage": 48.32, "elapsed_time": "0:31:02", "remaining_time": "0:33:12", "throughput": 2651.9, "total_tokens": 4939632} {"current_steps": 18440, "total_steps": 38150, "loss": 0.3283, "lr": 3.0765767734180714e-05, "epoch": 4.833551769331586, "percentage": 48.34, "elapsed_time": "0:31:03", "remaining_time": "0:33:11", "throughput": 2651.92, "total_tokens": 4940800} {"current_steps": 18445, "total_steps": 38150, "loss": 0.3344, "lr": 3.075463818270722e-05, "epoch": 4.834862385321101, "percentage": 48.35, "elapsed_time": "0:31:03", "remaining_time": "0:33:10", "throughput": 2651.94, "total_tokens": 4942032} {"current_steps": 18450, "total_steps": 38150, "loss": 0.2534, "lr": 3.074350742679789e-05, "epoch": 4.836173001310616, "percentage": 48.36, "elapsed_time": "0:31:04", "remaining_time": "0:33:10", "throughput": 2651.97, "total_tokens": 4943312} {"current_steps": 18455, "total_steps": 38150, "loss": 0.4618, "lr": 3.0732375468782384e-05, "epoch": 4.837483617300131, "percentage": 48.37, "elapsed_time": "0:31:04", "remaining_time": "0:33:09", "throughput": 2651.98, "total_tokens": 4944448} {"current_steps": 18460, "total_steps": 38150, "loss": 0.2838, "lr": 3.072124231099058e-05, "epoch": 4.838794233289646, "percentage": 48.39, "elapsed_time": "0:31:04", "remaining_time": "0:33:09", "throughput": 2652.09, "total_tokens": 4946000} {"current_steps": 18465, "total_steps": 38150, "loss": 0.3404, "lr": 3.0710107955752664e-05, "epoch": 4.840104849279161, "percentage": 48.4, "elapsed_time": "0:31:05", "remaining_time": "0:33:08", "throughput": 2652.1, "total_tokens": 4947152} {"current_steps": 18470, "total_steps": 38150, "loss": 0.3137, "lr": 3.069897240539901e-05, "epoch": 4.8414154652686765, "percentage": 48.41, "elapsed_time": "0:31:05", "remaining_time": "0:33:08", "throughput": 2652.26, "total_tokens": 4948704} {"current_steps": 18475, "total_steps": 38150, "loss": 0.3581, "lr": 3.068783566226028e-05, "epoch": 4.842726081258191, "percentage": 48.43, "elapsed_time": "0:31:06", "remaining_time": "0:33:07", "throughput": 2652.36, "total_tokens": 4950096} {"current_steps": 18480, "total_steps": 38150, "loss": 0.4159, "lr": 3.067669772866738e-05, "epoch": 4.844036697247707, "percentage": 48.44, "elapsed_time": "0:31:06", "remaining_time": "0:33:06", "throughput": 2652.44, "total_tokens": 4951408} {"current_steps": 18485, "total_steps": 38150, "loss": 0.5554, "lr": 3.066555860695145e-05, "epoch": 4.845347313237221, "percentage": 48.45, "elapsed_time": "0:31:07", "remaining_time": "0:33:06", "throughput": 2652.35, "total_tokens": 4952352} {"current_steps": 18490, "total_steps": 38150, "loss": 0.4769, "lr": 3.065441829944389e-05, "epoch": 4.846657929226737, "percentage": 48.47, "elapsed_time": "0:31:07", "remaining_time": "0:33:05", "throughput": 2652.44, "total_tokens": 4953696} {"current_steps": 18495, "total_steps": 38150, "loss": 0.2841, "lr": 3.064327680847635e-05, "epoch": 4.8479685452162515, "percentage": 48.48, "elapsed_time": "0:31:08", "remaining_time": "0:33:05", "throughput": 2652.62, "total_tokens": 4955376} {"current_steps": 18500, "total_steps": 38150, "loss": 0.3935, "lr": 3.063213413638073e-05, "epoch": 4.849279161205767, "percentage": 48.49, "elapsed_time": "0:31:08", "remaining_time": "0:33:04", "throughput": 2652.8, "total_tokens": 4957024} {"current_steps": 18505, "total_steps": 38150, "loss": 0.4453, "lr": 3.0620990285489165e-05, "epoch": 4.850589777195282, "percentage": 48.51, "elapsed_time": "0:31:09", "remaining_time": "0:33:04", "throughput": 2652.86, "total_tokens": 4958272} {"current_steps": 18510, "total_steps": 38150, "loss": 0.391, "lr": 3.0609845258134046e-05, "epoch": 4.851900393184797, "percentage": 48.52, "elapsed_time": "0:31:09", "remaining_time": "0:33:03", "throughput": 2652.83, "total_tokens": 4959328} {"current_steps": 18515, "total_steps": 38150, "loss": 0.3196, "lr": 3.0598699056648005e-05, "epoch": 4.853211009174312, "percentage": 48.53, "elapsed_time": "0:31:09", "remaining_time": "0:33:02", "throughput": 2652.77, "total_tokens": 4960352} {"current_steps": 18520, "total_steps": 38150, "loss": 0.3225, "lr": 3.0587551683363926e-05, "epoch": 4.854521625163827, "percentage": 48.55, "elapsed_time": "0:31:10", "remaining_time": "0:33:02", "throughput": 2652.79, "total_tokens": 4961488} {"current_steps": 18525, "total_steps": 38150, "loss": 0.3457, "lr": 3.057640314061493e-05, "epoch": 4.855832241153342, "percentage": 48.56, "elapsed_time": "0:31:10", "remaining_time": "0:33:01", "throughput": 2652.89, "total_tokens": 4962816} {"current_steps": 18530, "total_steps": 38150, "loss": 0.2444, "lr": 3.05652534307344e-05, "epoch": 4.857142857142857, "percentage": 48.57, "elapsed_time": "0:31:11", "remaining_time": "0:33:01", "throughput": 2652.98, "total_tokens": 4964256} {"current_steps": 18535, "total_steps": 38150, "loss": 0.3234, "lr": 3.055410255605594e-05, "epoch": 4.858453473132372, "percentage": 48.58, "elapsed_time": "0:31:11", "remaining_time": "0:33:00", "throughput": 2653.06, "total_tokens": 4965680} {"current_steps": 18540, "total_steps": 38150, "loss": 0.3004, "lr": 3.054295051891341e-05, "epoch": 4.859764089121887, "percentage": 48.6, "elapsed_time": "0:31:12", "remaining_time": "0:33:00", "throughput": 2653.18, "total_tokens": 4967216} {"current_steps": 18545, "total_steps": 38150, "loss": 0.2402, "lr": 3.053179732164092e-05, "epoch": 4.8610747051114025, "percentage": 48.61, "elapsed_time": "0:31:12", "remaining_time": "0:32:59", "throughput": 2653.25, "total_tokens": 4968496} {"current_steps": 18550, "total_steps": 38150, "loss": 0.4042, "lr": 3.0520642966572805e-05, "epoch": 4.862385321100917, "percentage": 48.62, "elapsed_time": "0:31:13", "remaining_time": "0:32:59", "throughput": 2653.43, "total_tokens": 4970112} {"current_steps": 18555, "total_steps": 38150, "loss": 0.3714, "lr": 3.050948745604365e-05, "epoch": 4.863695937090433, "percentage": 48.64, "elapsed_time": "0:31:13", "remaining_time": "0:32:58", "throughput": 2653.54, "total_tokens": 4971568} {"current_steps": 18560, "total_steps": 38150, "loss": 0.6908, "lr": 3.049833079238829e-05, "epoch": 4.865006553079947, "percentage": 48.65, "elapsed_time": "0:31:13", "remaining_time": "0:32:57", "throughput": 2653.54, "total_tokens": 4972704} {"current_steps": 18565, "total_steps": 38150, "loss": 0.307, "lr": 3.0487172977941806e-05, "epoch": 4.866317169069463, "percentage": 48.66, "elapsed_time": "0:31:14", "remaining_time": "0:32:57", "throughput": 2653.54, "total_tokens": 4973936} {"current_steps": 18570, "total_steps": 38150, "loss": 0.3311, "lr": 3.0476014015039496e-05, "epoch": 4.8676277850589775, "percentage": 48.68, "elapsed_time": "0:31:14", "remaining_time": "0:32:56", "throughput": 2653.57, "total_tokens": 4975184} {"current_steps": 18575, "total_steps": 38150, "loss": 0.294, "lr": 3.046485390601691e-05, "epoch": 4.868938401048493, "percentage": 48.69, "elapsed_time": "0:31:15", "remaining_time": "0:32:56", "throughput": 2653.52, "total_tokens": 4976304} {"current_steps": 18580, "total_steps": 38150, "loss": 0.3968, "lr": 3.045369265320984e-05, "epoch": 4.870249017038008, "percentage": 48.7, "elapsed_time": "0:31:15", "remaining_time": "0:32:55", "throughput": 2653.63, "total_tokens": 4977696} {"current_steps": 18585, "total_steps": 38150, "loss": 0.4869, "lr": 3.0442530258954334e-05, "epoch": 4.871559633027523, "percentage": 48.72, "elapsed_time": "0:31:16", "remaining_time": "0:32:55", "throughput": 2653.82, "total_tokens": 4979360} {"current_steps": 18590, "total_steps": 38150, "loss": 0.3285, "lr": 3.0431366725586642e-05, "epoch": 4.872870249017038, "percentage": 48.73, "elapsed_time": "0:31:16", "remaining_time": "0:32:54", "throughput": 2653.85, "total_tokens": 4980656} {"current_steps": 18595, "total_steps": 38150, "loss": 0.2647, "lr": 3.0420202055443276e-05, "epoch": 4.8741808650065535, "percentage": 48.74, "elapsed_time": "0:31:17", "remaining_time": "0:32:54", "throughput": 2653.92, "total_tokens": 4981920} {"current_steps": 18600, "total_steps": 38150, "loss": 0.3432, "lr": 3.040903625086099e-05, "epoch": 4.875491480996068, "percentage": 48.75, "elapsed_time": "0:31:17", "remaining_time": "0:32:53", "throughput": 2653.93, "total_tokens": 4983136} {"current_steps": 18605, "total_steps": 38150, "loss": 0.4865, "lr": 3.0397869314176762e-05, "epoch": 4.876802096985584, "percentage": 48.77, "elapsed_time": "0:31:18", "remaining_time": "0:32:52", "throughput": 2653.94, "total_tokens": 4984304} {"current_steps": 18610, "total_steps": 38150, "loss": 0.357, "lr": 3.0386701247727807e-05, "epoch": 4.878112712975098, "percentage": 48.78, "elapsed_time": "0:31:18", "remaining_time": "0:32:52", "throughput": 2654.05, "total_tokens": 4985824} {"current_steps": 18615, "total_steps": 38150, "loss": 0.43, "lr": 3.0375532053851592e-05, "epoch": 4.879423328964613, "percentage": 48.79, "elapsed_time": "0:31:19", "remaining_time": "0:32:51", "throughput": 2654.19, "total_tokens": 4987280} {"current_steps": 18620, "total_steps": 38150, "loss": 0.215, "lr": 3.036436173488581e-05, "epoch": 4.8807339449541285, "percentage": 48.81, "elapsed_time": "0:31:19", "remaining_time": "0:32:51", "throughput": 2654.13, "total_tokens": 4988272} {"current_steps": 18625, "total_steps": 38150, "loss": 0.2061, "lr": 3.0353190293168388e-05, "epoch": 4.882044560943643, "percentage": 48.82, "elapsed_time": "0:31:19", "remaining_time": "0:32:50", "throughput": 2654.14, "total_tokens": 4989392} {"current_steps": 18630, "total_steps": 38150, "loss": 0.3957, "lr": 3.0342017731037482e-05, "epoch": 4.883355176933159, "percentage": 48.83, "elapsed_time": "0:31:20", "remaining_time": "0:32:50", "throughput": 2654.41, "total_tokens": 4991296} {"current_steps": 18635, "total_steps": 38150, "loss": 0.3974, "lr": 3.0330844050831492e-05, "epoch": 4.884665792922673, "percentage": 48.85, "elapsed_time": "0:31:20", "remaining_time": "0:32:49", "throughput": 2654.51, "total_tokens": 4992720} {"current_steps": 18640, "total_steps": 38150, "loss": 0.3904, "lr": 3.0319669254889055e-05, "epoch": 4.885976408912189, "percentage": 48.86, "elapsed_time": "0:31:21", "remaining_time": "0:32:49", "throughput": 2654.51, "total_tokens": 4993856} {"current_steps": 18645, "total_steps": 38150, "loss": 0.3117, "lr": 3.030849334554904e-05, "epoch": 4.8872870249017035, "percentage": 48.87, "elapsed_time": "0:31:21", "remaining_time": "0:32:48", "throughput": 2654.45, "total_tokens": 4994864} {"current_steps": 18650, "total_steps": 38150, "loss": 0.3014, "lr": 3.0297316325150537e-05, "epoch": 4.888597640891219, "percentage": 48.89, "elapsed_time": "0:31:22", "remaining_time": "0:32:47", "throughput": 2654.47, "total_tokens": 4996048} {"current_steps": 18655, "total_steps": 38150, "loss": 0.3714, "lr": 3.0286138196032876e-05, "epoch": 4.889908256880734, "percentage": 48.9, "elapsed_time": "0:31:22", "remaining_time": "0:32:47", "throughput": 2654.61, "total_tokens": 4997568} {"current_steps": 18660, "total_steps": 38150, "loss": 0.3924, "lr": 3.0274958960535632e-05, "epoch": 4.891218872870249, "percentage": 48.91, "elapsed_time": "0:31:23", "remaining_time": "0:32:46", "throughput": 2654.58, "total_tokens": 4998640} {"current_steps": 18665, "total_steps": 38150, "loss": 0.4742, "lr": 3.0263778620998583e-05, "epoch": 4.892529488859764, "percentage": 48.93, "elapsed_time": "0:31:23", "remaining_time": "0:32:46", "throughput": 2654.66, "total_tokens": 5000064} {"current_steps": 18670, "total_steps": 38150, "loss": 0.1828, "lr": 3.025259717976177e-05, "epoch": 4.8938401048492794, "percentage": 48.94, "elapsed_time": "0:31:23", "remaining_time": "0:32:45", "throughput": 2654.65, "total_tokens": 5001152} {"current_steps": 18675, "total_steps": 38150, "loss": 0.3156, "lr": 3.0241414639165444e-05, "epoch": 4.895150720838794, "percentage": 48.95, "elapsed_time": "0:31:24", "remaining_time": "0:32:45", "throughput": 2654.73, "total_tokens": 5002480} {"current_steps": 18680, "total_steps": 38150, "loss": 0.3453, "lr": 3.0230231001550086e-05, "epoch": 4.89646133682831, "percentage": 48.96, "elapsed_time": "0:31:24", "remaining_time": "0:32:44", "throughput": 2654.77, "total_tokens": 5003696} {"current_steps": 18685, "total_steps": 38150, "loss": 0.2739, "lr": 3.0219046269256425e-05, "epoch": 4.897771952817824, "percentage": 48.98, "elapsed_time": "0:31:25", "remaining_time": "0:32:43", "throughput": 2654.95, "total_tokens": 5005312} {"current_steps": 18690, "total_steps": 38150, "loss": 0.4178, "lr": 3.020786044462539e-05, "epoch": 4.89908256880734, "percentage": 48.99, "elapsed_time": "0:31:25", "remaining_time": "0:32:43", "throughput": 2655.03, "total_tokens": 5006688} {"current_steps": 18695, "total_steps": 38150, "loss": 0.4, "lr": 3.019667352999816e-05, "epoch": 4.9003931847968545, "percentage": 49.0, "elapsed_time": "0:31:26", "remaining_time": "0:32:42", "throughput": 2655.12, "total_tokens": 5008160} {"current_steps": 18700, "total_steps": 38150, "loss": 0.4515, "lr": 3.018548552771615e-05, "epoch": 4.90170380078637, "percentage": 49.02, "elapsed_time": "0:31:26", "remaining_time": "0:32:42", "throughput": 2655.28, "total_tokens": 5009744} {"current_steps": 18705, "total_steps": 38150, "loss": 0.2791, "lr": 3.0174296440120968e-05, "epoch": 4.903014416775885, "percentage": 49.03, "elapsed_time": "0:31:27", "remaining_time": "0:32:41", "throughput": 2655.3, "total_tokens": 5010944} {"current_steps": 18710, "total_steps": 38150, "loss": 0.4343, "lr": 3.0163106269554485e-05, "epoch": 4.904325032765399, "percentage": 49.04, "elapsed_time": "0:31:27", "remaining_time": "0:32:41", "throughput": 2655.56, "total_tokens": 5012816} {"current_steps": 18715, "total_steps": 38150, "loss": 0.3745, "lr": 3.0151915018358785e-05, "epoch": 4.905635648754915, "percentage": 49.06, "elapsed_time": "0:31:28", "remaining_time": "0:32:40", "throughput": 2655.56, "total_tokens": 5013936} {"current_steps": 18720, "total_steps": 38150, "loss": 0.3716, "lr": 3.0140722688876166e-05, "epoch": 4.9069462647444295, "percentage": 49.07, "elapsed_time": "0:31:28", "remaining_time": "0:32:40", "throughput": 2655.65, "total_tokens": 5015344} {"current_steps": 18725, "total_steps": 38150, "loss": 0.2696, "lr": 3.0129529283449177e-05, "epoch": 4.908256880733945, "percentage": 49.08, "elapsed_time": "0:31:28", "remaining_time": "0:32:39", "throughput": 2655.68, "total_tokens": 5016544} {"current_steps": 18730, "total_steps": 38150, "loss": 0.362, "lr": 3.011833480442057e-05, "epoch": 4.90956749672346, "percentage": 49.1, "elapsed_time": "0:31:29", "remaining_time": "0:32:39", "throughput": 2655.84, "total_tokens": 5018128} {"current_steps": 18735, "total_steps": 38150, "loss": 0.3926, "lr": 3.0107139254133332e-05, "epoch": 4.910878112712975, "percentage": 49.11, "elapsed_time": "0:31:29", "remaining_time": "0:32:38", "throughput": 2655.88, "total_tokens": 5019504} {"current_steps": 18740, "total_steps": 38150, "loss": 0.2918, "lr": 3.009594263493068e-05, "epoch": 4.91218872870249, "percentage": 49.12, "elapsed_time": "0:31:30", "remaining_time": "0:32:38", "throughput": 2656.05, "total_tokens": 5021040} {"current_steps": 18745, "total_steps": 38150, "loss": 0.3305, "lr": 3.008474494915603e-05, "epoch": 4.913499344692005, "percentage": 49.13, "elapsed_time": "0:31:30", "remaining_time": "0:32:37", "throughput": 2656.11, "total_tokens": 5022304} {"current_steps": 18750, "total_steps": 38150, "loss": 0.3381, "lr": 3.0073546199153053e-05, "epoch": 4.91480996068152, "percentage": 49.15, "elapsed_time": "0:31:31", "remaining_time": "0:32:36", "throughput": 2656.24, "total_tokens": 5023808} {"current_steps": 18755, "total_steps": 38150, "loss": 0.4585, "lr": 3.006234638726561e-05, "epoch": 4.916120576671036, "percentage": 49.16, "elapsed_time": "0:31:31", "remaining_time": "0:32:36", "throughput": 2656.32, "total_tokens": 5025200} {"current_steps": 18760, "total_steps": 38150, "loss": 0.3228, "lr": 3.005114551583783e-05, "epoch": 4.91743119266055, "percentage": 49.17, "elapsed_time": "0:31:32", "remaining_time": "0:32:35", "throughput": 2656.45, "total_tokens": 5026656} {"current_steps": 18765, "total_steps": 38150, "loss": 0.2871, "lr": 3.003994358721402e-05, "epoch": 4.918741808650066, "percentage": 49.19, "elapsed_time": "0:31:32", "remaining_time": "0:32:35", "throughput": 2656.37, "total_tokens": 5027616} {"current_steps": 18770, "total_steps": 38150, "loss": 0.6214, "lr": 3.002874060373872e-05, "epoch": 4.9200524246395805, "percentage": 49.2, "elapsed_time": "0:31:33", "remaining_time": "0:32:34", "throughput": 2656.63, "total_tokens": 5029584} {"current_steps": 18775, "total_steps": 38150, "loss": 0.2996, "lr": 3.0017536567756705e-05, "epoch": 4.921363040629096, "percentage": 49.21, "elapsed_time": "0:31:33", "remaining_time": "0:32:34", "throughput": 2656.62, "total_tokens": 5030672} {"current_steps": 18780, "total_steps": 38150, "loss": 0.289, "lr": 3.0006331481612955e-05, "epoch": 4.922673656618611, "percentage": 49.23, "elapsed_time": "0:31:34", "remaining_time": "0:32:33", "throughput": 2656.78, "total_tokens": 5032352} {"current_steps": 18785, "total_steps": 38150, "loss": 0.1844, "lr": 2.999512534765267e-05, "epoch": 4.923984272608125, "percentage": 49.24, "elapsed_time": "0:31:34", "remaining_time": "0:32:33", "throughput": 2656.86, "total_tokens": 5033744} {"current_steps": 18790, "total_steps": 38150, "loss": 0.3214, "lr": 2.9983918168221287e-05, "epoch": 4.925294888597641, "percentage": 49.25, "elapsed_time": "0:31:35", "remaining_time": "0:32:32", "throughput": 2656.83, "total_tokens": 5034800} {"current_steps": 18795, "total_steps": 38150, "loss": 0.3791, "lr": 2.997270994566444e-05, "epoch": 4.926605504587156, "percentage": 49.27, "elapsed_time": "0:31:35", "remaining_time": "0:32:31", "throughput": 2656.85, "total_tokens": 5035952} {"current_steps": 18800, "total_steps": 38150, "loss": 0.2657, "lr": 2.9961500682328e-05, "epoch": 4.927916120576671, "percentage": 49.28, "elapsed_time": "0:31:35", "remaining_time": "0:32:31", "throughput": 2656.84, "total_tokens": 5037088} {"current_steps": 18805, "total_steps": 38150, "loss": 0.6195, "lr": 2.995029038055804e-05, "epoch": 4.929226736566186, "percentage": 49.29, "elapsed_time": "0:31:36", "remaining_time": "0:32:30", "throughput": 2656.98, "total_tokens": 5038624} {"current_steps": 18810, "total_steps": 38150, "loss": 0.3988, "lr": 2.9939079042700847e-05, "epoch": 4.930537352555701, "percentage": 49.31, "elapsed_time": "0:31:36", "remaining_time": "0:32:30", "throughput": 2657.2, "total_tokens": 5040416} {"current_steps": 18815, "total_steps": 38150, "loss": 0.332, "lr": 2.9927866671102946e-05, "epoch": 4.931847968545216, "percentage": 49.32, "elapsed_time": "0:31:37", "remaining_time": "0:32:29", "throughput": 2657.23, "total_tokens": 5041696} {"current_steps": 18820, "total_steps": 38150, "loss": 0.2579, "lr": 2.9916653268111074e-05, "epoch": 4.933158584534731, "percentage": 49.33, "elapsed_time": "0:31:37", "remaining_time": "0:32:29", "throughput": 2657.35, "total_tokens": 5043168} {"current_steps": 18825, "total_steps": 38150, "loss": 0.4346, "lr": 2.9905438836072165e-05, "epoch": 4.934469200524246, "percentage": 49.34, "elapsed_time": "0:31:38", "remaining_time": "0:32:28", "throughput": 2657.51, "total_tokens": 5044736} {"current_steps": 18830, "total_steps": 38150, "loss": 0.4328, "lr": 2.989422337733338e-05, "epoch": 4.935779816513762, "percentage": 49.36, "elapsed_time": "0:31:38", "remaining_time": "0:32:28", "throughput": 2657.64, "total_tokens": 5046256} {"current_steps": 18835, "total_steps": 38150, "loss": 0.4867, "lr": 2.98830068942421e-05, "epoch": 4.937090432503276, "percentage": 49.37, "elapsed_time": "0:31:39", "remaining_time": "0:32:27", "throughput": 2657.67, "total_tokens": 5047536} {"current_steps": 18840, "total_steps": 38150, "loss": 0.5391, "lr": 2.987178938914591e-05, "epoch": 4.938401048492792, "percentage": 49.38, "elapsed_time": "0:31:39", "remaining_time": "0:32:27", "throughput": 2657.71, "total_tokens": 5048768} {"current_steps": 18845, "total_steps": 38150, "loss": 0.3818, "lr": 2.9860570864392625e-05, "epoch": 4.9397116644823065, "percentage": 49.4, "elapsed_time": "0:31:40", "remaining_time": "0:32:26", "throughput": 2657.65, "total_tokens": 5049760} {"current_steps": 18850, "total_steps": 38150, "loss": 0.34, "lr": 2.9849351322330255e-05, "epoch": 4.941022280471822, "percentage": 49.41, "elapsed_time": "0:31:40", "remaining_time": "0:32:25", "throughput": 2657.58, "total_tokens": 5050720} {"current_steps": 18855, "total_steps": 38150, "loss": 0.3276, "lr": 2.983813076530703e-05, "epoch": 4.942332896461337, "percentage": 49.42, "elapsed_time": "0:31:40", "remaining_time": "0:32:25", "throughput": 2657.56, "total_tokens": 5051808} {"current_steps": 18860, "total_steps": 38150, "loss": 0.156, "lr": 2.9826909195671403e-05, "epoch": 4.943643512450852, "percentage": 49.44, "elapsed_time": "0:31:41", "remaining_time": "0:32:24", "throughput": 2657.65, "total_tokens": 5053168} {"current_steps": 18865, "total_steps": 38150, "loss": 0.4453, "lr": 2.981568661577202e-05, "epoch": 4.944954128440367, "percentage": 49.45, "elapsed_time": "0:31:41", "remaining_time": "0:32:24", "throughput": 2657.68, "total_tokens": 5054368} {"current_steps": 18870, "total_steps": 38150, "loss": 0.5692, "lr": 2.9804463027957736e-05, "epoch": 4.946264744429882, "percentage": 49.46, "elapsed_time": "0:31:42", "remaining_time": "0:32:23", "throughput": 2657.73, "total_tokens": 5055600} {"current_steps": 18875, "total_steps": 38150, "loss": 0.3101, "lr": 2.9793238434577652e-05, "epoch": 4.947575360419397, "percentage": 49.48, "elapsed_time": "0:31:42", "remaining_time": "0:32:23", "throughput": 2657.8, "total_tokens": 5057040} {"current_steps": 18880, "total_steps": 38150, "loss": 0.2243, "lr": 2.978201283798105e-05, "epoch": 4.948885976408912, "percentage": 49.49, "elapsed_time": "0:31:43", "remaining_time": "0:32:22", "throughput": 2658.08, "total_tokens": 5059248} {"current_steps": 18885, "total_steps": 38150, "loss": 0.3407, "lr": 2.977078624051742e-05, "epoch": 4.950196592398427, "percentage": 49.5, "elapsed_time": "0:31:43", "remaining_time": "0:32:22", "throughput": 2658.19, "total_tokens": 5060640} {"current_steps": 18890, "total_steps": 38150, "loss": 0.3933, "lr": 2.9759558644536467e-05, "epoch": 4.951507208387943, "percentage": 49.52, "elapsed_time": "0:31:44", "remaining_time": "0:32:21", "throughput": 2658.31, "total_tokens": 5062032} {"current_steps": 18895, "total_steps": 38150, "loss": 0.3363, "lr": 2.9748330052388117e-05, "epoch": 4.952817824377457, "percentage": 49.53, "elapsed_time": "0:31:44", "remaining_time": "0:32:20", "throughput": 2658.39, "total_tokens": 5063424} {"current_steps": 18900, "total_steps": 38150, "loss": 0.3541, "lr": 2.9737100466422498e-05, "epoch": 4.954128440366972, "percentage": 49.54, "elapsed_time": "0:31:45", "remaining_time": "0:32:20", "throughput": 2658.3, "total_tokens": 5064384} {"current_steps": 18905, "total_steps": 38150, "loss": 0.2861, "lr": 2.9725869888989926e-05, "epoch": 4.955439056356488, "percentage": 49.55, "elapsed_time": "0:31:45", "remaining_time": "0:32:19", "throughput": 2658.39, "total_tokens": 5065728} {"current_steps": 18910, "total_steps": 38150, "loss": 0.2758, "lr": 2.9714638322440956e-05, "epoch": 4.956749672346002, "percentage": 49.57, "elapsed_time": "0:31:46", "remaining_time": "0:32:19", "throughput": 2658.55, "total_tokens": 5067408} {"current_steps": 18915, "total_steps": 38150, "loss": 0.3925, "lr": 2.9703405769126334e-05, "epoch": 4.958060288335518, "percentage": 49.58, "elapsed_time": "0:31:46", "remaining_time": "0:32:18", "throughput": 2658.57, "total_tokens": 5068592} {"current_steps": 18920, "total_steps": 38150, "loss": 0.4236, "lr": 2.969217223139702e-05, "epoch": 4.9593709043250325, "percentage": 49.59, "elapsed_time": "0:31:47", "remaining_time": "0:32:18", "throughput": 2658.74, "total_tokens": 5070224} {"current_steps": 18925, "total_steps": 38150, "loss": 0.3271, "lr": 2.9680937711604146e-05, "epoch": 4.960681520314548, "percentage": 49.61, "elapsed_time": "0:31:47", "remaining_time": "0:32:17", "throughput": 2658.78, "total_tokens": 5071424} {"current_steps": 18930, "total_steps": 38150, "loss": 0.2606, "lr": 2.9669702212099104e-05, "epoch": 4.961992136304063, "percentage": 49.62, "elapsed_time": "0:31:47", "remaining_time": "0:32:17", "throughput": 2658.89, "total_tokens": 5072880} {"current_steps": 18935, "total_steps": 38150, "loss": 0.3071, "lr": 2.9658465735233467e-05, "epoch": 4.963302752293578, "percentage": 49.63, "elapsed_time": "0:31:48", "remaining_time": "0:32:16", "throughput": 2658.94, "total_tokens": 5074128} {"current_steps": 18940, "total_steps": 38150, "loss": 0.4616, "lr": 2.9647228283358995e-05, "epoch": 4.964613368283093, "percentage": 49.65, "elapsed_time": "0:31:48", "remaining_time": "0:32:15", "throughput": 2658.92, "total_tokens": 5075216} {"current_steps": 18945, "total_steps": 38150, "loss": 0.5076, "lr": 2.9635989858827673e-05, "epoch": 4.965923984272608, "percentage": 49.66, "elapsed_time": "0:31:49", "remaining_time": "0:32:15", "throughput": 2658.89, "total_tokens": 5076368} {"current_steps": 18950, "total_steps": 38150, "loss": 0.5347, "lr": 2.962475046399168e-05, "epoch": 4.967234600262123, "percentage": 49.67, "elapsed_time": "0:31:49", "remaining_time": "0:32:14", "throughput": 2658.97, "total_tokens": 5077760} {"current_steps": 18955, "total_steps": 38150, "loss": 0.3721, "lr": 2.9613510101203406e-05, "epoch": 4.968545216251639, "percentage": 49.69, "elapsed_time": "0:31:50", "remaining_time": "0:32:14", "throughput": 2659.21, "total_tokens": 5079728} {"current_steps": 18960, "total_steps": 38150, "loss": 0.3223, "lr": 2.9602268772815445e-05, "epoch": 4.969855832241153, "percentage": 49.7, "elapsed_time": "0:31:50", "remaining_time": "0:32:13", "throughput": 2659.31, "total_tokens": 5081232} {"current_steps": 18965, "total_steps": 38150, "loss": 0.5195, "lr": 2.959102648118058e-05, "epoch": 4.971166448230669, "percentage": 49.71, "elapsed_time": "0:31:51", "remaining_time": "0:32:13", "throughput": 2659.4, "total_tokens": 5082672} {"current_steps": 18970, "total_steps": 38150, "loss": 0.4022, "lr": 2.9579783228651802e-05, "epoch": 4.972477064220183, "percentage": 49.72, "elapsed_time": "0:31:51", "remaining_time": "0:32:12", "throughput": 2659.4, "total_tokens": 5083824} {"current_steps": 18975, "total_steps": 38150, "loss": 0.2929, "lr": 2.956853901758231e-05, "epoch": 4.973787680209698, "percentage": 49.74, "elapsed_time": "0:31:52", "remaining_time": "0:32:12", "throughput": 2659.38, "total_tokens": 5084912} {"current_steps": 18980, "total_steps": 38150, "loss": 0.3432, "lr": 2.9557293850325496e-05, "epoch": 4.975098296199214, "percentage": 49.75, "elapsed_time": "0:31:52", "remaining_time": "0:32:11", "throughput": 2659.52, "total_tokens": 5086528} {"current_steps": 18985, "total_steps": 38150, "loss": 0.2623, "lr": 2.954604772923495e-05, "epoch": 4.976408912188729, "percentage": 49.76, "elapsed_time": "0:31:53", "remaining_time": "0:32:11", "throughput": 2659.62, "total_tokens": 5087856} {"current_steps": 18990, "total_steps": 38150, "loss": 0.3802, "lr": 2.9534800656664468e-05, "epoch": 4.977719528178244, "percentage": 49.78, "elapsed_time": "0:31:53", "remaining_time": "0:32:10", "throughput": 2659.76, "total_tokens": 5089328} {"current_steps": 18995, "total_steps": 38150, "loss": 0.2767, "lr": 2.9523552634968056e-05, "epoch": 4.9790301441677585, "percentage": 49.79, "elapsed_time": "0:31:53", "remaining_time": "0:32:10", "throughput": 2659.72, "total_tokens": 5090400} {"current_steps": 19000, "total_steps": 38150, "loss": 0.2871, "lr": 2.9512303666499886e-05, "epoch": 4.980340760157274, "percentage": 49.8, "elapsed_time": "0:31:54", "remaining_time": "0:32:09", "throughput": 2659.85, "total_tokens": 5091984} {"current_steps": 19005, "total_steps": 38150, "loss": 0.3018, "lr": 2.9501053753614354e-05, "epoch": 4.981651376146789, "percentage": 49.82, "elapsed_time": "0:31:54", "remaining_time": "0:32:08", "throughput": 2659.95, "total_tokens": 5093424} {"current_steps": 19010, "total_steps": 38150, "loss": 0.3059, "lr": 2.9489802898666042e-05, "epoch": 4.982961992136304, "percentage": 49.83, "elapsed_time": "0:31:55", "remaining_time": "0:32:08", "throughput": 2660.02, "total_tokens": 5094752} {"current_steps": 19015, "total_steps": 38150, "loss": 0.3256, "lr": 2.9478551104009756e-05, "epoch": 4.984272608125819, "percentage": 49.84, "elapsed_time": "0:31:55", "remaining_time": "0:32:07", "throughput": 2660.13, "total_tokens": 5096240} {"current_steps": 19020, "total_steps": 38150, "loss": 0.2486, "lr": 2.946729837200045e-05, "epoch": 4.985583224115334, "percentage": 49.86, "elapsed_time": "0:31:56", "remaining_time": "0:32:07", "throughput": 2660.37, "total_tokens": 5098176} {"current_steps": 19025, "total_steps": 38150, "loss": 0.3634, "lr": 2.945604470499332e-05, "epoch": 4.986893840104849, "percentage": 49.87, "elapsed_time": "0:31:56", "remaining_time": "0:32:06", "throughput": 2660.44, "total_tokens": 5099520} {"current_steps": 19030, "total_steps": 38150, "loss": 0.3849, "lr": 2.9444790105343735e-05, "epoch": 4.988204456094365, "percentage": 49.88, "elapsed_time": "0:31:57", "remaining_time": "0:32:06", "throughput": 2660.46, "total_tokens": 5100688} {"current_steps": 19035, "total_steps": 38150, "loss": 0.3329, "lr": 2.9433534575407257e-05, "epoch": 4.989515072083879, "percentage": 49.9, "elapsed_time": "0:31:57", "remaining_time": "0:32:05", "throughput": 2660.49, "total_tokens": 5101888} {"current_steps": 19040, "total_steps": 38150, "loss": 0.3658, "lr": 2.942227811753965e-05, "epoch": 4.990825688073395, "percentage": 49.91, "elapsed_time": "0:31:58", "remaining_time": "0:32:05", "throughput": 2660.59, "total_tokens": 5103264} {"current_steps": 19045, "total_steps": 38150, "loss": 0.3754, "lr": 2.9411020734096874e-05, "epoch": 4.992136304062909, "percentage": 49.92, "elapsed_time": "0:31:58", "remaining_time": "0:32:04", "throughput": 2660.79, "total_tokens": 5104976} {"current_steps": 19050, "total_steps": 38150, "loss": 0.3137, "lr": 2.9399762427435084e-05, "epoch": 4.993446920052425, "percentage": 49.93, "elapsed_time": "0:31:59", "remaining_time": "0:32:04", "throughput": 2660.84, "total_tokens": 5106320} {"current_steps": 19055, "total_steps": 38150, "loss": 0.3961, "lr": 2.938850319991062e-05, "epoch": 4.99475753604194, "percentage": 49.95, "elapsed_time": "0:31:59", "remaining_time": "0:32:03", "throughput": 2660.93, "total_tokens": 5107744} {"current_steps": 19060, "total_steps": 38150, "loss": 0.2818, "lr": 2.937724305388002e-05, "epoch": 4.996068152031455, "percentage": 49.96, "elapsed_time": "0:31:59", "remaining_time": "0:32:03", "throughput": 2661.01, "total_tokens": 5109136} {"current_steps": 19065, "total_steps": 38150, "loss": 0.2861, "lr": 2.936598199170001e-05, "epoch": 4.99737876802097, "percentage": 49.97, "elapsed_time": "0:32:00", "remaining_time": "0:32:02", "throughput": 2661.1, "total_tokens": 5110544} {"current_steps": 19070, "total_steps": 38150, "loss": 0.4953, "lr": 2.9354720015727515e-05, "epoch": 4.9986893840104845, "percentage": 49.99, "elapsed_time": "0:32:00", "remaining_time": "0:32:01", "throughput": 2661.11, "total_tokens": 5111680} {"current_steps": 19075, "total_steps": 38150, "loss": 0.2838, "lr": 2.934345712831964e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:32:01", "remaining_time": "0:32:01", "throughput": 2661.09, "total_tokens": 5113312} {"current_steps": 19080, "total_steps": 38150, "loss": 0.3007, "lr": 2.9332193331833696e-05, "epoch": 5.001310615989515, "percentage": 50.01, "elapsed_time": "0:32:02", "remaining_time": "0:32:01", "throughput": 2660.98, "total_tokens": 5114800} {"current_steps": 19080, "total_steps": 38150, "eval_loss": 0.5386644601821899, "epoch": 5.001310615989515, "percentage": 50.01, "elapsed_time": "0:32:19", "remaining_time": "0:32:18", "throughput": 2637.83, "total_tokens": 5114800} {"current_steps": 19085, "total_steps": 38150, "loss": 0.2386, "lr": 2.9320928628627175e-05, "epoch": 5.00262123197903, "percentage": 50.03, "elapsed_time": "0:32:20", "remaining_time": "0:32:18", "throughput": 2635.93, "total_tokens": 5116176} {"current_steps": 19090, "total_steps": 38150, "loss": 0.2779, "lr": 2.9309663021057754e-05, "epoch": 5.003931847968545, "percentage": 50.04, "elapsed_time": "0:32:21", "remaining_time": "0:32:18", "throughput": 2636.13, "total_tokens": 5117904} {"current_steps": 19095, "total_steps": 38150, "loss": 0.2941, "lr": 2.929839651148331e-05, "epoch": 5.00524246395806, "percentage": 50.05, "elapsed_time": "0:32:21", "remaining_time": "0:32:17", "throughput": 2636.27, "total_tokens": 5119520} {"current_steps": 19100, "total_steps": 38150, "loss": 0.2932, "lr": 2.9287129102261907e-05, "epoch": 5.006553079947575, "percentage": 50.07, "elapsed_time": "0:32:22", "remaining_time": "0:32:17", "throughput": 2636.29, "total_tokens": 5120688} {"current_steps": 19105, "total_steps": 38150, "loss": 0.4253, "lr": 2.9275860795751786e-05, "epoch": 5.007863695937091, "percentage": 50.08, "elapsed_time": "0:32:22", "remaining_time": "0:32:16", "throughput": 2636.32, "total_tokens": 5121936} {"current_steps": 19110, "total_steps": 38150, "loss": 0.2895, "lr": 2.926459159431139e-05, "epoch": 5.009174311926605, "percentage": 50.09, "elapsed_time": "0:32:23", "remaining_time": "0:32:16", "throughput": 2636.23, "total_tokens": 5122896} {"current_steps": 19115, "total_steps": 38150, "loss": 0.4112, "lr": 2.9253321500299354e-05, "epoch": 5.010484927916121, "percentage": 50.1, "elapsed_time": "0:32:23", "remaining_time": "0:32:15", "throughput": 2636.31, "total_tokens": 5124256} {"current_steps": 19120, "total_steps": 38150, "loss": 0.3948, "lr": 2.9242050516074466e-05, "epoch": 5.011795543905635, "percentage": 50.12, "elapsed_time": "0:32:24", "remaining_time": "0:32:15", "throughput": 2636.44, "total_tokens": 5125696} {"current_steps": 19125, "total_steps": 38150, "loss": 0.36, "lr": 2.9230778643995726e-05, "epoch": 5.013106159895151, "percentage": 50.13, "elapsed_time": "0:32:24", "remaining_time": "0:32:14", "throughput": 2636.5, "total_tokens": 5126960} {"current_steps": 19130, "total_steps": 38150, "loss": 0.3353, "lr": 2.9219505886422338e-05, "epoch": 5.014416775884666, "percentage": 50.14, "elapsed_time": "0:32:25", "remaining_time": "0:32:13", "throughput": 2636.58, "total_tokens": 5128336} {"current_steps": 19135, "total_steps": 38150, "loss": 0.4492, "lr": 2.9208232245713657e-05, "epoch": 5.015727391874181, "percentage": 50.16, "elapsed_time": "0:32:25", "remaining_time": "0:32:13", "throughput": 2636.75, "total_tokens": 5129984} {"current_steps": 19140, "total_steps": 38150, "loss": 0.2318, "lr": 2.9196957724229234e-05, "epoch": 5.017038007863696, "percentage": 50.17, "elapsed_time": "0:32:26", "remaining_time": "0:32:12", "throughput": 2636.75, "total_tokens": 5131120} {"current_steps": 19145, "total_steps": 38150, "loss": 0.2438, "lr": 2.9185682324328815e-05, "epoch": 5.018348623853211, "percentage": 50.18, "elapsed_time": "0:32:26", "remaining_time": "0:32:12", "throughput": 2636.77, "total_tokens": 5132352} {"current_steps": 19150, "total_steps": 38150, "loss": 0.6217, "lr": 2.9174406048372316e-05, "epoch": 5.019659239842726, "percentage": 50.2, "elapsed_time": "0:32:26", "remaining_time": "0:32:11", "throughput": 2636.96, "total_tokens": 5134048} {"current_steps": 19155, "total_steps": 38150, "loss": 0.2995, "lr": 2.9163128898719845e-05, "epoch": 5.0209698558322415, "percentage": 50.21, "elapsed_time": "0:32:27", "remaining_time": "0:32:11", "throughput": 2637.1, "total_tokens": 5135600} {"current_steps": 19160, "total_steps": 38150, "loss": 0.2953, "lr": 2.915185087773169e-05, "epoch": 5.022280471821756, "percentage": 50.22, "elapsed_time": "0:32:27", "remaining_time": "0:32:10", "throughput": 2637.12, "total_tokens": 5136784} {"current_steps": 19165, "total_steps": 38150, "loss": 0.3484, "lr": 2.9140571987768316e-05, "epoch": 5.023591087811272, "percentage": 50.24, "elapsed_time": "0:32:28", "remaining_time": "0:32:10", "throughput": 2637.33, "total_tokens": 5138656} {"current_steps": 19170, "total_steps": 38150, "loss": 0.2587, "lr": 2.9129292231190386e-05, "epoch": 5.024901703800786, "percentage": 50.25, "elapsed_time": "0:32:28", "remaining_time": "0:32:09", "throughput": 2637.5, "total_tokens": 5140256} {"current_steps": 19175, "total_steps": 38150, "loss": 0.3163, "lr": 2.9118011610358726e-05, "epoch": 5.026212319790301, "percentage": 50.26, "elapsed_time": "0:32:29", "remaining_time": "0:32:09", "throughput": 2637.61, "total_tokens": 5141648} {"current_steps": 19180, "total_steps": 38150, "loss": 0.3443, "lr": 2.9106730127634346e-05, "epoch": 5.027522935779817, "percentage": 50.28, "elapsed_time": "0:32:29", "remaining_time": "0:32:08", "throughput": 2637.64, "total_tokens": 5142848} {"current_steps": 19185, "total_steps": 38150, "loss": 0.2466, "lr": 2.9095447785378443e-05, "epoch": 5.028833551769331, "percentage": 50.29, "elapsed_time": "0:32:30", "remaining_time": "0:32:07", "throughput": 2637.7, "total_tokens": 5144128} {"current_steps": 19190, "total_steps": 38150, "loss": 0.1388, "lr": 2.9084164585952405e-05, "epoch": 5.030144167758847, "percentage": 50.3, "elapsed_time": "0:32:30", "remaining_time": "0:32:07", "throughput": 2637.84, "total_tokens": 5145808} {"current_steps": 19195, "total_steps": 38150, "loss": 0.1952, "lr": 2.9072880531717773e-05, "epoch": 5.031454783748361, "percentage": 50.31, "elapsed_time": "0:32:31", "remaining_time": "0:32:06", "throughput": 2638.09, "total_tokens": 5147728} {"current_steps": 19200, "total_steps": 38150, "loss": 0.2951, "lr": 2.9061595625036277e-05, "epoch": 5.032765399737877, "percentage": 50.33, "elapsed_time": "0:32:31", "remaining_time": "0:32:06", "throughput": 2638.21, "total_tokens": 5149200} {"current_steps": 19205, "total_steps": 38150, "loss": 0.3132, "lr": 2.905030986826984e-05, "epoch": 5.034076015727392, "percentage": 50.34, "elapsed_time": "0:32:32", "remaining_time": "0:32:05", "throughput": 2638.21, "total_tokens": 5150336} {"current_steps": 19210, "total_steps": 38150, "loss": 0.1629, "lr": 2.903902326378054e-05, "epoch": 5.035386631716907, "percentage": 50.35, "elapsed_time": "0:32:32", "remaining_time": "0:32:05", "throughput": 2638.17, "total_tokens": 5151344} {"current_steps": 19215, "total_steps": 38150, "loss": 0.2407, "lr": 2.9027735813930658e-05, "epoch": 5.036697247706422, "percentage": 50.37, "elapsed_time": "0:32:33", "remaining_time": "0:32:04", "throughput": 2638.31, "total_tokens": 5152944} {"current_steps": 19220, "total_steps": 38150, "loss": 0.4713, "lr": 2.9016447521082625e-05, "epoch": 5.038007863695937, "percentage": 50.38, "elapsed_time": "0:32:33", "remaining_time": "0:32:04", "throughput": 2638.42, "total_tokens": 5154384} {"current_steps": 19225, "total_steps": 38150, "loss": 0.2443, "lr": 2.9005158387599068e-05, "epoch": 5.039318479685452, "percentage": 50.39, "elapsed_time": "0:32:34", "remaining_time": "0:32:03", "throughput": 2638.45, "total_tokens": 5155632} {"current_steps": 19230, "total_steps": 38150, "loss": 0.5856, "lr": 2.8993868415842785e-05, "epoch": 5.0406290956749675, "percentage": 50.41, "elapsed_time": "0:32:34", "remaining_time": "0:32:02", "throughput": 2638.51, "total_tokens": 5156992} {"current_steps": 19235, "total_steps": 38150, "loss": 0.2811, "lr": 2.8982577608176737e-05, "epoch": 5.041939711664482, "percentage": 50.42, "elapsed_time": "0:32:34", "remaining_time": "0:32:02", "throughput": 2638.64, "total_tokens": 5158528} {"current_steps": 19240, "total_steps": 38150, "loss": 0.3627, "lr": 2.8971285966964075e-05, "epoch": 5.043250327653998, "percentage": 50.43, "elapsed_time": "0:32:35", "remaining_time": "0:32:01", "throughput": 2638.81, "total_tokens": 5160208} {"current_steps": 19245, "total_steps": 38150, "loss": 0.3247, "lr": 2.8959993494568123e-05, "epoch": 5.044560943643512, "percentage": 50.45, "elapsed_time": "0:32:35", "remaining_time": "0:32:01", "throughput": 2638.87, "total_tokens": 5161536} {"current_steps": 19250, "total_steps": 38150, "loss": 0.346, "lr": 2.894870019335238e-05, "epoch": 5.045871559633028, "percentage": 50.46, "elapsed_time": "0:32:36", "remaining_time": "0:32:01", "throughput": 2639.36, "total_tokens": 5164688} {"current_steps": 19255, "total_steps": 38150, "loss": 0.3088, "lr": 2.8937406065680505e-05, "epoch": 5.047182175622543, "percentage": 50.47, "elapsed_time": "0:32:37", "remaining_time": "0:32:00", "throughput": 2639.51, "total_tokens": 5166160} {"current_steps": 19260, "total_steps": 38150, "loss": 0.2715, "lr": 2.8926111113916344e-05, "epoch": 5.048492791612058, "percentage": 50.48, "elapsed_time": "0:32:37", "remaining_time": "0:32:00", "throughput": 2639.49, "total_tokens": 5167232} {"current_steps": 19265, "total_steps": 38150, "loss": 0.3304, "lr": 2.891481534042391e-05, "epoch": 5.049803407601573, "percentage": 50.5, "elapsed_time": "0:32:38", "remaining_time": "0:31:59", "throughput": 2639.45, "total_tokens": 5168288} {"current_steps": 19270, "total_steps": 38150, "loss": 0.2436, "lr": 2.8903518747567394e-05, "epoch": 5.051114023591087, "percentage": 50.51, "elapsed_time": "0:32:38", "remaining_time": "0:31:58", "throughput": 2639.42, "total_tokens": 5169344} {"current_steps": 19275, "total_steps": 38150, "loss": 0.2384, "lr": 2.8892221337711143e-05, "epoch": 5.052424639580603, "percentage": 50.52, "elapsed_time": "0:32:38", "remaining_time": "0:31:58", "throughput": 2639.35, "total_tokens": 5170288} {"current_steps": 19280, "total_steps": 38150, "loss": 0.2975, "lr": 2.88809231132197e-05, "epoch": 5.053735255570118, "percentage": 50.54, "elapsed_time": "0:32:39", "remaining_time": "0:31:57", "throughput": 2639.41, "total_tokens": 5171568} {"current_steps": 19285, "total_steps": 38150, "loss": 0.2971, "lr": 2.8869624076457745e-05, "epoch": 5.055045871559633, "percentage": 50.55, "elapsed_time": "0:32:39", "remaining_time": "0:31:57", "throughput": 2639.47, "total_tokens": 5172832} {"current_steps": 19290, "total_steps": 38150, "loss": 0.3247, "lr": 2.885832422979017e-05, "epoch": 5.056356487549148, "percentage": 50.56, "elapsed_time": "0:32:40", "remaining_time": "0:31:56", "throughput": 2639.64, "total_tokens": 5174400} {"current_steps": 19295, "total_steps": 38150, "loss": 0.2534, "lr": 2.8847023575581988e-05, "epoch": 5.057667103538663, "percentage": 50.58, "elapsed_time": "0:32:40", "remaining_time": "0:31:55", "throughput": 2639.61, "total_tokens": 5175456} {"current_steps": 19300, "total_steps": 38150, "loss": 0.2731, "lr": 2.8835722116198415e-05, "epoch": 5.058977719528178, "percentage": 50.59, "elapsed_time": "0:32:41", "remaining_time": "0:31:55", "throughput": 2639.65, "total_tokens": 5176672} {"current_steps": 19305, "total_steps": 38150, "loss": 0.2198, "lr": 2.882441985400484e-05, "epoch": 5.0602883355176935, "percentage": 50.6, "elapsed_time": "0:32:41", "remaining_time": "0:31:54", "throughput": 2639.62, "total_tokens": 5177728} {"current_steps": 19310, "total_steps": 38150, "loss": 0.318, "lr": 2.88131167913668e-05, "epoch": 5.061598951507208, "percentage": 50.62, "elapsed_time": "0:32:41", "remaining_time": "0:31:54", "throughput": 2639.68, "total_tokens": 5178992} {"current_steps": 19315, "total_steps": 38150, "loss": 0.21, "lr": 2.8801812930650002e-05, "epoch": 5.062909567496724, "percentage": 50.63, "elapsed_time": "0:32:42", "remaining_time": "0:31:53", "throughput": 2639.92, "total_tokens": 5180832} {"current_steps": 19320, "total_steps": 38150, "loss": 0.5233, "lr": 2.8790508274220323e-05, "epoch": 5.064220183486238, "percentage": 50.64, "elapsed_time": "0:32:42", "remaining_time": "0:31:53", "throughput": 2639.98, "total_tokens": 5182176} {"current_steps": 19325, "total_steps": 38150, "loss": 0.3461, "lr": 2.877920282444381e-05, "epoch": 5.065530799475754, "percentage": 50.66, "elapsed_time": "0:32:43", "remaining_time": "0:31:52", "throughput": 2640.03, "total_tokens": 5183424} {"current_steps": 19330, "total_steps": 38150, "loss": 0.5208, "lr": 2.8767896583686682e-05, "epoch": 5.066841415465269, "percentage": 50.67, "elapsed_time": "0:32:43", "remaining_time": "0:31:52", "throughput": 2640.16, "total_tokens": 5184912} {"current_steps": 19335, "total_steps": 38150, "loss": 0.2582, "lr": 2.875658955431531e-05, "epoch": 5.068152031454784, "percentage": 50.68, "elapsed_time": "0:32:44", "remaining_time": "0:31:51", "throughput": 2640.33, "total_tokens": 5186512} {"current_steps": 19340, "total_steps": 38150, "loss": 0.203, "lr": 2.874528173869623e-05, "epoch": 5.069462647444299, "percentage": 50.69, "elapsed_time": "0:32:44", "remaining_time": "0:31:50", "throughput": 2640.44, "total_tokens": 5187984} {"current_steps": 19345, "total_steps": 38150, "loss": 0.2126, "lr": 2.873397313919616e-05, "epoch": 5.070773263433814, "percentage": 50.71, "elapsed_time": "0:32:45", "remaining_time": "0:31:50", "throughput": 2640.53, "total_tokens": 5189296} {"current_steps": 19350, "total_steps": 38150, "loss": 0.2555, "lr": 2.872266375818196e-05, "epoch": 5.072083879423329, "percentage": 50.72, "elapsed_time": "0:32:45", "remaining_time": "0:31:49", "throughput": 2640.5, "total_tokens": 5190400} {"current_steps": 19355, "total_steps": 38150, "loss": 0.2271, "lr": 2.8711353598020662e-05, "epoch": 5.073394495412844, "percentage": 50.73, "elapsed_time": "0:32:46", "remaining_time": "0:31:49", "throughput": 2640.45, "total_tokens": 5191408} {"current_steps": 19360, "total_steps": 38150, "loss": 0.2076, "lr": 2.8700042661079472e-05, "epoch": 5.074705111402359, "percentage": 50.75, "elapsed_time": "0:32:46", "remaining_time": "0:31:48", "throughput": 2640.47, "total_tokens": 5192672} {"current_steps": 19365, "total_steps": 38150, "loss": 0.2966, "lr": 2.8688730949725752e-05, "epoch": 5.076015727391874, "percentage": 50.76, "elapsed_time": "0:32:47", "remaining_time": "0:31:48", "throughput": 2640.61, "total_tokens": 5194112} {"current_steps": 19370, "total_steps": 38150, "loss": 0.236, "lr": 2.867741846632701e-05, "epoch": 5.077326343381389, "percentage": 50.77, "elapsed_time": "0:32:47", "remaining_time": "0:31:47", "throughput": 2640.61, "total_tokens": 5195264} {"current_steps": 19375, "total_steps": 38150, "loss": 0.2667, "lr": 2.8666105213250943e-05, "epoch": 5.078636959370904, "percentage": 50.79, "elapsed_time": "0:32:47", "remaining_time": "0:31:47", "throughput": 2640.82, "total_tokens": 5197040} {"current_steps": 19380, "total_steps": 38150, "loss": 0.2732, "lr": 2.8654791192865388e-05, "epoch": 5.0799475753604195, "percentage": 50.8, "elapsed_time": "0:32:48", "remaining_time": "0:31:46", "throughput": 2640.8, "total_tokens": 5198160} {"current_steps": 19385, "total_steps": 38150, "loss": 0.3355, "lr": 2.864347640753835e-05, "epoch": 5.081258191349934, "percentage": 50.81, "elapsed_time": "0:32:48", "remaining_time": "0:31:45", "throughput": 2640.73, "total_tokens": 5199120} {"current_steps": 19390, "total_steps": 38150, "loss": 0.3042, "lr": 2.8632160859637998e-05, "epoch": 5.08256880733945, "percentage": 50.83, "elapsed_time": "0:32:49", "remaining_time": "0:31:45", "throughput": 2640.8, "total_tokens": 5200544} {"current_steps": 19395, "total_steps": 38150, "loss": 0.2937, "lr": 2.8620844551532648e-05, "epoch": 5.083879423328964, "percentage": 50.84, "elapsed_time": "0:32:49", "remaining_time": "0:31:44", "throughput": 2640.85, "total_tokens": 5201840} {"current_steps": 19400, "total_steps": 38150, "loss": 0.2928, "lr": 2.8609527485590794e-05, "epoch": 5.08519003931848, "percentage": 50.85, "elapsed_time": "0:32:50", "remaining_time": "0:31:44", "throughput": 2640.88, "total_tokens": 5203104} {"current_steps": 19405, "total_steps": 38150, "loss": 0.3621, "lr": 2.8598209664181073e-05, "epoch": 5.086500655307995, "percentage": 50.87, "elapsed_time": "0:32:50", "remaining_time": "0:31:43", "throughput": 2640.93, "total_tokens": 5204352} {"current_steps": 19410, "total_steps": 38150, "loss": 0.216, "lr": 2.858689108967229e-05, "epoch": 5.08781127129751, "percentage": 50.88, "elapsed_time": "0:32:51", "remaining_time": "0:31:43", "throughput": 2641.07, "total_tokens": 5205920} {"current_steps": 19415, "total_steps": 38150, "loss": 0.3812, "lr": 2.8575571764433396e-05, "epoch": 5.089121887287025, "percentage": 50.89, "elapsed_time": "0:32:51", "remaining_time": "0:31:42", "throughput": 2641.04, "total_tokens": 5206992} {"current_steps": 19420, "total_steps": 38150, "loss": 0.3056, "lr": 2.8564251690833505e-05, "epoch": 5.09043250327654, "percentage": 50.9, "elapsed_time": "0:32:52", "remaining_time": "0:31:41", "throughput": 2641.12, "total_tokens": 5208400} {"current_steps": 19425, "total_steps": 38150, "loss": 0.4112, "lr": 2.8552930871241906e-05, "epoch": 5.091743119266055, "percentage": 50.92, "elapsed_time": "0:32:52", "remaining_time": "0:31:41", "throughput": 2641.19, "total_tokens": 5209680} {"current_steps": 19430, "total_steps": 38150, "loss": 0.384, "lr": 2.8541609308028006e-05, "epoch": 5.0930537352555705, "percentage": 50.93, "elapsed_time": "0:32:52", "remaining_time": "0:31:40", "throughput": 2641.2, "total_tokens": 5210832} {"current_steps": 19435, "total_steps": 38150, "loss": 0.2313, "lr": 2.8530287003561402e-05, "epoch": 5.094364351245085, "percentage": 50.94, "elapsed_time": "0:32:53", "remaining_time": "0:31:40", "throughput": 2641.28, "total_tokens": 5212160} {"current_steps": 19440, "total_steps": 38150, "loss": 0.3362, "lr": 2.8518963960211814e-05, "epoch": 5.095674967234601, "percentage": 50.96, "elapsed_time": "0:32:53", "remaining_time": "0:31:39", "throughput": 2641.42, "total_tokens": 5213728} {"current_steps": 19445, "total_steps": 38150, "loss": 0.34, "lr": 2.850764018034917e-05, "epoch": 5.096985583224115, "percentage": 50.97, "elapsed_time": "0:32:54", "remaining_time": "0:31:39", "throughput": 2641.68, "total_tokens": 5215536} {"current_steps": 19450, "total_steps": 38150, "loss": 0.2683, "lr": 2.8496315666343487e-05, "epoch": 5.09829619921363, "percentage": 50.98, "elapsed_time": "0:32:54", "remaining_time": "0:31:38", "throughput": 2641.68, "total_tokens": 5216704} {"current_steps": 19455, "total_steps": 38150, "loss": 0.2494, "lr": 2.8484990420564972e-05, "epoch": 5.0996068152031455, "percentage": 51.0, "elapsed_time": "0:32:55", "remaining_time": "0:31:38", "throughput": 2641.73, "total_tokens": 5218016} {"current_steps": 19460, "total_steps": 38150, "loss": 0.24, "lr": 2.847366444538399e-05, "epoch": 5.10091743119266, "percentage": 51.01, "elapsed_time": "0:32:55", "remaining_time": "0:31:37", "throughput": 2641.65, "total_tokens": 5218960} {"current_steps": 19465, "total_steps": 38150, "loss": 0.3195, "lr": 2.8462337743171046e-05, "epoch": 5.102228047182176, "percentage": 51.02, "elapsed_time": "0:32:56", "remaining_time": "0:31:36", "throughput": 2641.78, "total_tokens": 5220352} {"current_steps": 19470, "total_steps": 38150, "loss": 0.2324, "lr": 2.8451010316296783e-05, "epoch": 5.10353866317169, "percentage": 51.04, "elapsed_time": "0:32:56", "remaining_time": "0:31:36", "throughput": 2641.86, "total_tokens": 5221776} {"current_steps": 19475, "total_steps": 38150, "loss": 0.5458, "lr": 2.8439682167132027e-05, "epoch": 5.104849279161206, "percentage": 51.05, "elapsed_time": "0:32:56", "remaining_time": "0:31:35", "throughput": 2641.88, "total_tokens": 5222944} {"current_steps": 19480, "total_steps": 38150, "loss": 0.2506, "lr": 2.8428353298047738e-05, "epoch": 5.1061598951507206, "percentage": 51.06, "elapsed_time": "0:32:57", "remaining_time": "0:31:35", "throughput": 2641.82, "total_tokens": 5223904} {"current_steps": 19485, "total_steps": 38150, "loss": 0.2336, "lr": 2.8417023711415036e-05, "epoch": 5.107470511140236, "percentage": 51.07, "elapsed_time": "0:32:57", "remaining_time": "0:31:34", "throughput": 2641.94, "total_tokens": 5225408} {"current_steps": 19490, "total_steps": 38150, "loss": 0.2678, "lr": 2.8405693409605166e-05, "epoch": 5.108781127129751, "percentage": 51.09, "elapsed_time": "0:32:58", "remaining_time": "0:31:34", "throughput": 2641.88, "total_tokens": 5226368} {"current_steps": 19495, "total_steps": 38150, "loss": 0.4728, "lr": 2.839436239498955e-05, "epoch": 5.110091743119266, "percentage": 51.1, "elapsed_time": "0:32:58", "remaining_time": "0:31:33", "throughput": 2641.93, "total_tokens": 5227696} {"current_steps": 19500, "total_steps": 38150, "loss": 0.295, "lr": 2.8383030669939752e-05, "epoch": 5.111402359108781, "percentage": 51.11, "elapsed_time": "0:32:59", "remaining_time": "0:31:32", "throughput": 2642.09, "total_tokens": 5229264} {"current_steps": 19505, "total_steps": 38150, "loss": 0.2944, "lr": 2.837169823682748e-05, "epoch": 5.1127129750982965, "percentage": 51.13, "elapsed_time": "0:32:59", "remaining_time": "0:31:32", "throughput": 2642.15, "total_tokens": 5230528} {"current_steps": 19510, "total_steps": 38150, "loss": 0.3215, "lr": 2.8360365098024593e-05, "epoch": 5.114023591087811, "percentage": 51.14, "elapsed_time": "0:33:00", "remaining_time": "0:31:31", "throughput": 2642.19, "total_tokens": 5231840} {"current_steps": 19515, "total_steps": 38150, "loss": 0.2466, "lr": 2.8349031255903098e-05, "epoch": 5.115334207077327, "percentage": 51.15, "elapsed_time": "0:33:00", "remaining_time": "0:31:31", "throughput": 2642.17, "total_tokens": 5232912} {"current_steps": 19520, "total_steps": 38150, "loss": 0.293, "lr": 2.8337696712835143e-05, "epoch": 5.116644823066841, "percentage": 51.17, "elapsed_time": "0:33:01", "remaining_time": "0:31:30", "throughput": 2642.38, "total_tokens": 5234752} {"current_steps": 19525, "total_steps": 38150, "loss": 0.4103, "lr": 2.8326361471193035e-05, "epoch": 5.117955439056357, "percentage": 51.18, "elapsed_time": "0:33:01", "remaining_time": "0:31:30", "throughput": 2642.41, "total_tokens": 5235968} {"current_steps": 19530, "total_steps": 38150, "loss": 0.2423, "lr": 2.831502553334922e-05, "epoch": 5.1192660550458715, "percentage": 51.19, "elapsed_time": "0:33:01", "remaining_time": "0:31:29", "throughput": 2642.41, "total_tokens": 5237168} {"current_steps": 19535, "total_steps": 38150, "loss": 0.2342, "lr": 2.8303688901676288e-05, "epoch": 5.120576671035387, "percentage": 51.21, "elapsed_time": "0:33:02", "remaining_time": "0:31:29", "throughput": 2642.41, "total_tokens": 5238304} {"current_steps": 19540, "total_steps": 38150, "loss": 0.3271, "lr": 2.8292351578546982e-05, "epoch": 5.121887287024902, "percentage": 51.22, "elapsed_time": "0:33:02", "remaining_time": "0:31:28", "throughput": 2642.55, "total_tokens": 5239840} {"current_steps": 19545, "total_steps": 38150, "loss": 0.2762, "lr": 2.8281013566334182e-05, "epoch": 5.123197903014416, "percentage": 51.23, "elapsed_time": "0:33:03", "remaining_time": "0:31:27", "throughput": 2642.58, "total_tokens": 5241088} {"current_steps": 19550, "total_steps": 38150, "loss": 0.2577, "lr": 2.8269674867410907e-05, "epoch": 5.124508519003932, "percentage": 51.25, "elapsed_time": "0:33:03", "remaining_time": "0:31:27", "throughput": 2642.59, "total_tokens": 5242208} {"current_steps": 19555, "total_steps": 38150, "loss": 0.2008, "lr": 2.8258335484150323e-05, "epoch": 5.1258191349934465, "percentage": 51.26, "elapsed_time": "0:33:04", "remaining_time": "0:31:26", "throughput": 2642.67, "total_tokens": 5243552} {"current_steps": 19560, "total_steps": 38150, "loss": 0.2728, "lr": 2.8246995418925764e-05, "epoch": 5.127129750982962, "percentage": 51.27, "elapsed_time": "0:33:04", "remaining_time": "0:31:26", "throughput": 2642.7, "total_tokens": 5244800} {"current_steps": 19565, "total_steps": 38150, "loss": 0.3377, "lr": 2.823565467411067e-05, "epoch": 5.128440366972477, "percentage": 51.28, "elapsed_time": "0:33:05", "remaining_time": "0:31:25", "throughput": 2642.84, "total_tokens": 5246400} {"current_steps": 19570, "total_steps": 38150, "loss": 0.2667, "lr": 2.8224313252078637e-05, "epoch": 5.129750982961992, "percentage": 51.3, "elapsed_time": "0:33:05", "remaining_time": "0:31:25", "throughput": 2642.87, "total_tokens": 5247600} {"current_steps": 19575, "total_steps": 38150, "loss": 0.319, "lr": 2.8212971155203422e-05, "epoch": 5.131061598951507, "percentage": 51.31, "elapsed_time": "0:33:06", "remaining_time": "0:31:24", "throughput": 2642.95, "total_tokens": 5248976} {"current_steps": 19580, "total_steps": 38150, "loss": 0.3421, "lr": 2.820162838585889e-05, "epoch": 5.1323722149410225, "percentage": 51.32, "elapsed_time": "0:33:06", "remaining_time": "0:31:23", "throughput": 2642.85, "total_tokens": 5249872} {"current_steps": 19585, "total_steps": 38150, "loss": 0.3786, "lr": 2.819028494641907e-05, "epoch": 5.133682830930537, "percentage": 51.34, "elapsed_time": "0:33:06", "remaining_time": "0:31:23", "throughput": 2642.96, "total_tokens": 5251376} {"current_steps": 19590, "total_steps": 38150, "loss": 0.3423, "lr": 2.817894083925812e-05, "epoch": 5.134993446920053, "percentage": 51.35, "elapsed_time": "0:33:07", "remaining_time": "0:31:22", "throughput": 2643.03, "total_tokens": 5252672} {"current_steps": 19595, "total_steps": 38150, "loss": 0.2341, "lr": 2.816759606675035e-05, "epoch": 5.136304062909567, "percentage": 51.36, "elapsed_time": "0:33:07", "remaining_time": "0:31:22", "throughput": 2643.1, "total_tokens": 5253984} {"current_steps": 19600, "total_steps": 38150, "loss": 0.3781, "lr": 2.81562506312702e-05, "epoch": 5.137614678899083, "percentage": 51.38, "elapsed_time": "0:33:08", "remaining_time": "0:31:21", "throughput": 2643.26, "total_tokens": 5255552} {"current_steps": 19605, "total_steps": 38150, "loss": 0.2943, "lr": 2.814490453519224e-05, "epoch": 5.1389252948885975, "percentage": 51.39, "elapsed_time": "0:33:08", "remaining_time": "0:31:21", "throughput": 2643.23, "total_tokens": 5256592} {"current_steps": 19610, "total_steps": 38150, "loss": 0.3553, "lr": 2.8133557780891194e-05, "epoch": 5.140235910878113, "percentage": 51.4, "elapsed_time": "0:33:09", "remaining_time": "0:31:20", "throughput": 2643.25, "total_tokens": 5257728} {"current_steps": 19615, "total_steps": 38150, "loss": 0.2036, "lr": 2.812221037074192e-05, "epoch": 5.141546526867628, "percentage": 51.42, "elapsed_time": "0:33:09", "remaining_time": "0:31:19", "throughput": 2643.24, "total_tokens": 5258816} {"current_steps": 19620, "total_steps": 38150, "loss": 0.2006, "lr": 2.8110862307119413e-05, "epoch": 5.142857142857143, "percentage": 51.43, "elapsed_time": "0:33:09", "remaining_time": "0:31:19", "throughput": 2643.22, "total_tokens": 5259904} {"current_steps": 19625, "total_steps": 38150, "loss": 0.2412, "lr": 2.80995135923988e-05, "epoch": 5.144167758846658, "percentage": 51.44, "elapsed_time": "0:33:10", "remaining_time": "0:31:18", "throughput": 2643.26, "total_tokens": 5261216} {"current_steps": 19630, "total_steps": 38150, "loss": 0.1794, "lr": 2.8088164228955345e-05, "epoch": 5.145478374836173, "percentage": 51.45, "elapsed_time": "0:33:10", "remaining_time": "0:31:18", "throughput": 2643.28, "total_tokens": 5262400} {"current_steps": 19635, "total_steps": 38150, "loss": 0.2454, "lr": 2.8076814219164456e-05, "epoch": 5.146788990825688, "percentage": 51.47, "elapsed_time": "0:33:11", "remaining_time": "0:31:17", "throughput": 2643.17, "total_tokens": 5263280} {"current_steps": 19640, "total_steps": 38150, "loss": 0.4865, "lr": 2.806546356540166e-05, "epoch": 5.148099606815203, "percentage": 51.48, "elapsed_time": "0:33:11", "remaining_time": "0:31:17", "throughput": 2643.29, "total_tokens": 5264688} {"current_steps": 19645, "total_steps": 38150, "loss": 0.3193, "lr": 2.8054112270042644e-05, "epoch": 5.149410222804718, "percentage": 51.49, "elapsed_time": "0:33:12", "remaining_time": "0:31:16", "throughput": 2643.33, "total_tokens": 5265952} {"current_steps": 19650, "total_steps": 38150, "loss": 0.2176, "lr": 2.8042760335463203e-05, "epoch": 5.150720838794233, "percentage": 51.51, "elapsed_time": "0:33:12", "remaining_time": "0:31:16", "throughput": 2643.55, "total_tokens": 5267680} {"current_steps": 19655, "total_steps": 38150, "loss": 0.3143, "lr": 2.8031407764039287e-05, "epoch": 5.1520314547837485, "percentage": 51.52, "elapsed_time": "0:33:13", "remaining_time": "0:31:15", "throughput": 2643.59, "total_tokens": 5268944} {"current_steps": 19660, "total_steps": 38150, "loss": 0.2549, "lr": 2.8020054558146964e-05, "epoch": 5.153342070773263, "percentage": 51.53, "elapsed_time": "0:33:13", "remaining_time": "0:31:14", "throughput": 2643.6, "total_tokens": 5270096} {"current_steps": 19665, "total_steps": 38150, "loss": 0.5715, "lr": 2.8008700720162433e-05, "epoch": 5.154652686762779, "percentage": 51.55, "elapsed_time": "0:33:13", "remaining_time": "0:31:14", "throughput": 2643.5, "total_tokens": 5271024} {"current_steps": 19670, "total_steps": 38150, "loss": 0.3178, "lr": 2.7997346252462035e-05, "epoch": 5.155963302752293, "percentage": 51.56, "elapsed_time": "0:33:14", "remaining_time": "0:31:13", "throughput": 2643.44, "total_tokens": 5271984} {"current_steps": 19675, "total_steps": 38150, "loss": 0.2511, "lr": 2.7985991157422254e-05, "epoch": 5.157273918741809, "percentage": 51.57, "elapsed_time": "0:33:14", "remaining_time": "0:31:13", "throughput": 2643.54, "total_tokens": 5273456} {"current_steps": 19680, "total_steps": 38150, "loss": 0.2362, "lr": 2.797463543741969e-05, "epoch": 5.1585845347313235, "percentage": 51.59, "elapsed_time": "0:33:15", "remaining_time": "0:31:12", "throughput": 2643.6, "total_tokens": 5274720} {"current_steps": 19685, "total_steps": 38150, "loss": 0.3019, "lr": 2.7963279094831057e-05, "epoch": 5.159895150720839, "percentage": 51.6, "elapsed_time": "0:33:15", "remaining_time": "0:31:12", "throughput": 2643.61, "total_tokens": 5275840} {"current_steps": 19690, "total_steps": 38150, "loss": 0.2508, "lr": 2.7951922132033235e-05, "epoch": 5.161205766710354, "percentage": 51.61, "elapsed_time": "0:33:16", "remaining_time": "0:31:11", "throughput": 2643.76, "total_tokens": 5277344} {"current_steps": 19695, "total_steps": 38150, "loss": 0.3241, "lr": 2.794056455140321e-05, "epoch": 5.162516382699869, "percentage": 51.63, "elapsed_time": "0:33:16", "remaining_time": "0:31:11", "throughput": 2644.08, "total_tokens": 5279568} {"current_steps": 19700, "total_steps": 38150, "loss": 0.3341, "lr": 2.7929206355318104e-05, "epoch": 5.163826998689384, "percentage": 51.64, "elapsed_time": "0:33:17", "remaining_time": "0:31:10", "throughput": 2644.21, "total_tokens": 5281120} {"current_steps": 19705, "total_steps": 38150, "loss": 0.468, "lr": 2.791784754615517e-05, "epoch": 5.165137614678899, "percentage": 51.65, "elapsed_time": "0:33:17", "remaining_time": "0:31:10", "throughput": 2644.37, "total_tokens": 5282816} {"current_steps": 19710, "total_steps": 38150, "loss": 0.2541, "lr": 2.7906488126291784e-05, "epoch": 5.166448230668414, "percentage": 51.66, "elapsed_time": "0:33:18", "remaining_time": "0:31:09", "throughput": 2644.43, "total_tokens": 5284144} {"current_steps": 19715, "total_steps": 38150, "loss": 0.2693, "lr": 2.789512809810546e-05, "epoch": 5.16775884665793, "percentage": 51.68, "elapsed_time": "0:33:18", "remaining_time": "0:31:08", "throughput": 2644.52, "total_tokens": 5285616} {"current_steps": 19720, "total_steps": 38150, "loss": 0.3194, "lr": 2.7883767463973832e-05, "epoch": 5.169069462647444, "percentage": 51.69, "elapsed_time": "0:33:19", "remaining_time": "0:31:08", "throughput": 2644.51, "total_tokens": 5286720} {"current_steps": 19725, "total_steps": 38150, "loss": 0.4397, "lr": 2.787240622627465e-05, "epoch": 5.17038007863696, "percentage": 51.7, "elapsed_time": "0:33:19", "remaining_time": "0:31:07", "throughput": 2644.53, "total_tokens": 5287936} {"current_steps": 19730, "total_steps": 38150, "loss": 0.3182, "lr": 2.78610443873858e-05, "epoch": 5.1716906946264745, "percentage": 51.72, "elapsed_time": "0:33:19", "remaining_time": "0:31:07", "throughput": 2644.58, "total_tokens": 5289152} {"current_steps": 19735, "total_steps": 38150, "loss": 0.1879, "lr": 2.7849681949685314e-05, "epoch": 5.173001310615989, "percentage": 51.73, "elapsed_time": "0:33:20", "remaining_time": "0:31:06", "throughput": 2644.53, "total_tokens": 5290160} {"current_steps": 19740, "total_steps": 38150, "loss": 0.2072, "lr": 2.783831891555132e-05, "epoch": 5.174311926605505, "percentage": 51.74, "elapsed_time": "0:33:20", "remaining_time": "0:31:06", "throughput": 2644.69, "total_tokens": 5291760} {"current_steps": 19745, "total_steps": 38150, "loss": 0.4708, "lr": 2.7826955287362077e-05, "epoch": 5.175622542595019, "percentage": 51.76, "elapsed_time": "0:33:21", "remaining_time": "0:31:05", "throughput": 2644.71, "total_tokens": 5293024} {"current_steps": 19750, "total_steps": 38150, "loss": 0.1162, "lr": 2.7815591067495977e-05, "epoch": 5.176933158584535, "percentage": 51.77, "elapsed_time": "0:33:21", "remaining_time": "0:31:04", "throughput": 2644.61, "total_tokens": 5293920} {"current_steps": 19755, "total_steps": 38150, "loss": 0.3018, "lr": 2.7804226258331535e-05, "epoch": 5.1782437745740495, "percentage": 51.78, "elapsed_time": "0:33:22", "remaining_time": "0:31:04", "throughput": 2644.65, "total_tokens": 5295200} {"current_steps": 19760, "total_steps": 38150, "loss": 0.4139, "lr": 2.7792860862247377e-05, "epoch": 5.179554390563565, "percentage": 51.8, "elapsed_time": "0:33:22", "remaining_time": "0:31:03", "throughput": 2644.88, "total_tokens": 5297088} {"current_steps": 19765, "total_steps": 38150, "loss": 0.2922, "lr": 2.7781494881622268e-05, "epoch": 5.18086500655308, "percentage": 51.81, "elapsed_time": "0:33:23", "remaining_time": "0:31:03", "throughput": 2644.99, "total_tokens": 5298480} {"current_steps": 19770, "total_steps": 38150, "loss": 0.3084, "lr": 2.7770128318835087e-05, "epoch": 5.182175622542595, "percentage": 51.82, "elapsed_time": "0:33:23", "remaining_time": "0:31:02", "throughput": 2645.0, "total_tokens": 5299648} {"current_steps": 19775, "total_steps": 38150, "loss": 0.3377, "lr": 2.7758761176264835e-05, "epoch": 5.18348623853211, "percentage": 51.83, "elapsed_time": "0:33:24", "remaining_time": "0:31:02", "throughput": 2644.98, "total_tokens": 5300752} {"current_steps": 19780, "total_steps": 38150, "loss": 0.3885, "lr": 2.7747393456290644e-05, "epoch": 5.184796854521625, "percentage": 51.85, "elapsed_time": "0:33:24", "remaining_time": "0:31:01", "throughput": 2645.16, "total_tokens": 5302384} {"current_steps": 19785, "total_steps": 38150, "loss": 0.2874, "lr": 2.7736025161291734e-05, "epoch": 5.18610747051114, "percentage": 51.86, "elapsed_time": "0:33:25", "remaining_time": "0:31:01", "throughput": 2645.16, "total_tokens": 5303584} {"current_steps": 19790, "total_steps": 38150, "loss": 0.2495, "lr": 2.7724656293647494e-05, "epoch": 5.187418086500656, "percentage": 51.87, "elapsed_time": "0:33:25", "remaining_time": "0:31:00", "throughput": 2645.27, "total_tokens": 5305072} {"current_steps": 19795, "total_steps": 38150, "loss": 0.266, "lr": 2.7713286855737403e-05, "epoch": 5.18872870249017, "percentage": 51.89, "elapsed_time": "0:33:25", "remaining_time": "0:31:00", "throughput": 2645.33, "total_tokens": 5306368} {"current_steps": 19800, "total_steps": 38150, "loss": 0.2003, "lr": 2.7701916849941056e-05, "epoch": 5.190039318479686, "percentage": 51.9, "elapsed_time": "0:33:26", "remaining_time": "0:30:59", "throughput": 2645.38, "total_tokens": 5307600} {"current_steps": 19805, "total_steps": 38150, "loss": 0.3682, "lr": 2.7690546278638184e-05, "epoch": 5.1913499344692005, "percentage": 51.91, "elapsed_time": "0:33:26", "remaining_time": "0:30:58", "throughput": 2645.34, "total_tokens": 5308688} {"current_steps": 19810, "total_steps": 38150, "loss": 0.4728, "lr": 2.7679175144208626e-05, "epoch": 5.192660550458716, "percentage": 51.93, "elapsed_time": "0:33:27", "remaining_time": "0:30:58", "throughput": 2645.44, "total_tokens": 5310192} {"current_steps": 19815, "total_steps": 38150, "loss": 0.3182, "lr": 2.7667803449032333e-05, "epoch": 5.193971166448231, "percentage": 51.94, "elapsed_time": "0:33:27", "remaining_time": "0:30:57", "throughput": 2645.47, "total_tokens": 5311392} {"current_steps": 19820, "total_steps": 38150, "loss": 0.227, "lr": 2.765643119548939e-05, "epoch": 5.195281782437746, "percentage": 51.95, "elapsed_time": "0:33:28", "remaining_time": "0:30:57", "throughput": 2645.57, "total_tokens": 5312848} {"current_steps": 19825, "total_steps": 38150, "loss": 0.2831, "lr": 2.7645058385959987e-05, "epoch": 5.196592398427261, "percentage": 51.97, "elapsed_time": "0:33:28", "remaining_time": "0:30:56", "throughput": 2645.76, "total_tokens": 5314528} {"current_steps": 19830, "total_steps": 38150, "loss": 0.2523, "lr": 2.7633685022824436e-05, "epoch": 5.1979030144167755, "percentage": 51.98, "elapsed_time": "0:33:29", "remaining_time": "0:30:56", "throughput": 2645.87, "total_tokens": 5316000} {"current_steps": 19835, "total_steps": 38150, "loss": 0.2993, "lr": 2.7622311108463167e-05, "epoch": 5.199213630406291, "percentage": 51.99, "elapsed_time": "0:33:29", "remaining_time": "0:30:55", "throughput": 2645.92, "total_tokens": 5317328} {"current_steps": 19840, "total_steps": 38150, "loss": 0.1938, "lr": 2.76109366452567e-05, "epoch": 5.200524246395806, "percentage": 52.01, "elapsed_time": "0:33:30", "remaining_time": "0:30:55", "throughput": 2645.86, "total_tokens": 5318336} {"current_steps": 19845, "total_steps": 38150, "loss": 0.9643, "lr": 2.7599561635585713e-05, "epoch": 5.201834862385321, "percentage": 52.02, "elapsed_time": "0:33:30", "remaining_time": "0:30:54", "throughput": 2645.88, "total_tokens": 5319488} {"current_steps": 19850, "total_steps": 38150, "loss": 0.3049, "lr": 2.7588186081830965e-05, "epoch": 5.203145478374836, "percentage": 52.03, "elapsed_time": "0:33:30", "remaining_time": "0:30:53", "throughput": 2645.86, "total_tokens": 5320560} {"current_steps": 19855, "total_steps": 38150, "loss": 0.249, "lr": 2.7576809986373348e-05, "epoch": 5.204456094364351, "percentage": 52.04, "elapsed_time": "0:33:31", "remaining_time": "0:30:53", "throughput": 2645.94, "total_tokens": 5321920} {"current_steps": 19860, "total_steps": 38150, "loss": 0.3364, "lr": 2.756543335159385e-05, "epoch": 5.205766710353866, "percentage": 52.06, "elapsed_time": "0:33:31", "remaining_time": "0:30:52", "throughput": 2646.14, "total_tokens": 5323664} {"current_steps": 19865, "total_steps": 38150, "loss": 0.2231, "lr": 2.7554056179873583e-05, "epoch": 5.207077326343382, "percentage": 52.07, "elapsed_time": "0:33:32", "remaining_time": "0:30:52", "throughput": 2646.18, "total_tokens": 5324896} {"current_steps": 19870, "total_steps": 38150, "loss": 0.4658, "lr": 2.7542678473593762e-05, "epoch": 5.208387942332896, "percentage": 52.08, "elapsed_time": "0:33:32", "remaining_time": "0:30:51", "throughput": 2646.26, "total_tokens": 5326288} {"current_steps": 19875, "total_steps": 38150, "loss": 0.1587, "lr": 2.753130023513574e-05, "epoch": 5.209698558322412, "percentage": 52.1, "elapsed_time": "0:33:33", "remaining_time": "0:30:51", "throughput": 2646.28, "total_tokens": 5327472} {"current_steps": 19880, "total_steps": 38150, "loss": 0.2909, "lr": 2.7519921466880954e-05, "epoch": 5.2110091743119265, "percentage": 52.11, "elapsed_time": "0:33:33", "remaining_time": "0:30:50", "throughput": 2646.34, "total_tokens": 5328832} {"current_steps": 19885, "total_steps": 38150, "loss": 0.2705, "lr": 2.7508542171210953e-05, "epoch": 5.212319790301442, "percentage": 52.12, "elapsed_time": "0:33:34", "remaining_time": "0:30:50", "throughput": 2646.33, "total_tokens": 5329936} {"current_steps": 19890, "total_steps": 38150, "loss": 0.3029, "lr": 2.7497162350507415e-05, "epoch": 5.213630406290957, "percentage": 52.14, "elapsed_time": "0:33:34", "remaining_time": "0:30:49", "throughput": 2646.4, "total_tokens": 5331248} {"current_steps": 19895, "total_steps": 38150, "loss": 0.2964, "lr": 2.7485782007152117e-05, "epoch": 5.214941022280472, "percentage": 52.15, "elapsed_time": "0:33:34", "remaining_time": "0:30:48", "throughput": 2646.55, "total_tokens": 5332720} {"current_steps": 19900, "total_steps": 38150, "loss": 0.3179, "lr": 2.747440114352693e-05, "epoch": 5.216251638269987, "percentage": 52.16, "elapsed_time": "0:33:35", "remaining_time": "0:30:48", "throughput": 2646.51, "total_tokens": 5333760} {"current_steps": 19905, "total_steps": 38150, "loss": 0.5129, "lr": 2.7463019762013858e-05, "epoch": 5.217562254259502, "percentage": 52.18, "elapsed_time": "0:33:35", "remaining_time": "0:30:47", "throughput": 2646.78, "total_tokens": 5335696} {"current_steps": 19910, "total_steps": 38150, "loss": 0.278, "lr": 2.745163786499501e-05, "epoch": 5.218872870249017, "percentage": 52.19, "elapsed_time": "0:33:36", "remaining_time": "0:30:47", "throughput": 2646.89, "total_tokens": 5337088} {"current_steps": 19915, "total_steps": 38150, "loss": 0.2953, "lr": 2.74402554548526e-05, "epoch": 5.220183486238533, "percentage": 52.2, "elapsed_time": "0:33:36", "remaining_time": "0:30:46", "throughput": 2646.98, "total_tokens": 5338480} {"current_steps": 19920, "total_steps": 38150, "loss": 0.3238, "lr": 2.742887253396893e-05, "epoch": 5.221494102228047, "percentage": 52.21, "elapsed_time": "0:33:37", "remaining_time": "0:30:46", "throughput": 2647.02, "total_tokens": 5339680} {"current_steps": 19925, "total_steps": 38150, "loss": 0.3185, "lr": 2.7417489104726435e-05, "epoch": 5.222804718217562, "percentage": 52.23, "elapsed_time": "0:33:37", "remaining_time": "0:30:45", "throughput": 2647.02, "total_tokens": 5340880} {"current_steps": 19930, "total_steps": 38150, "loss": 0.3681, "lr": 2.740610516950765e-05, "epoch": 5.224115334207077, "percentage": 52.24, "elapsed_time": "0:33:38", "remaining_time": "0:30:44", "throughput": 2646.96, "total_tokens": 5341888} {"current_steps": 19935, "total_steps": 38150, "loss": 0.2874, "lr": 2.739472073069521e-05, "epoch": 5.225425950196592, "percentage": 52.25, "elapsed_time": "0:33:38", "remaining_time": "0:30:44", "throughput": 2647.1, "total_tokens": 5343424} {"current_steps": 19940, "total_steps": 38150, "loss": 0.2464, "lr": 2.738333579067186e-05, "epoch": 5.226736566186108, "percentage": 52.27, "elapsed_time": "0:33:39", "remaining_time": "0:30:43", "throughput": 2647.25, "total_tokens": 5345024} {"current_steps": 19945, "total_steps": 38150, "loss": 0.2768, "lr": 2.7371950351820445e-05, "epoch": 5.228047182175622, "percentage": 52.28, "elapsed_time": "0:33:39", "remaining_time": "0:30:43", "throughput": 2647.25, "total_tokens": 5346144} {"current_steps": 19950, "total_steps": 38150, "loss": 0.1866, "lr": 2.736056441652392e-05, "epoch": 5.229357798165138, "percentage": 52.29, "elapsed_time": "0:33:39", "remaining_time": "0:30:42", "throughput": 2647.11, "total_tokens": 5346960} {"current_steps": 19955, "total_steps": 38150, "loss": 0.2984, "lr": 2.7349177987165342e-05, "epoch": 5.2306684141546524, "percentage": 52.31, "elapsed_time": "0:33:40", "remaining_time": "0:30:42", "throughput": 2647.25, "total_tokens": 5348496} {"current_steps": 19960, "total_steps": 38150, "loss": 0.3447, "lr": 2.7337791066127872e-05, "epoch": 5.231979030144168, "percentage": 52.32, "elapsed_time": "0:33:40", "remaining_time": "0:30:41", "throughput": 2647.26, "total_tokens": 5349632} {"current_steps": 19965, "total_steps": 38150, "loss": 0.2479, "lr": 2.732640365579477e-05, "epoch": 5.233289646133683, "percentage": 52.33, "elapsed_time": "0:33:41", "remaining_time": "0:30:41", "throughput": 2647.22, "total_tokens": 5350672} {"current_steps": 19970, "total_steps": 38150, "loss": 0.2005, "lr": 2.73150157585494e-05, "epoch": 5.234600262123198, "percentage": 52.35, "elapsed_time": "0:33:41", "remaining_time": "0:30:40", "throughput": 2647.25, "total_tokens": 5351952} {"current_steps": 19975, "total_steps": 38150, "loss": 0.2172, "lr": 2.7303627376775242e-05, "epoch": 5.235910878112713, "percentage": 52.36, "elapsed_time": "0:33:42", "remaining_time": "0:30:39", "throughput": 2647.39, "total_tokens": 5353552} {"current_steps": 19980, "total_steps": 38150, "loss": 0.4779, "lr": 2.7292238512855844e-05, "epoch": 5.237221494102228, "percentage": 52.37, "elapsed_time": "0:33:42", "remaining_time": "0:30:39", "throughput": 2647.44, "total_tokens": 5354800} {"current_steps": 19985, "total_steps": 38150, "loss": 0.3049, "lr": 2.7280849169174887e-05, "epoch": 5.238532110091743, "percentage": 52.39, "elapsed_time": "0:33:43", "remaining_time": "0:30:38", "throughput": 2647.33, "total_tokens": 5355696} {"current_steps": 19990, "total_steps": 38150, "loss": 0.3215, "lr": 2.7269459348116143e-05, "epoch": 5.239842726081259, "percentage": 52.4, "elapsed_time": "0:33:43", "remaining_time": "0:30:38", "throughput": 2647.45, "total_tokens": 5357232} {"current_steps": 19995, "total_steps": 38150, "loss": 0.3191, "lr": 2.7258069052063477e-05, "epoch": 5.241153342070773, "percentage": 52.41, "elapsed_time": "0:33:43", "remaining_time": "0:30:37", "throughput": 2647.5, "total_tokens": 5358528} {"current_steps": 20000, "total_steps": 38150, "loss": 0.2318, "lr": 2.724667828340086e-05, "epoch": 5.242463958060289, "percentage": 52.42, "elapsed_time": "0:33:44", "remaining_time": "0:30:37", "throughput": 2647.54, "total_tokens": 5359840} {"current_steps": 20005, "total_steps": 38150, "loss": 0.3093, "lr": 2.7235287044512365e-05, "epoch": 5.243774574049803, "percentage": 52.44, "elapsed_time": "0:33:44", "remaining_time": "0:30:36", "throughput": 2647.52, "total_tokens": 5360944} {"current_steps": 20010, "total_steps": 38150, "loss": 0.3534, "lr": 2.7223895337782145e-05, "epoch": 5.245085190039318, "percentage": 52.45, "elapsed_time": "0:33:45", "remaining_time": "0:30:36", "throughput": 2647.68, "total_tokens": 5362704} {"current_steps": 20015, "total_steps": 38150, "loss": 0.241, "lr": 2.7212503165594483e-05, "epoch": 5.246395806028834, "percentage": 52.46, "elapsed_time": "0:33:45", "remaining_time": "0:30:35", "throughput": 2647.57, "total_tokens": 5363584} {"current_steps": 20020, "total_steps": 38150, "loss": 0.2581, "lr": 2.7201110530333722e-05, "epoch": 5.247706422018348, "percentage": 52.48, "elapsed_time": "0:33:46", "remaining_time": "0:30:34", "throughput": 2647.49, "total_tokens": 5364544} {"current_steps": 20025, "total_steps": 38150, "loss": 0.3966, "lr": 2.7189717434384338e-05, "epoch": 5.249017038007864, "percentage": 52.49, "elapsed_time": "0:33:46", "remaining_time": "0:30:34", "throughput": 2647.63, "total_tokens": 5366144} {"current_steps": 20030, "total_steps": 38150, "loss": 0.3475, "lr": 2.7178323880130878e-05, "epoch": 5.250327653997378, "percentage": 52.5, "elapsed_time": "0:33:47", "remaining_time": "0:30:33", "throughput": 2647.66, "total_tokens": 5367408} {"current_steps": 20035, "total_steps": 38150, "loss": 0.2577, "lr": 2.716692986995799e-05, "epoch": 5.251638269986894, "percentage": 52.52, "elapsed_time": "0:33:47", "remaining_time": "0:30:33", "throughput": 2647.63, "total_tokens": 5368480} {"current_steps": 20040, "total_steps": 38150, "loss": 0.426, "lr": 2.7155535406250425e-05, "epoch": 5.252948885976409, "percentage": 52.53, "elapsed_time": "0:33:48", "remaining_time": "0:30:32", "throughput": 2647.69, "total_tokens": 5369744} {"current_steps": 20045, "total_steps": 38150, "loss": 0.2653, "lr": 2.7144140491393018e-05, "epoch": 5.254259501965924, "percentage": 52.54, "elapsed_time": "0:33:48", "remaining_time": "0:30:32", "throughput": 2647.62, "total_tokens": 5370736} {"current_steps": 20050, "total_steps": 38150, "loss": 0.162, "lr": 2.713274512777072e-05, "epoch": 5.255570117955439, "percentage": 52.56, "elapsed_time": "0:33:48", "remaining_time": "0:30:31", "throughput": 2647.57, "total_tokens": 5371744} {"current_steps": 20055, "total_steps": 38150, "loss": 0.4528, "lr": 2.7121349317768552e-05, "epoch": 5.256880733944954, "percentage": 52.57, "elapsed_time": "0:33:49", "remaining_time": "0:30:31", "throughput": 2647.67, "total_tokens": 5373200} {"current_steps": 20060, "total_steps": 38150, "loss": 0.2563, "lr": 2.710995306377163e-05, "epoch": 5.258191349934469, "percentage": 52.58, "elapsed_time": "0:33:49", "remaining_time": "0:30:30", "throughput": 2647.71, "total_tokens": 5374400} {"current_steps": 20065, "total_steps": 38150, "loss": 0.4328, "lr": 2.7098556368165186e-05, "epoch": 5.259501965923985, "percentage": 52.6, "elapsed_time": "0:33:50", "remaining_time": "0:30:29", "throughput": 2647.77, "total_tokens": 5375776} {"current_steps": 20070, "total_steps": 38150, "loss": 0.3599, "lr": 2.7087159233334512e-05, "epoch": 5.260812581913499, "percentage": 52.61, "elapsed_time": "0:33:50", "remaining_time": "0:30:29", "throughput": 2647.75, "total_tokens": 5376848} {"current_steps": 20075, "total_steps": 38150, "loss": 0.263, "lr": 2.707576166166502e-05, "epoch": 5.262123197903015, "percentage": 52.62, "elapsed_time": "0:33:51", "remaining_time": "0:30:28", "throughput": 2647.79, "total_tokens": 5378144} {"current_steps": 20080, "total_steps": 38150, "loss": 0.117, "lr": 2.7064363655542203e-05, "epoch": 5.263433813892529, "percentage": 52.63, "elapsed_time": "0:33:51", "remaining_time": "0:30:28", "throughput": 2647.81, "total_tokens": 5379392} {"current_steps": 20085, "total_steps": 38150, "loss": 0.4371, "lr": 2.7052965217351633e-05, "epoch": 5.264744429882045, "percentage": 52.65, "elapsed_time": "0:33:52", "remaining_time": "0:30:27", "throughput": 2647.83, "total_tokens": 5380576} {"current_steps": 20090, "total_steps": 38150, "loss": 0.1704, "lr": 2.7041566349479003e-05, "epoch": 5.26605504587156, "percentage": 52.66, "elapsed_time": "0:33:52", "remaining_time": "0:30:27", "throughput": 2647.82, "total_tokens": 5381680} {"current_steps": 20095, "total_steps": 38150, "loss": 0.3602, "lr": 2.7030167054310052e-05, "epoch": 5.267365661861074, "percentage": 52.67, "elapsed_time": "0:33:52", "remaining_time": "0:30:26", "throughput": 2647.83, "total_tokens": 5382848} {"current_steps": 20100, "total_steps": 38150, "loss": 0.1882, "lr": 2.701876733423064e-05, "epoch": 5.26867627785059, "percentage": 52.69, "elapsed_time": "0:33:53", "remaining_time": "0:30:25", "throughput": 2647.85, "total_tokens": 5384080} {"current_steps": 20105, "total_steps": 38150, "loss": 0.3774, "lr": 2.700736719162672e-05, "epoch": 5.269986893840104, "percentage": 52.7, "elapsed_time": "0:33:53", "remaining_time": "0:30:25", "throughput": 2648.07, "total_tokens": 5385920} {"current_steps": 20110, "total_steps": 38150, "loss": 0.3175, "lr": 2.699596662888432e-05, "epoch": 5.27129750982962, "percentage": 52.71, "elapsed_time": "0:33:54", "remaining_time": "0:30:24", "throughput": 2648.15, "total_tokens": 5387264} {"current_steps": 20115, "total_steps": 38150, "loss": 0.335, "lr": 2.698456564838955e-05, "epoch": 5.272608125819135, "percentage": 52.73, "elapsed_time": "0:33:54", "remaining_time": "0:30:24", "throughput": 2648.21, "total_tokens": 5388576} {"current_steps": 20120, "total_steps": 38150, "loss": 0.2457, "lr": 2.6973164252528615e-05, "epoch": 5.27391874180865, "percentage": 52.74, "elapsed_time": "0:33:55", "remaining_time": "0:30:23", "throughput": 2648.26, "total_tokens": 5389872} {"current_steps": 20125, "total_steps": 38150, "loss": 0.2562, "lr": 2.696176244368781e-05, "epoch": 5.275229357798165, "percentage": 52.75, "elapsed_time": "0:33:55", "remaining_time": "0:30:23", "throughput": 2648.38, "total_tokens": 5391376} {"current_steps": 20130, "total_steps": 38150, "loss": 0.3317, "lr": 2.6950360224253524e-05, "epoch": 5.27653997378768, "percentage": 52.77, "elapsed_time": "0:33:56", "remaining_time": "0:30:22", "throughput": 2648.46, "total_tokens": 5392736} {"current_steps": 20135, "total_steps": 38150, "loss": 0.2752, "lr": 2.6938957596612203e-05, "epoch": 5.277850589777195, "percentage": 52.78, "elapsed_time": "0:33:56", "remaining_time": "0:30:22", "throughput": 2648.47, "total_tokens": 5393888} {"current_steps": 20140, "total_steps": 38150, "loss": 0.1466, "lr": 2.6927554563150414e-05, "epoch": 5.2791612057667106, "percentage": 52.79, "elapsed_time": "0:33:57", "remaining_time": "0:30:21", "throughput": 2648.41, "total_tokens": 5394848} {"current_steps": 20145, "total_steps": 38150, "loss": 0.5164, "lr": 2.6916151126254785e-05, "epoch": 5.280471821756225, "percentage": 52.8, "elapsed_time": "0:33:57", "remaining_time": "0:30:21", "throughput": 2648.35, "total_tokens": 5395872} {"current_steps": 20150, "total_steps": 38150, "loss": 0.2962, "lr": 2.6904747288312036e-05, "epoch": 5.281782437745741, "percentage": 52.82, "elapsed_time": "0:33:57", "remaining_time": "0:30:20", "throughput": 2648.39, "total_tokens": 5397056} {"current_steps": 20155, "total_steps": 38150, "loss": 0.2373, "lr": 2.689334305170897e-05, "epoch": 5.283093053735255, "percentage": 52.83, "elapsed_time": "0:33:58", "remaining_time": "0:30:19", "throughput": 2648.46, "total_tokens": 5398368} {"current_steps": 20160, "total_steps": 38150, "loss": 0.2837, "lr": 2.688193841883247e-05, "epoch": 5.284403669724771, "percentage": 52.84, "elapsed_time": "0:33:58", "remaining_time": "0:30:19", "throughput": 2648.52, "total_tokens": 5399664} {"current_steps": 20165, "total_steps": 38150, "loss": 0.2719, "lr": 2.6870533392069518e-05, "epoch": 5.285714285714286, "percentage": 52.86, "elapsed_time": "0:33:59", "remaining_time": "0:30:18", "throughput": 2648.53, "total_tokens": 5400816} {"current_steps": 20170, "total_steps": 38150, "loss": 0.2896, "lr": 2.6859127973807158e-05, "epoch": 5.287024901703801, "percentage": 52.87, "elapsed_time": "0:33:59", "remaining_time": "0:30:18", "throughput": 2648.53, "total_tokens": 5401952} {"current_steps": 20175, "total_steps": 38150, "loss": 0.2961, "lr": 2.6847722166432522e-05, "epoch": 5.288335517693316, "percentage": 52.88, "elapsed_time": "0:34:00", "remaining_time": "0:30:17", "throughput": 2648.68, "total_tokens": 5403648} {"current_steps": 20180, "total_steps": 38150, "loss": 0.3123, "lr": 2.6836315972332827e-05, "epoch": 5.289646133682831, "percentage": 52.9, "elapsed_time": "0:34:00", "remaining_time": "0:30:17", "throughput": 2648.95, "total_tokens": 5405728} {"current_steps": 20185, "total_steps": 38150, "loss": 0.2578, "lr": 2.6824909393895375e-05, "epoch": 5.290956749672346, "percentage": 52.91, "elapsed_time": "0:34:01", "remaining_time": "0:30:16", "throughput": 2649.03, "total_tokens": 5407088} {"current_steps": 20190, "total_steps": 38150, "loss": 0.2943, "lr": 2.681350243350754e-05, "epoch": 5.292267365661861, "percentage": 52.92, "elapsed_time": "0:34:01", "remaining_time": "0:30:16", "throughput": 2649.16, "total_tokens": 5408592} {"current_steps": 20195, "total_steps": 38150, "loss": 0.2856, "lr": 2.680209509355678e-05, "epoch": 5.293577981651376, "percentage": 52.94, "elapsed_time": "0:34:02", "remaining_time": "0:30:15", "throughput": 2649.19, "total_tokens": 5409808} {"current_steps": 20200, "total_steps": 38150, "loss": 0.302, "lr": 2.679068737643063e-05, "epoch": 5.294888597640891, "percentage": 52.95, "elapsed_time": "0:34:02", "remaining_time": "0:30:14", "throughput": 2649.13, "total_tokens": 5410784} {"current_steps": 20205, "total_steps": 38150, "loss": 0.293, "lr": 2.6779279284516706e-05, "epoch": 5.296199213630406, "percentage": 52.96, "elapsed_time": "0:34:02", "remaining_time": "0:30:14", "throughput": 2649.17, "total_tokens": 5411984} {"current_steps": 20210, "total_steps": 38150, "loss": 0.3704, "lr": 2.6767870820202707e-05, "epoch": 5.297509829619921, "percentage": 52.98, "elapsed_time": "0:34:03", "remaining_time": "0:30:13", "throughput": 2649.21, "total_tokens": 5413232} {"current_steps": 20215, "total_steps": 38150, "loss": 0.1858, "lr": 2.675646198587639e-05, "epoch": 5.2988204456094365, "percentage": 52.99, "elapsed_time": "0:34:03", "remaining_time": "0:30:13", "throughput": 2649.23, "total_tokens": 5414400} {"current_steps": 20220, "total_steps": 38150, "loss": 0.3209, "lr": 2.6745052783925616e-05, "epoch": 5.300131061598951, "percentage": 53.0, "elapsed_time": "0:34:04", "remaining_time": "0:30:12", "throughput": 2649.37, "total_tokens": 5415872} {"current_steps": 20225, "total_steps": 38150, "loss": 0.3133, "lr": 2.6733643216738325e-05, "epoch": 5.301441677588467, "percentage": 53.01, "elapsed_time": "0:34:04", "remaining_time": "0:30:12", "throughput": 2649.41, "total_tokens": 5417152} {"current_steps": 20230, "total_steps": 38150, "loss": 0.2642, "lr": 2.6722233286702492e-05, "epoch": 5.302752293577981, "percentage": 53.03, "elapsed_time": "0:34:05", "remaining_time": "0:30:11", "throughput": 2649.44, "total_tokens": 5418368} {"current_steps": 20235, "total_steps": 38150, "loss": 0.4131, "lr": 2.671082299620621e-05, "epoch": 5.304062909567497, "percentage": 53.04, "elapsed_time": "0:34:05", "remaining_time": "0:30:11", "throughput": 2649.54, "total_tokens": 5419728} {"current_steps": 20240, "total_steps": 38150, "loss": 0.3651, "lr": 2.6699412347637626e-05, "epoch": 5.305373525557012, "percentage": 53.05, "elapsed_time": "0:34:06", "remaining_time": "0:30:10", "throughput": 2649.71, "total_tokens": 5421408} {"current_steps": 20245, "total_steps": 38150, "loss": 0.1665, "lr": 2.6688001343384977e-05, "epoch": 5.306684141546527, "percentage": 53.07, "elapsed_time": "0:34:06", "remaining_time": "0:30:09", "throughput": 2649.77, "total_tokens": 5422768} {"current_steps": 20250, "total_steps": 38150, "loss": 0.2439, "lr": 2.6676589985836563e-05, "epoch": 5.307994757536042, "percentage": 53.08, "elapsed_time": "0:34:07", "remaining_time": "0:30:09", "throughput": 2649.95, "total_tokens": 5424592} {"current_steps": 20255, "total_steps": 38150, "loss": 0.201, "lr": 2.6665178277380766e-05, "epoch": 5.309305373525557, "percentage": 53.09, "elapsed_time": "0:34:07", "remaining_time": "0:30:09", "throughput": 2650.14, "total_tokens": 5426416} {"current_steps": 20260, "total_steps": 38150, "loss": 0.4559, "lr": 2.6653766220406022e-05, "epoch": 5.310615989515072, "percentage": 53.11, "elapsed_time": "0:34:08", "remaining_time": "0:30:08", "throughput": 2650.13, "total_tokens": 5427536} {"current_steps": 20265, "total_steps": 38150, "loss": 0.1696, "lr": 2.664235381730088e-05, "epoch": 5.3119266055045875, "percentage": 53.12, "elapsed_time": "0:34:08", "remaining_time": "0:30:07", "throughput": 2650.16, "total_tokens": 5428752} {"current_steps": 20270, "total_steps": 38150, "loss": 0.2501, "lr": 2.663094107045391e-05, "epoch": 5.313237221494102, "percentage": 53.13, "elapsed_time": "0:34:08", "remaining_time": "0:30:07", "throughput": 2650.13, "total_tokens": 5429808} {"current_steps": 20275, "total_steps": 38150, "loss": 0.2064, "lr": 2.6619527982253794e-05, "epoch": 5.314547837483618, "percentage": 53.15, "elapsed_time": "0:34:09", "remaining_time": "0:30:06", "throughput": 2650.24, "total_tokens": 5431264} {"current_steps": 20280, "total_steps": 38150, "loss": 0.2795, "lr": 2.6608114555089275e-05, "epoch": 5.315858453473132, "percentage": 53.16, "elapsed_time": "0:34:09", "remaining_time": "0:30:06", "throughput": 2650.3, "total_tokens": 5432672} {"current_steps": 20285, "total_steps": 38150, "loss": 0.2091, "lr": 2.659670079134916e-05, "epoch": 5.317169069462647, "percentage": 53.17, "elapsed_time": "0:34:10", "remaining_time": "0:30:05", "throughput": 2650.25, "total_tokens": 5433696} {"current_steps": 20290, "total_steps": 38150, "loss": 0.462, "lr": 2.6585286693422322e-05, "epoch": 5.3184796854521625, "percentage": 53.18, "elapsed_time": "0:34:10", "remaining_time": "0:30:05", "throughput": 2650.41, "total_tokens": 5435280} {"current_steps": 20295, "total_steps": 38150, "loss": 0.4322, "lr": 2.6573872263697724e-05, "epoch": 5.319790301441677, "percentage": 53.2, "elapsed_time": "0:34:11", "remaining_time": "0:30:04", "throughput": 2650.41, "total_tokens": 5436416} {"current_steps": 20300, "total_steps": 38150, "loss": 0.1766, "lr": 2.6562457504564375e-05, "epoch": 5.321100917431193, "percentage": 53.21, "elapsed_time": "0:34:11", "remaining_time": "0:30:04", "throughput": 2650.58, "total_tokens": 5438016} {"current_steps": 20305, "total_steps": 38150, "loss": 0.3519, "lr": 2.655104241841137e-05, "epoch": 5.322411533420707, "percentage": 53.22, "elapsed_time": "0:34:12", "remaining_time": "0:30:03", "throughput": 2650.62, "total_tokens": 5439392} {"current_steps": 20310, "total_steps": 38150, "loss": 0.3053, "lr": 2.653962700762787e-05, "epoch": 5.323722149410223, "percentage": 53.24, "elapsed_time": "0:34:12", "remaining_time": "0:30:02", "throughput": 2650.77, "total_tokens": 5440960} {"current_steps": 20315, "total_steps": 38150, "loss": 0.3728, "lr": 2.6528211274603092e-05, "epoch": 5.325032765399738, "percentage": 53.25, "elapsed_time": "0:34:13", "remaining_time": "0:30:02", "throughput": 2650.98, "total_tokens": 5442816} {"current_steps": 20320, "total_steps": 38150, "loss": 0.2891, "lr": 2.6516795221726344e-05, "epoch": 5.326343381389253, "percentage": 53.26, "elapsed_time": "0:34:13", "remaining_time": "0:30:01", "throughput": 2650.92, "total_tokens": 5443792} {"current_steps": 20325, "total_steps": 38150, "loss": 0.4974, "lr": 2.6505378851386976e-05, "epoch": 5.327653997378768, "percentage": 53.28, "elapsed_time": "0:34:14", "remaining_time": "0:30:01", "throughput": 2651.03, "total_tokens": 5445312} {"current_steps": 20330, "total_steps": 38150, "loss": 0.2708, "lr": 2.6493962165974405e-05, "epoch": 5.328964613368283, "percentage": 53.29, "elapsed_time": "0:34:14", "remaining_time": "0:30:00", "throughput": 2650.95, "total_tokens": 5446224} {"current_steps": 20335, "total_steps": 38150, "loss": 0.1613, "lr": 2.648254516787814e-05, "epoch": 5.330275229357798, "percentage": 53.3, "elapsed_time": "0:34:14", "remaining_time": "0:30:00", "throughput": 2650.95, "total_tokens": 5447344} {"current_steps": 20340, "total_steps": 38150, "loss": 0.2226, "lr": 2.6471127859487732e-05, "epoch": 5.3315858453473135, "percentage": 53.32, "elapsed_time": "0:34:15", "remaining_time": "0:29:59", "throughput": 2651.03, "total_tokens": 5448752} {"current_steps": 20345, "total_steps": 38150, "loss": 0.4, "lr": 2.6459710243192816e-05, "epoch": 5.332896461336828, "percentage": 53.33, "elapsed_time": "0:34:15", "remaining_time": "0:29:59", "throughput": 2651.07, "total_tokens": 5450000} {"current_steps": 20350, "total_steps": 38150, "loss": 0.2707, "lr": 2.6448292321383057e-05, "epoch": 5.334207077326344, "percentage": 53.34, "elapsed_time": "0:34:16", "remaining_time": "0:29:58", "throughput": 2651.06, "total_tokens": 5451104} {"current_steps": 20355, "total_steps": 38150, "loss": 0.3363, "lr": 2.6436874096448216e-05, "epoch": 5.335517693315858, "percentage": 53.36, "elapsed_time": "0:34:16", "remaining_time": "0:29:57", "throughput": 2651.1, "total_tokens": 5452336} {"current_steps": 20360, "total_steps": 38150, "loss": 0.3602, "lr": 2.642545557077811e-05, "epoch": 5.336828309305374, "percentage": 53.37, "elapsed_time": "0:34:17", "remaining_time": "0:29:57", "throughput": 2651.26, "total_tokens": 5453904} {"current_steps": 20365, "total_steps": 38150, "loss": 0.3871, "lr": 2.641403674676262e-05, "epoch": 5.3381389252948885, "percentage": 53.38, "elapsed_time": "0:34:17", "remaining_time": "0:29:56", "throughput": 2651.31, "total_tokens": 5455136} {"current_steps": 20370, "total_steps": 38150, "loss": 0.4327, "lr": 2.6402617626791682e-05, "epoch": 5.339449541284404, "percentage": 53.39, "elapsed_time": "0:34:17", "remaining_time": "0:29:56", "throughput": 2651.34, "total_tokens": 5456352} {"current_steps": 20375, "total_steps": 38150, "loss": 0.3677, "lr": 2.6391198213255297e-05, "epoch": 5.340760157273919, "percentage": 53.41, "elapsed_time": "0:34:18", "remaining_time": "0:29:55", "throughput": 2651.31, "total_tokens": 5457392} {"current_steps": 20380, "total_steps": 38150, "loss": 0.3699, "lr": 2.637977850854353e-05, "epoch": 5.342070773263433, "percentage": 53.42, "elapsed_time": "0:34:18", "remaining_time": "0:29:55", "throughput": 2651.48, "total_tokens": 5459056} {"current_steps": 20385, "total_steps": 38150, "loss": 0.2508, "lr": 2.6368358515046503e-05, "epoch": 5.343381389252949, "percentage": 53.43, "elapsed_time": "0:34:19", "remaining_time": "0:29:54", "throughput": 2651.45, "total_tokens": 5460080} {"current_steps": 20390, "total_steps": 38150, "loss": 0.2913, "lr": 2.6356938235154404e-05, "epoch": 5.344692005242464, "percentage": 53.45, "elapsed_time": "0:34:19", "remaining_time": "0:29:54", "throughput": 2651.58, "total_tokens": 5461536} {"current_steps": 20395, "total_steps": 38150, "loss": 0.2527, "lr": 2.634551767125748e-05, "epoch": 5.346002621231979, "percentage": 53.46, "elapsed_time": "0:34:20", "remaining_time": "0:29:53", "throughput": 2651.69, "total_tokens": 5462960} {"current_steps": 20400, "total_steps": 38150, "loss": 0.4531, "lr": 2.6334096825746035e-05, "epoch": 5.347313237221494, "percentage": 53.47, "elapsed_time": "0:34:20", "remaining_time": "0:29:52", "throughput": 2651.74, "total_tokens": 5464192} {"current_steps": 20405, "total_steps": 38150, "loss": 0.251, "lr": 2.6322675701010423e-05, "epoch": 5.348623853211009, "percentage": 53.49, "elapsed_time": "0:34:21", "remaining_time": "0:29:52", "throughput": 2651.71, "total_tokens": 5465344} {"current_steps": 20410, "total_steps": 38150, "loss": 0.3747, "lr": 2.6311254299441072e-05, "epoch": 5.349934469200524, "percentage": 53.5, "elapsed_time": "0:34:21", "remaining_time": "0:29:51", "throughput": 2651.61, "total_tokens": 5466240} {"current_steps": 20415, "total_steps": 38150, "loss": 0.1961, "lr": 2.629983262342846e-05, "epoch": 5.3512450851900395, "percentage": 53.51, "elapsed_time": "0:34:21", "remaining_time": "0:29:51", "throughput": 2651.61, "total_tokens": 5467360} {"current_steps": 20420, "total_steps": 38150, "loss": 0.2606, "lr": 2.628841067536314e-05, "epoch": 5.352555701179554, "percentage": 53.53, "elapsed_time": "0:34:22", "remaining_time": "0:29:50", "throughput": 2651.62, "total_tokens": 5468512} {"current_steps": 20425, "total_steps": 38150, "loss": 0.3126, "lr": 2.6276988457635675e-05, "epoch": 5.35386631716907, "percentage": 53.54, "elapsed_time": "0:34:22", "remaining_time": "0:29:50", "throughput": 2651.57, "total_tokens": 5469552} {"current_steps": 20430, "total_steps": 38150, "loss": 0.3528, "lr": 2.626556597263674e-05, "epoch": 5.355176933158584, "percentage": 53.55, "elapsed_time": "0:34:23", "remaining_time": "0:29:49", "throughput": 2651.64, "total_tokens": 5470864} {"current_steps": 20435, "total_steps": 38150, "loss": 0.3973, "lr": 2.625414322275703e-05, "epoch": 5.3564875491481, "percentage": 53.56, "elapsed_time": "0:34:23", "remaining_time": "0:29:48", "throughput": 2651.67, "total_tokens": 5472080} {"current_steps": 20440, "total_steps": 38150, "loss": 0.3023, "lr": 2.6242720210387317e-05, "epoch": 5.3577981651376145, "percentage": 53.58, "elapsed_time": "0:34:24", "remaining_time": "0:29:48", "throughput": 2651.78, "total_tokens": 5473488} {"current_steps": 20445, "total_steps": 38150, "loss": 0.2043, "lr": 2.623129693791841e-05, "epoch": 5.35910878112713, "percentage": 53.59, "elapsed_time": "0:34:24", "remaining_time": "0:29:47", "throughput": 2651.79, "total_tokens": 5474640} {"current_steps": 20450, "total_steps": 38150, "loss": 0.2319, "lr": 2.6219873407741175e-05, "epoch": 5.360419397116645, "percentage": 53.6, "elapsed_time": "0:34:24", "remaining_time": "0:29:47", "throughput": 2651.81, "total_tokens": 5475808} {"current_steps": 20455, "total_steps": 38150, "loss": 0.2659, "lr": 2.620844962224655e-05, "epoch": 5.36173001310616, "percentage": 53.62, "elapsed_time": "0:34:25", "remaining_time": "0:29:46", "throughput": 2651.86, "total_tokens": 5477072} {"current_steps": 20460, "total_steps": 38150, "loss": 0.2951, "lr": 2.6197025583825508e-05, "epoch": 5.363040629095675, "percentage": 53.63, "elapsed_time": "0:34:25", "remaining_time": "0:29:46", "throughput": 2651.91, "total_tokens": 5478352} {"current_steps": 20465, "total_steps": 38150, "loss": 0.1654, "lr": 2.6185601294869077e-05, "epoch": 5.3643512450851905, "percentage": 53.64, "elapsed_time": "0:34:26", "remaining_time": "0:29:45", "throughput": 2652.01, "total_tokens": 5479808} {"current_steps": 20470, "total_steps": 38150, "loss": 0.3029, "lr": 2.617417675776834e-05, "epoch": 5.365661861074705, "percentage": 53.66, "elapsed_time": "0:34:26", "remaining_time": "0:29:45", "throughput": 2652.08, "total_tokens": 5481104} {"current_steps": 20475, "total_steps": 38150, "loss": 0.3222, "lr": 2.6162751974914433e-05, "epoch": 5.36697247706422, "percentage": 53.67, "elapsed_time": "0:34:27", "remaining_time": "0:29:44", "throughput": 2652.16, "total_tokens": 5482432} {"current_steps": 20480, "total_steps": 38150, "loss": 0.3962, "lr": 2.6151326948698557e-05, "epoch": 5.368283093053735, "percentage": 53.68, "elapsed_time": "0:34:27", "remaining_time": "0:29:43", "throughput": 2652.22, "total_tokens": 5483792} {"current_steps": 20485, "total_steps": 38150, "loss": 0.3906, "lr": 2.6139901681511935e-05, "epoch": 5.36959370904325, "percentage": 53.7, "elapsed_time": "0:34:28", "remaining_time": "0:29:43", "throughput": 2652.56, "total_tokens": 5486112} {"current_steps": 20490, "total_steps": 38150, "loss": 0.2132, "lr": 2.6128476175745865e-05, "epoch": 5.3709043250327655, "percentage": 53.71, "elapsed_time": "0:34:28", "remaining_time": "0:29:42", "throughput": 2652.6, "total_tokens": 5487408} {"current_steps": 20495, "total_steps": 38150, "loss": 0.2789, "lr": 2.6117050433791672e-05, "epoch": 5.37221494102228, "percentage": 53.72, "elapsed_time": "0:34:29", "remaining_time": "0:29:42", "throughput": 2652.65, "total_tokens": 5488656} {"current_steps": 20500, "total_steps": 38150, "loss": 0.3393, "lr": 2.6105624458040763e-05, "epoch": 5.373525557011796, "percentage": 53.74, "elapsed_time": "0:34:29", "remaining_time": "0:29:41", "throughput": 2652.69, "total_tokens": 5489984} {"current_steps": 20505, "total_steps": 38150, "loss": 0.3245, "lr": 2.6094198250884562e-05, "epoch": 5.37483617300131, "percentage": 53.75, "elapsed_time": "0:34:30", "remaining_time": "0:29:41", "throughput": 2652.87, "total_tokens": 5491664} {"current_steps": 20510, "total_steps": 38150, "loss": 0.3721, "lr": 2.6082771814714552e-05, "epoch": 5.376146788990826, "percentage": 53.76, "elapsed_time": "0:34:30", "remaining_time": "0:29:40", "throughput": 2652.88, "total_tokens": 5492816} {"current_steps": 20515, "total_steps": 38150, "loss": 0.3241, "lr": 2.6071345151922276e-05, "epoch": 5.3774574049803405, "percentage": 53.77, "elapsed_time": "0:34:31", "remaining_time": "0:29:40", "throughput": 2652.96, "total_tokens": 5494304} {"current_steps": 20520, "total_steps": 38150, "loss": 0.2924, "lr": 2.605991826489932e-05, "epoch": 5.378768020969856, "percentage": 53.79, "elapsed_time": "0:34:31", "remaining_time": "0:29:39", "throughput": 2652.89, "total_tokens": 5495264} {"current_steps": 20525, "total_steps": 38150, "loss": 0.2959, "lr": 2.604849115603729e-05, "epoch": 5.380078636959371, "percentage": 53.8, "elapsed_time": "0:34:31", "remaining_time": "0:29:39", "throughput": 2653.0, "total_tokens": 5496736} {"current_steps": 20530, "total_steps": 38150, "loss": 0.3596, "lr": 2.6037063827727874e-05, "epoch": 5.381389252948886, "percentage": 53.81, "elapsed_time": "0:34:32", "remaining_time": "0:29:38", "throughput": 2652.99, "total_tokens": 5497840} {"current_steps": 20535, "total_steps": 38150, "loss": 0.2687, "lr": 2.6025636282362792e-05, "epoch": 5.382699868938401, "percentage": 53.83, "elapsed_time": "0:34:32", "remaining_time": "0:29:38", "throughput": 2653.01, "total_tokens": 5498992} {"current_steps": 20540, "total_steps": 38150, "loss": 0.3107, "lr": 2.6014208522333815e-05, "epoch": 5.3840104849279165, "percentage": 53.84, "elapsed_time": "0:34:33", "remaining_time": "0:29:37", "throughput": 2653.06, "total_tokens": 5500256} {"current_steps": 20545, "total_steps": 38150, "loss": 0.2891, "lr": 2.6002780550032747e-05, "epoch": 5.385321100917431, "percentage": 53.85, "elapsed_time": "0:34:33", "remaining_time": "0:29:36", "throughput": 2653.14, "total_tokens": 5501600} {"current_steps": 20550, "total_steps": 38150, "loss": 0.1694, "lr": 2.5991352367851435e-05, "epoch": 5.386631716906947, "percentage": 53.87, "elapsed_time": "0:34:34", "remaining_time": "0:29:36", "throughput": 2653.22, "total_tokens": 5503024} {"current_steps": 20555, "total_steps": 38150, "loss": 0.427, "lr": 2.5979923978181787e-05, "epoch": 5.387942332896461, "percentage": 53.88, "elapsed_time": "0:34:34", "remaining_time": "0:29:35", "throughput": 2653.3, "total_tokens": 5504352} {"current_steps": 20560, "total_steps": 38150, "loss": 0.246, "lr": 2.5968495383415742e-05, "epoch": 5.389252948885977, "percentage": 53.89, "elapsed_time": "0:34:34", "remaining_time": "0:29:35", "throughput": 2653.4, "total_tokens": 5505808} {"current_steps": 20565, "total_steps": 38150, "loss": 0.4701, "lr": 2.595706658594529e-05, "epoch": 5.3905635648754915, "percentage": 53.91, "elapsed_time": "0:34:35", "remaining_time": "0:29:34", "throughput": 2653.4, "total_tokens": 5506944} {"current_steps": 20570, "total_steps": 38150, "loss": 0.2782, "lr": 2.5945637588162452e-05, "epoch": 5.391874180865006, "percentage": 53.92, "elapsed_time": "0:34:35", "remaining_time": "0:29:34", "throughput": 2653.32, "total_tokens": 5507888} {"current_steps": 20575, "total_steps": 38150, "loss": 0.2405, "lr": 2.5934208392459304e-05, "epoch": 5.393184796854522, "percentage": 53.93, "elapsed_time": "0:34:36", "remaining_time": "0:29:33", "throughput": 2653.34, "total_tokens": 5509088} {"current_steps": 20580, "total_steps": 38150, "loss": 0.2678, "lr": 2.592277900122796e-05, "epoch": 5.394495412844036, "percentage": 53.94, "elapsed_time": "0:34:36", "remaining_time": "0:29:33", "throughput": 2653.4, "total_tokens": 5510448} {"current_steps": 20585, "total_steps": 38150, "loss": 0.3006, "lr": 2.5911349416860558e-05, "epoch": 5.395806028833552, "percentage": 53.96, "elapsed_time": "0:34:37", "remaining_time": "0:29:32", "throughput": 2653.47, "total_tokens": 5511728} {"current_steps": 20590, "total_steps": 38150, "loss": 0.292, "lr": 2.5899919641749286e-05, "epoch": 5.3971166448230665, "percentage": 53.97, "elapsed_time": "0:34:37", "remaining_time": "0:29:31", "throughput": 2653.48, "total_tokens": 5512880} {"current_steps": 20595, "total_steps": 38150, "loss": 0.3504, "lr": 2.588848967828641e-05, "epoch": 5.398427260812582, "percentage": 53.98, "elapsed_time": "0:34:38", "remaining_time": "0:29:31", "throughput": 2653.49, "total_tokens": 5514032} {"current_steps": 20600, "total_steps": 38150, "loss": 0.2407, "lr": 2.5877059528864168e-05, "epoch": 5.399737876802097, "percentage": 54.0, "elapsed_time": "0:34:38", "remaining_time": "0:29:30", "throughput": 2653.63, "total_tokens": 5515504} {"current_steps": 20605, "total_steps": 38150, "loss": 0.2971, "lr": 2.5865629195874886e-05, "epoch": 5.401048492791612, "percentage": 54.01, "elapsed_time": "0:34:38", "remaining_time": "0:29:30", "throughput": 2653.72, "total_tokens": 5516864} {"current_steps": 20610, "total_steps": 38150, "loss": 0.1821, "lr": 2.58541986817109e-05, "epoch": 5.402359108781127, "percentage": 54.02, "elapsed_time": "0:34:39", "remaining_time": "0:29:29", "throughput": 2653.85, "total_tokens": 5518384} {"current_steps": 20615, "total_steps": 38150, "loss": 0.325, "lr": 2.5842767988764615e-05, "epoch": 5.4036697247706424, "percentage": 54.04, "elapsed_time": "0:34:39", "remaining_time": "0:29:29", "throughput": 2653.93, "total_tokens": 5519696} {"current_steps": 20620, "total_steps": 38150, "loss": 0.3364, "lr": 2.5831337119428446e-05, "epoch": 5.404980340760157, "percentage": 54.05, "elapsed_time": "0:34:40", "remaining_time": "0:29:28", "throughput": 2653.91, "total_tokens": 5520800} {"current_steps": 20625, "total_steps": 38150, "loss": 0.3421, "lr": 2.5819906076094848e-05, "epoch": 5.406290956749673, "percentage": 54.06, "elapsed_time": "0:34:40", "remaining_time": "0:29:27", "throughput": 2653.92, "total_tokens": 5521968} {"current_steps": 20630, "total_steps": 38150, "loss": 0.3649, "lr": 2.5808474861156328e-05, "epoch": 5.407601572739187, "percentage": 54.08, "elapsed_time": "0:34:41", "remaining_time": "0:29:27", "throughput": 2653.9, "total_tokens": 5523024} {"current_steps": 20635, "total_steps": 38150, "loss": 0.3785, "lr": 2.5797043477005423e-05, "epoch": 5.408912188728703, "percentage": 54.09, "elapsed_time": "0:34:41", "remaining_time": "0:29:26", "throughput": 2653.9, "total_tokens": 5524224} {"current_steps": 20640, "total_steps": 38150, "loss": 0.3701, "lr": 2.5785611926034686e-05, "epoch": 5.4102228047182175, "percentage": 54.1, "elapsed_time": "0:34:41", "remaining_time": "0:29:26", "throughput": 2653.91, "total_tokens": 5525360} {"current_steps": 20645, "total_steps": 38150, "loss": 0.2321, "lr": 2.5774180210636728e-05, "epoch": 5.411533420707733, "percentage": 54.12, "elapsed_time": "0:34:42", "remaining_time": "0:29:25", "throughput": 2654.23, "total_tokens": 5527984} {"current_steps": 20650, "total_steps": 38150, "loss": 0.367, "lr": 2.5762748333204196e-05, "epoch": 5.412844036697248, "percentage": 54.13, "elapsed_time": "0:34:43", "remaining_time": "0:29:25", "throughput": 2654.4, "total_tokens": 5529744} {"current_steps": 20655, "total_steps": 38150, "loss": 0.2189, "lr": 2.575131629612976e-05, "epoch": 5.414154652686763, "percentage": 54.14, "elapsed_time": "0:34:43", "remaining_time": "0:29:24", "throughput": 2654.47, "total_tokens": 5531152} {"current_steps": 20660, "total_steps": 38150, "loss": 0.2665, "lr": 2.5739884101806117e-05, "epoch": 5.415465268676278, "percentage": 54.15, "elapsed_time": "0:34:44", "remaining_time": "0:29:24", "throughput": 2654.56, "total_tokens": 5532592} {"current_steps": 20665, "total_steps": 38150, "loss": 0.2734, "lr": 2.5728451752626008e-05, "epoch": 5.4167758846657925, "percentage": 54.17, "elapsed_time": "0:34:44", "remaining_time": "0:29:23", "throughput": 2654.59, "total_tokens": 5533824} {"current_steps": 20670, "total_steps": 38150, "loss": 0.499, "lr": 2.571701925098221e-05, "epoch": 5.418086500655308, "percentage": 54.18, "elapsed_time": "0:34:45", "remaining_time": "0:29:23", "throughput": 2654.85, "total_tokens": 5535792} {"current_steps": 20675, "total_steps": 38150, "loss": 0.2957, "lr": 2.5705586599267518e-05, "epoch": 5.419397116644823, "percentage": 54.19, "elapsed_time": "0:34:45", "remaining_time": "0:29:22", "throughput": 2655.02, "total_tokens": 5537456} {"current_steps": 20680, "total_steps": 38150, "loss": 0.288, "lr": 2.569415379987477e-05, "epoch": 5.420707732634338, "percentage": 54.21, "elapsed_time": "0:34:46", "remaining_time": "0:29:22", "throughput": 2655.07, "total_tokens": 5538688} {"current_steps": 20685, "total_steps": 38150, "loss": 0.2911, "lr": 2.5682720855196836e-05, "epoch": 5.422018348623853, "percentage": 54.22, "elapsed_time": "0:34:46", "remaining_time": "0:29:21", "throughput": 2655.26, "total_tokens": 5540464} {"current_steps": 20690, "total_steps": 38150, "loss": 0.3399, "lr": 2.56712877676266e-05, "epoch": 5.423328964613368, "percentage": 54.23, "elapsed_time": "0:34:47", "remaining_time": "0:29:21", "throughput": 2655.2, "total_tokens": 5541440} {"current_steps": 20695, "total_steps": 38150, "loss": 0.3346, "lr": 2.5659854539556998e-05, "epoch": 5.424639580602883, "percentage": 54.25, "elapsed_time": "0:34:47", "remaining_time": "0:29:20", "throughput": 2655.23, "total_tokens": 5542640} {"current_steps": 20700, "total_steps": 38150, "loss": 0.3151, "lr": 2.5648421173380977e-05, "epoch": 5.425950196592399, "percentage": 54.26, "elapsed_time": "0:34:47", "remaining_time": "0:29:20", "throughput": 2655.27, "total_tokens": 5543920} {"current_steps": 20705, "total_steps": 38150, "loss": 0.2786, "lr": 2.5636987671491525e-05, "epoch": 5.427260812581913, "percentage": 54.27, "elapsed_time": "0:34:48", "remaining_time": "0:29:19", "throughput": 2655.31, "total_tokens": 5545152} {"current_steps": 20710, "total_steps": 38150, "loss": 0.291, "lr": 2.562555403628166e-05, "epoch": 5.428571428571429, "percentage": 54.29, "elapsed_time": "0:34:48", "remaining_time": "0:29:18", "throughput": 2655.3, "total_tokens": 5546336} {"current_steps": 20715, "total_steps": 38150, "loss": 0.2214, "lr": 2.5614120270144415e-05, "epoch": 5.4298820445609435, "percentage": 54.3, "elapsed_time": "0:34:49", "remaining_time": "0:29:18", "throughput": 2655.44, "total_tokens": 5547824} {"current_steps": 20720, "total_steps": 38150, "loss": 0.4341, "lr": 2.5602686375472856e-05, "epoch": 5.431192660550459, "percentage": 54.31, "elapsed_time": "0:34:49", "remaining_time": "0:29:17", "throughput": 2655.44, "total_tokens": 5548976} {"current_steps": 20725, "total_steps": 38150, "loss": 0.5787, "lr": 2.5591252354660083e-05, "epoch": 5.432503276539974, "percentage": 54.33, "elapsed_time": "0:34:50", "remaining_time": "0:29:17", "throughput": 2655.46, "total_tokens": 5550160} {"current_steps": 20730, "total_steps": 38150, "loss": 0.3372, "lr": 2.557981821009921e-05, "epoch": 5.433813892529489, "percentage": 54.34, "elapsed_time": "0:34:50", "remaining_time": "0:29:16", "throughput": 2655.46, "total_tokens": 5551280} {"current_steps": 20735, "total_steps": 38150, "loss": 0.2054, "lr": 2.556838394418339e-05, "epoch": 5.435124508519004, "percentage": 54.35, "elapsed_time": "0:34:50", "remaining_time": "0:29:16", "throughput": 2655.44, "total_tokens": 5552480} {"current_steps": 20740, "total_steps": 38150, "loss": 0.1989, "lr": 2.5556949559305786e-05, "epoch": 5.436435124508519, "percentage": 54.36, "elapsed_time": "0:34:51", "remaining_time": "0:29:15", "throughput": 2655.49, "total_tokens": 5553840} {"current_steps": 20745, "total_steps": 38150, "loss": 0.2127, "lr": 2.554551505785961e-05, "epoch": 5.437745740498034, "percentage": 54.38, "elapsed_time": "0:34:51", "remaining_time": "0:29:15", "throughput": 2655.57, "total_tokens": 5555248} {"current_steps": 20750, "total_steps": 38150, "loss": 0.2971, "lr": 2.553408044223807e-05, "epoch": 5.43905635648755, "percentage": 54.39, "elapsed_time": "0:34:52", "remaining_time": "0:29:14", "throughput": 2655.62, "total_tokens": 5556592} {"current_steps": 20755, "total_steps": 38150, "loss": 0.3289, "lr": 2.5522645714834426e-05, "epoch": 5.440366972477064, "percentage": 54.4, "elapsed_time": "0:34:52", "remaining_time": "0:29:14", "throughput": 2655.65, "total_tokens": 5557888} {"current_steps": 20760, "total_steps": 38150, "loss": 0.2829, "lr": 2.551121087804192e-05, "epoch": 5.441677588466579, "percentage": 54.42, "elapsed_time": "0:34:53", "remaining_time": "0:29:13", "throughput": 2655.65, "total_tokens": 5559024} {"current_steps": 20765, "total_steps": 38150, "loss": 0.2284, "lr": 2.5499775934253865e-05, "epoch": 5.442988204456094, "percentage": 54.43, "elapsed_time": "0:34:53", "remaining_time": "0:29:12", "throughput": 2655.6, "total_tokens": 5560048} {"current_steps": 20770, "total_steps": 38150, "loss": 0.274, "lr": 2.5488340885863578e-05, "epoch": 5.444298820445609, "percentage": 54.44, "elapsed_time": "0:34:54", "remaining_time": "0:29:12", "throughput": 2655.62, "total_tokens": 5561296} {"current_steps": 20775, "total_steps": 38150, "loss": 0.352, "lr": 2.547690573526439e-05, "epoch": 5.445609436435125, "percentage": 54.46, "elapsed_time": "0:34:54", "remaining_time": "0:29:11", "throughput": 2655.84, "total_tokens": 5563136} {"current_steps": 20780, "total_steps": 38150, "loss": 0.2924, "lr": 2.546547048484965e-05, "epoch": 5.446920052424639, "percentage": 54.47, "elapsed_time": "0:34:55", "remaining_time": "0:29:11", "throughput": 2655.93, "total_tokens": 5564560} {"current_steps": 20785, "total_steps": 38150, "loss": 0.3182, "lr": 2.545403513701274e-05, "epoch": 5.448230668414155, "percentage": 54.48, "elapsed_time": "0:34:55", "remaining_time": "0:29:10", "throughput": 2655.94, "total_tokens": 5565696} {"current_steps": 20790, "total_steps": 38150, "loss": 0.3303, "lr": 2.544259969414706e-05, "epoch": 5.4495412844036695, "percentage": 54.5, "elapsed_time": "0:34:56", "remaining_time": "0:29:10", "throughput": 2656.11, "total_tokens": 5567296} {"current_steps": 20795, "total_steps": 38150, "loss": 0.3427, "lr": 2.543116415864603e-05, "epoch": 5.450851900393185, "percentage": 54.51, "elapsed_time": "0:34:56", "remaining_time": "0:29:09", "throughput": 2656.21, "total_tokens": 5568752} {"current_steps": 20800, "total_steps": 38150, "loss": 0.2112, "lr": 2.541972853290309e-05, "epoch": 5.4521625163827, "percentage": 54.52, "elapsed_time": "0:34:56", "remaining_time": "0:29:09", "throughput": 2656.22, "total_tokens": 5569904} {"current_steps": 20805, "total_steps": 38150, "loss": 0.3957, "lr": 2.540829281931169e-05, "epoch": 5.453473132372215, "percentage": 54.53, "elapsed_time": "0:34:57", "remaining_time": "0:29:08", "throughput": 2656.37, "total_tokens": 5571568} {"current_steps": 20810, "total_steps": 38150, "loss": 0.3162, "lr": 2.5396857020265307e-05, "epoch": 5.45478374836173, "percentage": 54.55, "elapsed_time": "0:34:57", "remaining_time": "0:29:08", "throughput": 2656.36, "total_tokens": 5572704} {"current_steps": 20815, "total_steps": 38150, "loss": 0.3776, "lr": 2.538542113815744e-05, "epoch": 5.456094364351245, "percentage": 54.56, "elapsed_time": "0:34:58", "remaining_time": "0:29:07", "throughput": 2656.56, "total_tokens": 5574576} {"current_steps": 20820, "total_steps": 38150, "loss": 0.2439, "lr": 2.5373985175381594e-05, "epoch": 5.45740498034076, "percentage": 54.57, "elapsed_time": "0:34:58", "remaining_time": "0:29:07", "throughput": 2656.54, "total_tokens": 5575648} {"current_steps": 20825, "total_steps": 38150, "loss": 0.2243, "lr": 2.536254913433129e-05, "epoch": 5.458715596330276, "percentage": 54.59, "elapsed_time": "0:34:59", "remaining_time": "0:29:06", "throughput": 2656.54, "total_tokens": 5576784} {"current_steps": 20830, "total_steps": 38150, "loss": 0.3362, "lr": 2.535111301740009e-05, "epoch": 5.46002621231979, "percentage": 54.6, "elapsed_time": "0:34:59", "remaining_time": "0:29:05", "throughput": 2656.53, "total_tokens": 5577920} {"current_steps": 20835, "total_steps": 38150, "loss": 0.4032, "lr": 2.5339676826981534e-05, "epoch": 5.461336828309306, "percentage": 54.61, "elapsed_time": "0:35:00", "remaining_time": "0:29:05", "throughput": 2656.59, "total_tokens": 5579280} {"current_steps": 20840, "total_steps": 38150, "loss": 0.3308, "lr": 2.532824056546921e-05, "epoch": 5.46264744429882, "percentage": 54.63, "elapsed_time": "0:35:00", "remaining_time": "0:29:05", "throughput": 2656.99, "total_tokens": 5582000} {"current_steps": 20845, "total_steps": 38150, "loss": 0.2827, "lr": 2.531680423525669e-05, "epoch": 5.463958060288336, "percentage": 54.64, "elapsed_time": "0:35:01", "remaining_time": "0:29:04", "throughput": 2657.04, "total_tokens": 5583264} {"current_steps": 20850, "total_steps": 38150, "loss": 0.2765, "lr": 2.5305367838737608e-05, "epoch": 5.465268676277851, "percentage": 54.65, "elapsed_time": "0:35:01", "remaining_time": "0:29:03", "throughput": 2656.99, "total_tokens": 5584304} {"current_steps": 20855, "total_steps": 38150, "loss": 0.3439, "lr": 2.5293931378305558e-05, "epoch": 5.466579292267365, "percentage": 54.67, "elapsed_time": "0:35:02", "remaining_time": "0:29:03", "throughput": 2657.11, "total_tokens": 5585824} {"current_steps": 20860, "total_steps": 38150, "loss": 0.3552, "lr": 2.5282494856354176e-05, "epoch": 5.467889908256881, "percentage": 54.68, "elapsed_time": "0:35:02", "remaining_time": "0:29:02", "throughput": 2657.19, "total_tokens": 5587152} {"current_steps": 20865, "total_steps": 38150, "loss": 0.2629, "lr": 2.5271058275277117e-05, "epoch": 5.4692005242463955, "percentage": 54.69, "elapsed_time": "0:35:03", "remaining_time": "0:29:02", "throughput": 2657.24, "total_tokens": 5588368} {"current_steps": 20870, "total_steps": 38150, "loss": 0.2961, "lr": 2.5259621637468016e-05, "epoch": 5.470511140235911, "percentage": 54.71, "elapsed_time": "0:35:03", "remaining_time": "0:29:01", "throughput": 2657.39, "total_tokens": 5590128} {"current_steps": 20875, "total_steps": 38150, "loss": 0.3829, "lr": 2.5248184945320563e-05, "epoch": 5.471821756225426, "percentage": 54.72, "elapsed_time": "0:35:04", "remaining_time": "0:29:01", "throughput": 2657.53, "total_tokens": 5591712} {"current_steps": 20880, "total_steps": 38150, "loss": 0.3389, "lr": 2.5236748201228428e-05, "epoch": 5.473132372214941, "percentage": 54.73, "elapsed_time": "0:35:04", "remaining_time": "0:29:00", "throughput": 2657.54, "total_tokens": 5592880} {"current_steps": 20885, "total_steps": 38150, "loss": 0.2155, "lr": 2.5225311407585306e-05, "epoch": 5.474442988204456, "percentage": 54.74, "elapsed_time": "0:35:04", "remaining_time": "0:29:00", "throughput": 2657.57, "total_tokens": 5594064} {"current_steps": 20890, "total_steps": 38150, "loss": 0.308, "lr": 2.5213874566784902e-05, "epoch": 5.475753604193971, "percentage": 54.76, "elapsed_time": "0:35:05", "remaining_time": "0:28:59", "throughput": 2657.64, "total_tokens": 5595344} {"current_steps": 20895, "total_steps": 38150, "loss": 0.3393, "lr": 2.5202437681220907e-05, "epoch": 5.477064220183486, "percentage": 54.77, "elapsed_time": "0:35:05", "remaining_time": "0:28:58", "throughput": 2657.67, "total_tokens": 5596576} {"current_steps": 20900, "total_steps": 38150, "loss": 0.2954, "lr": 2.5191000753287064e-05, "epoch": 5.478374836173002, "percentage": 54.78, "elapsed_time": "0:35:06", "remaining_time": "0:28:58", "throughput": 2657.68, "total_tokens": 5597712} {"current_steps": 20905, "total_steps": 38150, "loss": 0.3336, "lr": 2.5179563785377088e-05, "epoch": 5.479685452162516, "percentage": 54.8, "elapsed_time": "0:35:06", "remaining_time": "0:28:57", "throughput": 2657.68, "total_tokens": 5598848} {"current_steps": 20910, "total_steps": 38150, "loss": 0.38, "lr": 2.5168126779884727e-05, "epoch": 5.480996068152032, "percentage": 54.81, "elapsed_time": "0:35:07", "remaining_time": "0:28:57", "throughput": 2657.79, "total_tokens": 5600336} {"current_steps": 20915, "total_steps": 38150, "loss": 0.3326, "lr": 2.5156689739203714e-05, "epoch": 5.482306684141546, "percentage": 54.82, "elapsed_time": "0:35:07", "remaining_time": "0:28:56", "throughput": 2657.76, "total_tokens": 5601392} {"current_steps": 20920, "total_steps": 38150, "loss": 0.3166, "lr": 2.5145252665727815e-05, "epoch": 5.483617300131062, "percentage": 54.84, "elapsed_time": "0:35:08", "remaining_time": "0:28:56", "throughput": 2657.9, "total_tokens": 5602864} {"current_steps": 20925, "total_steps": 38150, "loss": 0.2527, "lr": 2.5133815561850782e-05, "epoch": 5.484927916120577, "percentage": 54.85, "elapsed_time": "0:35:08", "remaining_time": "0:28:55", "throughput": 2657.9, "total_tokens": 5604016} {"current_steps": 20930, "total_steps": 38150, "loss": 0.2561, "lr": 2.5122378429966387e-05, "epoch": 5.486238532110092, "percentage": 54.86, "elapsed_time": "0:35:08", "remaining_time": "0:28:55", "throughput": 2657.88, "total_tokens": 5605120} {"current_steps": 20935, "total_steps": 38150, "loss": 0.3364, "lr": 2.511094127246839e-05, "epoch": 5.487549148099607, "percentage": 54.88, "elapsed_time": "0:35:09", "remaining_time": "0:28:54", "throughput": 2657.89, "total_tokens": 5606256} {"current_steps": 20940, "total_steps": 38150, "loss": 0.1692, "lr": 2.5099504091750585e-05, "epoch": 5.488859764089122, "percentage": 54.89, "elapsed_time": "0:35:09", "remaining_time": "0:28:53", "throughput": 2657.91, "total_tokens": 5607424} {"current_steps": 20945, "total_steps": 38150, "loss": 0.491, "lr": 2.508806689020674e-05, "epoch": 5.490170380078637, "percentage": 54.9, "elapsed_time": "0:35:10", "remaining_time": "0:28:53", "throughput": 2657.88, "total_tokens": 5608528} {"current_steps": 20950, "total_steps": 38150, "loss": 0.3308, "lr": 2.5076629670230655e-05, "epoch": 5.491480996068152, "percentage": 54.91, "elapsed_time": "0:35:10", "remaining_time": "0:28:52", "throughput": 2657.92, "total_tokens": 5609824} {"current_steps": 20955, "total_steps": 38150, "loss": 0.2936, "lr": 2.5065192434216106e-05, "epoch": 5.492791612057667, "percentage": 54.93, "elapsed_time": "0:35:11", "remaining_time": "0:28:52", "throughput": 2657.92, "total_tokens": 5610944} {"current_steps": 20960, "total_steps": 38150, "loss": 0.1303, "lr": 2.5053755184556886e-05, "epoch": 5.494102228047182, "percentage": 54.94, "elapsed_time": "0:35:11", "remaining_time": "0:28:51", "throughput": 2657.9, "total_tokens": 5612016} {"current_steps": 20965, "total_steps": 38150, "loss": 0.3344, "lr": 2.5042317923646812e-05, "epoch": 5.495412844036697, "percentage": 54.95, "elapsed_time": "0:35:11", "remaining_time": "0:28:51", "throughput": 2658.05, "total_tokens": 5613632} {"current_steps": 20970, "total_steps": 38150, "loss": 0.3584, "lr": 2.5030880653879667e-05, "epoch": 5.496723460026212, "percentage": 54.97, "elapsed_time": "0:35:12", "remaining_time": "0:28:50", "throughput": 2658.17, "total_tokens": 5615056} {"current_steps": 20975, "total_steps": 38150, "loss": 0.1738, "lr": 2.5019443377649247e-05, "epoch": 5.498034076015728, "percentage": 54.98, "elapsed_time": "0:35:12", "remaining_time": "0:28:50", "throughput": 2658.16, "total_tokens": 5616192} {"current_steps": 20980, "total_steps": 38150, "loss": 0.2844, "lr": 2.500800609734937e-05, "epoch": 5.499344692005242, "percentage": 54.99, "elapsed_time": "0:35:13", "remaining_time": "0:28:49", "throughput": 2658.15, "total_tokens": 5617296} {"current_steps": 20985, "total_steps": 38150, "loss": 0.3973, "lr": 2.4996568815373827e-05, "epoch": 5.500655307994758, "percentage": 55.01, "elapsed_time": "0:35:13", "remaining_time": "0:28:48", "throughput": 2658.21, "total_tokens": 5618656} {"current_steps": 20988, "total_steps": 38150, "eval_loss": 0.5853312611579895, "epoch": 5.501441677588467, "percentage": 55.01, "elapsed_time": "0:35:30", "remaining_time": "0:29:02", "throughput": 2637.33, "total_tokens": 5619904} {"current_steps": 20990, "total_steps": 38150, "loss": 0.4481, "lr": 2.4985131534116422e-05, "epoch": 5.501965923984272, "percentage": 55.02, "elapsed_time": "0:35:32", "remaining_time": "0:29:03", "throughput": 2635.75, "total_tokens": 5620480} {"current_steps": 20995, "total_steps": 38150, "loss": 0.4728, "lr": 2.4973694255970966e-05, "epoch": 5.503276539973788, "percentage": 55.03, "elapsed_time": "0:35:32", "remaining_time": "0:29:02", "throughput": 2635.77, "total_tokens": 5621648} {"current_steps": 21000, "total_steps": 38150, "loss": 0.3087, "lr": 2.4962256983331254e-05, "epoch": 5.504587155963303, "percentage": 55.05, "elapsed_time": "0:35:33", "remaining_time": "0:29:02", "throughput": 2635.75, "total_tokens": 5622768} {"current_steps": 21005, "total_steps": 38150, "loss": 0.2689, "lr": 2.4950819718591094e-05, "epoch": 5.505897771952818, "percentage": 55.06, "elapsed_time": "0:35:33", "remaining_time": "0:29:01", "throughput": 2635.81, "total_tokens": 5624048} {"current_steps": 21010, "total_steps": 38150, "loss": 0.2273, "lr": 2.493938246414428e-05, "epoch": 5.507208387942333, "percentage": 55.07, "elapsed_time": "0:35:34", "remaining_time": "0:29:01", "throughput": 2635.86, "total_tokens": 5625344} {"current_steps": 21015, "total_steps": 38150, "loss": 0.3489, "lr": 2.4927945222384613e-05, "epoch": 5.508519003931848, "percentage": 55.09, "elapsed_time": "0:35:34", "remaining_time": "0:29:00", "throughput": 2635.86, "total_tokens": 5626480} {"current_steps": 21020, "total_steps": 38150, "loss": 0.2336, "lr": 2.491650799570588e-05, "epoch": 5.509829619921363, "percentage": 55.1, "elapsed_time": "0:35:35", "remaining_time": "0:28:59", "throughput": 2635.89, "total_tokens": 5627744} {"current_steps": 21025, "total_steps": 38150, "loss": 0.2922, "lr": 2.4905070786501887e-05, "epoch": 5.511140235910878, "percentage": 55.11, "elapsed_time": "0:35:35", "remaining_time": "0:28:59", "throughput": 2635.94, "total_tokens": 5629008} {"current_steps": 21030, "total_steps": 38150, "loss": 0.3577, "lr": 2.4893633597166405e-05, "epoch": 5.512450851900393, "percentage": 55.12, "elapsed_time": "0:35:35", "remaining_time": "0:28:58", "throughput": 2635.94, "total_tokens": 5630144} {"current_steps": 21035, "total_steps": 38150, "loss": 0.3406, "lr": 2.4882196430093233e-05, "epoch": 5.513761467889909, "percentage": 55.14, "elapsed_time": "0:35:36", "remaining_time": "0:28:58", "throughput": 2636.16, "total_tokens": 5632112} {"current_steps": 21040, "total_steps": 38150, "loss": 0.322, "lr": 2.4870759287676143e-05, "epoch": 5.515072083879423, "percentage": 55.15, "elapsed_time": "0:35:36", "remaining_time": "0:28:57", "throughput": 2636.31, "total_tokens": 5633664} {"current_steps": 21045, "total_steps": 38150, "loss": 0.3308, "lr": 2.485932217230892e-05, "epoch": 5.516382699868938, "percentage": 55.16, "elapsed_time": "0:35:37", "remaining_time": "0:28:57", "throughput": 2636.36, "total_tokens": 5634992} {"current_steps": 21050, "total_steps": 38150, "loss": 0.2945, "lr": 2.4847885086385314e-05, "epoch": 5.517693315858454, "percentage": 55.18, "elapsed_time": "0:35:37", "remaining_time": "0:28:56", "throughput": 2636.32, "total_tokens": 5636000} {"current_steps": 21055, "total_steps": 38150, "loss": 0.3996, "lr": 2.4836448032299097e-05, "epoch": 5.519003931847968, "percentage": 55.19, "elapsed_time": "0:35:38", "remaining_time": "0:28:56", "throughput": 2636.31, "total_tokens": 5637088} {"current_steps": 21060, "total_steps": 38150, "loss": 0.3173, "lr": 2.4825011012444026e-05, "epoch": 5.520314547837484, "percentage": 55.2, "elapsed_time": "0:35:38", "remaining_time": "0:28:55", "throughput": 2636.32, "total_tokens": 5638240} {"current_steps": 21065, "total_steps": 38150, "loss": 0.3687, "lr": 2.4813574029213853e-05, "epoch": 5.521625163826998, "percentage": 55.22, "elapsed_time": "0:35:39", "remaining_time": "0:28:55", "throughput": 2636.48, "total_tokens": 5639952} {"current_steps": 21070, "total_steps": 38150, "loss": 0.3523, "lr": 2.4802137085002306e-05, "epoch": 5.522935779816514, "percentage": 55.23, "elapsed_time": "0:35:39", "remaining_time": "0:28:54", "throughput": 2636.61, "total_tokens": 5641504} {"current_steps": 21075, "total_steps": 38150, "loss": 0.6207, "lr": 2.479070018220313e-05, "epoch": 5.524246395806029, "percentage": 55.24, "elapsed_time": "0:35:40", "remaining_time": "0:28:53", "throughput": 2636.56, "total_tokens": 5642512} {"current_steps": 21080, "total_steps": 38150, "loss": 0.2492, "lr": 2.4779263323210036e-05, "epoch": 5.525557011795544, "percentage": 55.26, "elapsed_time": "0:35:40", "remaining_time": "0:28:53", "throughput": 2636.61, "total_tokens": 5643776} {"current_steps": 21085, "total_steps": 38150, "loss": 0.2897, "lr": 2.4767826510416753e-05, "epoch": 5.526867627785059, "percentage": 55.27, "elapsed_time": "0:35:41", "remaining_time": "0:28:52", "throughput": 2636.83, "total_tokens": 5645536} {"current_steps": 21090, "total_steps": 38150, "loss": 0.2118, "lr": 2.4756389746216974e-05, "epoch": 5.528178243774574, "percentage": 55.28, "elapsed_time": "0:35:41", "remaining_time": "0:28:52", "throughput": 2636.93, "total_tokens": 5646976} {"current_steps": 21095, "total_steps": 38150, "loss": 0.2537, "lr": 2.4744953033004408e-05, "epoch": 5.529488859764089, "percentage": 55.29, "elapsed_time": "0:35:41", "remaining_time": "0:28:51", "throughput": 2637.02, "total_tokens": 5648368} {"current_steps": 21100, "total_steps": 38150, "loss": 0.3028, "lr": 2.4733516373172728e-05, "epoch": 5.5307994757536045, "percentage": 55.31, "elapsed_time": "0:35:42", "remaining_time": "0:28:51", "throughput": 2637.12, "total_tokens": 5649824} {"current_steps": 21105, "total_steps": 38150, "loss": 0.3143, "lr": 2.4722079769115617e-05, "epoch": 5.532110091743119, "percentage": 55.32, "elapsed_time": "0:35:42", "remaining_time": "0:28:50", "throughput": 2637.12, "total_tokens": 5650976} {"current_steps": 21110, "total_steps": 38150, "loss": 0.3593, "lr": 2.4710643223226722e-05, "epoch": 5.533420707732635, "percentage": 55.33, "elapsed_time": "0:35:43", "remaining_time": "0:28:50", "throughput": 2637.26, "total_tokens": 5652608} {"current_steps": 21115, "total_steps": 38150, "loss": 0.3141, "lr": 2.4699206737899707e-05, "epoch": 5.534731323722149, "percentage": 55.35, "elapsed_time": "0:35:43", "remaining_time": "0:28:49", "throughput": 2637.26, "total_tokens": 5653808} {"current_steps": 21120, "total_steps": 38150, "loss": 0.3716, "lr": 2.4687770315528195e-05, "epoch": 5.536041939711664, "percentage": 55.36, "elapsed_time": "0:35:44", "remaining_time": "0:28:49", "throughput": 2637.34, "total_tokens": 5655200} {"current_steps": 21125, "total_steps": 38150, "loss": 0.3615, "lr": 2.4676333958505827e-05, "epoch": 5.53735255570118, "percentage": 55.37, "elapsed_time": "0:35:44", "remaining_time": "0:28:48", "throughput": 2637.29, "total_tokens": 5656192} {"current_steps": 21130, "total_steps": 38150, "loss": 0.2982, "lr": 2.4664897669226193e-05, "epoch": 5.538663171690695, "percentage": 55.39, "elapsed_time": "0:35:45", "remaining_time": "0:28:47", "throughput": 2637.31, "total_tokens": 5657472} {"current_steps": 21135, "total_steps": 38150, "loss": 0.3162, "lr": 2.46534614500829e-05, "epoch": 5.53997378768021, "percentage": 55.4, "elapsed_time": "0:35:45", "remaining_time": "0:28:47", "throughput": 2637.24, "total_tokens": 5658416} {"current_steps": 21140, "total_steps": 38150, "loss": 0.2985, "lr": 2.4642025303469527e-05, "epoch": 5.541284403669724, "percentage": 55.41, "elapsed_time": "0:35:46", "remaining_time": "0:28:46", "throughput": 2637.3, "total_tokens": 5659776} {"current_steps": 21145, "total_steps": 38150, "loss": 0.2848, "lr": 2.4630589231779633e-05, "epoch": 5.54259501965924, "percentage": 55.43, "elapsed_time": "0:35:46", "remaining_time": "0:28:46", "throughput": 2637.31, "total_tokens": 5660912} {"current_steps": 21150, "total_steps": 38150, "loss": 0.338, "lr": 2.4619153237406782e-05, "epoch": 5.543905635648755, "percentage": 55.44, "elapsed_time": "0:35:47", "remaining_time": "0:28:45", "throughput": 2637.7, "total_tokens": 5663440} {"current_steps": 21155, "total_steps": 38150, "loss": 0.26, "lr": 2.4607717322744498e-05, "epoch": 5.54521625163827, "percentage": 55.45, "elapsed_time": "0:35:47", "remaining_time": "0:28:45", "throughput": 2637.85, "total_tokens": 5664960} {"current_steps": 21160, "total_steps": 38150, "loss": 0.4569, "lr": 2.4596281490186303e-05, "epoch": 5.546526867627785, "percentage": 55.47, "elapsed_time": "0:35:47", "remaining_time": "0:28:44", "throughput": 2637.83, "total_tokens": 5666048} {"current_steps": 21165, "total_steps": 38150, "loss": 0.1526, "lr": 2.4584845742125696e-05, "epoch": 5.5478374836173, "percentage": 55.48, "elapsed_time": "0:35:48", "remaining_time": "0:28:44", "throughput": 2637.95, "total_tokens": 5667616} {"current_steps": 21170, "total_steps": 38150, "loss": 0.2797, "lr": 2.457341008095615e-05, "epoch": 5.549148099606815, "percentage": 55.49, "elapsed_time": "0:35:48", "remaining_time": "0:28:43", "throughput": 2638.0, "total_tokens": 5668880} {"current_steps": 21175, "total_steps": 38150, "loss": 0.3399, "lr": 2.4561974509071143e-05, "epoch": 5.5504587155963305, "percentage": 55.5, "elapsed_time": "0:35:49", "remaining_time": "0:28:43", "throughput": 2638.02, "total_tokens": 5670032} {"current_steps": 21180, "total_steps": 38150, "loss": 0.3157, "lr": 2.4550539028864113e-05, "epoch": 5.551769331585845, "percentage": 55.52, "elapsed_time": "0:35:49", "remaining_time": "0:28:42", "throughput": 2638.05, "total_tokens": 5671280} {"current_steps": 21185, "total_steps": 38150, "loss": 0.3491, "lr": 2.4539103642728494e-05, "epoch": 5.553079947575361, "percentage": 55.53, "elapsed_time": "0:35:50", "remaining_time": "0:28:41", "throughput": 2638.1, "total_tokens": 5672544} {"current_steps": 21190, "total_steps": 38150, "loss": 0.24, "lr": 2.4527668353057683e-05, "epoch": 5.554390563564875, "percentage": 55.54, "elapsed_time": "0:35:50", "remaining_time": "0:28:41", "throughput": 2638.15, "total_tokens": 5673792} {"current_steps": 21195, "total_steps": 38150, "loss": 0.4043, "lr": 2.4516233162245063e-05, "epoch": 5.555701179554391, "percentage": 55.56, "elapsed_time": "0:35:51", "remaining_time": "0:28:40", "throughput": 2638.08, "total_tokens": 5674848} {"current_steps": 21200, "total_steps": 38150, "loss": 0.2824, "lr": 2.450479807268401e-05, "epoch": 5.557011795543906, "percentage": 55.57, "elapsed_time": "0:35:51", "remaining_time": "0:28:40", "throughput": 2638.12, "total_tokens": 5676064} {"current_steps": 21205, "total_steps": 38150, "loss": 0.3179, "lr": 2.449336308676786e-05, "epoch": 5.558322411533421, "percentage": 55.58, "elapsed_time": "0:35:51", "remaining_time": "0:28:39", "throughput": 2638.23, "total_tokens": 5677472} {"current_steps": 21210, "total_steps": 38150, "loss": 0.4196, "lr": 2.4481928206889946e-05, "epoch": 5.559633027522936, "percentage": 55.6, "elapsed_time": "0:35:52", "remaining_time": "0:28:39", "throughput": 2638.3, "total_tokens": 5678752} {"current_steps": 21215, "total_steps": 38150, "loss": 0.458, "lr": 2.4470493435443558e-05, "epoch": 5.56094364351245, "percentage": 55.61, "elapsed_time": "0:35:52", "remaining_time": "0:28:38", "throughput": 2638.43, "total_tokens": 5680288} {"current_steps": 21220, "total_steps": 38150, "loss": 0.3049, "lr": 2.4459058774821992e-05, "epoch": 5.562254259501966, "percentage": 55.62, "elapsed_time": "0:35:53", "remaining_time": "0:28:38", "throughput": 2638.39, "total_tokens": 5681360} {"current_steps": 21225, "total_steps": 38150, "loss": 0.3133, "lr": 2.4447624227418482e-05, "epoch": 5.5635648754914815, "percentage": 55.64, "elapsed_time": "0:35:53", "remaining_time": "0:28:37", "throughput": 2638.38, "total_tokens": 5682432} {"current_steps": 21230, "total_steps": 38150, "loss": 0.2163, "lr": 2.4436189795626262e-05, "epoch": 5.564875491480996, "percentage": 55.65, "elapsed_time": "0:35:54", "remaining_time": "0:28:36", "throughput": 2638.48, "total_tokens": 5683808} {"current_steps": 21235, "total_steps": 38150, "loss": 0.215, "lr": 2.442475548183855e-05, "epoch": 5.566186107470511, "percentage": 55.66, "elapsed_time": "0:35:54", "remaining_time": "0:28:36", "throughput": 2638.48, "total_tokens": 5684928} {"current_steps": 21240, "total_steps": 38150, "loss": 0.2289, "lr": 2.4413321288448518e-05, "epoch": 5.567496723460026, "percentage": 55.67, "elapsed_time": "0:35:55", "remaining_time": "0:28:35", "throughput": 2638.39, "total_tokens": 5685840} {"current_steps": 21245, "total_steps": 38150, "loss": 0.4088, "lr": 2.440188721784933e-05, "epoch": 5.568807339449541, "percentage": 55.69, "elapsed_time": "0:35:55", "remaining_time": "0:28:35", "throughput": 2638.4, "total_tokens": 5687008} {"current_steps": 21250, "total_steps": 38150, "loss": 0.2381, "lr": 2.4390453272434115e-05, "epoch": 5.5701179554390565, "percentage": 55.7, "elapsed_time": "0:35:55", "remaining_time": "0:28:34", "throughput": 2638.48, "total_tokens": 5688400} {"current_steps": 21255, "total_steps": 38150, "loss": 0.3395, "lr": 2.4379019454595973e-05, "epoch": 5.571428571428571, "percentage": 55.71, "elapsed_time": "0:35:56", "remaining_time": "0:28:34", "throughput": 2638.55, "total_tokens": 5689712} {"current_steps": 21260, "total_steps": 38150, "loss": 0.3316, "lr": 2.436758576672798e-05, "epoch": 5.572739187418087, "percentage": 55.73, "elapsed_time": "0:35:56", "remaining_time": "0:28:33", "throughput": 2638.54, "total_tokens": 5690816} {"current_steps": 21265, "total_steps": 38150, "loss": 0.206, "lr": 2.4356152211223198e-05, "epoch": 5.574049803407601, "percentage": 55.74, "elapsed_time": "0:35:57", "remaining_time": "0:28:32", "throughput": 2638.59, "total_tokens": 5692032} {"current_steps": 21270, "total_steps": 38150, "loss": 0.3851, "lr": 2.434471879047465e-05, "epoch": 5.575360419397117, "percentage": 55.75, "elapsed_time": "0:35:57", "remaining_time": "0:28:32", "throughput": 2638.71, "total_tokens": 5693568} {"current_steps": 21275, "total_steps": 38150, "loss": 0.3263, "lr": 2.4333285506875322e-05, "epoch": 5.576671035386632, "percentage": 55.77, "elapsed_time": "0:35:58", "remaining_time": "0:28:31", "throughput": 2638.83, "total_tokens": 5695056} {"current_steps": 21280, "total_steps": 38150, "loss": 0.3219, "lr": 2.4321852362818195e-05, "epoch": 5.577981651376147, "percentage": 55.78, "elapsed_time": "0:35:58", "remaining_time": "0:28:31", "throughput": 2638.92, "total_tokens": 5696480} {"current_steps": 21285, "total_steps": 38150, "loss": 0.2641, "lr": 2.431041936069619e-05, "epoch": 5.579292267365662, "percentage": 55.79, "elapsed_time": "0:35:59", "remaining_time": "0:28:30", "throughput": 2638.94, "total_tokens": 5697632} {"current_steps": 21290, "total_steps": 38150, "loss": 0.4728, "lr": 2.4298986502902218e-05, "epoch": 5.580602883355177, "percentage": 55.81, "elapsed_time": "0:35:59", "remaining_time": "0:28:30", "throughput": 2638.94, "total_tokens": 5698752} {"current_steps": 21295, "total_steps": 38150, "loss": 0.3499, "lr": 2.4287553791829166e-05, "epoch": 5.581913499344692, "percentage": 55.82, "elapsed_time": "0:35:59", "remaining_time": "0:28:29", "throughput": 2639.01, "total_tokens": 5700192} {"current_steps": 21300, "total_steps": 38150, "loss": 0.1937, "lr": 2.4276121229869875e-05, "epoch": 5.5832241153342075, "percentage": 55.83, "elapsed_time": "0:36:00", "remaining_time": "0:28:29", "throughput": 2639.09, "total_tokens": 5701520} {"current_steps": 21305, "total_steps": 38150, "loss": 0.2655, "lr": 2.4264688819417155e-05, "epoch": 5.584534731323722, "percentage": 55.85, "elapsed_time": "0:36:00", "remaining_time": "0:28:28", "throughput": 2639.29, "total_tokens": 5703280} {"current_steps": 21310, "total_steps": 38150, "loss": 0.2037, "lr": 2.4253256562863795e-05, "epoch": 5.585845347313237, "percentage": 55.86, "elapsed_time": "0:36:01", "remaining_time": "0:28:28", "throughput": 2639.42, "total_tokens": 5704848} {"current_steps": 21315, "total_steps": 38150, "loss": 0.3529, "lr": 2.4241824462602546e-05, "epoch": 5.587155963302752, "percentage": 55.87, "elapsed_time": "0:36:01", "remaining_time": "0:28:27", "throughput": 2639.6, "total_tokens": 5706608} {"current_steps": 21320, "total_steps": 38150, "loss": 0.3494, "lr": 2.4230392521026123e-05, "epoch": 5.588466579292267, "percentage": 55.88, "elapsed_time": "0:36:02", "remaining_time": "0:28:26", "throughput": 2639.67, "total_tokens": 5707936} {"current_steps": 21325, "total_steps": 38150, "loss": 0.3191, "lr": 2.4218960740527218e-05, "epoch": 5.5897771952817825, "percentage": 55.9, "elapsed_time": "0:36:02", "remaining_time": "0:28:26", "throughput": 2639.73, "total_tokens": 5709200} {"current_steps": 21330, "total_steps": 38150, "loss": 0.2553, "lr": 2.4207529123498485e-05, "epoch": 5.591087811271297, "percentage": 55.91, "elapsed_time": "0:36:03", "remaining_time": "0:28:25", "throughput": 2639.74, "total_tokens": 5710320} {"current_steps": 21335, "total_steps": 38150, "loss": 0.2836, "lr": 2.4196097672332533e-05, "epoch": 5.592398427260813, "percentage": 55.92, "elapsed_time": "0:36:03", "remaining_time": "0:28:25", "throughput": 2639.87, "total_tokens": 5711888} {"current_steps": 21340, "total_steps": 38150, "loss": 0.4024, "lr": 2.4184666389421957e-05, "epoch": 5.593709043250327, "percentage": 55.94, "elapsed_time": "0:36:04", "remaining_time": "0:28:24", "throughput": 2640.02, "total_tokens": 5713456} {"current_steps": 21345, "total_steps": 38150, "loss": 0.3247, "lr": 2.417323527715929e-05, "epoch": 5.595019659239843, "percentage": 55.95, "elapsed_time": "0:36:04", "remaining_time": "0:28:24", "throughput": 2640.05, "total_tokens": 5714720} {"current_steps": 21350, "total_steps": 38150, "loss": 0.3866, "lr": 2.416180433793705e-05, "epoch": 5.5963302752293576, "percentage": 55.96, "elapsed_time": "0:36:05", "remaining_time": "0:28:23", "throughput": 2640.13, "total_tokens": 5716048} {"current_steps": 21355, "total_steps": 38150, "loss": 0.4126, "lr": 2.4150373574147715e-05, "epoch": 5.597640891218873, "percentage": 55.98, "elapsed_time": "0:36:05", "remaining_time": "0:28:23", "throughput": 2640.3, "total_tokens": 5717840} {"current_steps": 21360, "total_steps": 38150, "loss": 0.2743, "lr": 2.413894298818373e-05, "epoch": 5.598951507208388, "percentage": 55.99, "elapsed_time": "0:36:06", "remaining_time": "0:28:22", "throughput": 2640.38, "total_tokens": 5719184} {"current_steps": 21365, "total_steps": 38150, "loss": 0.2673, "lr": 2.4127512582437485e-05, "epoch": 5.600262123197903, "percentage": 56.0, "elapsed_time": "0:36:06", "remaining_time": "0:28:22", "throughput": 2640.51, "total_tokens": 5720704} {"current_steps": 21370, "total_steps": 38150, "loss": 0.1744, "lr": 2.4116082359301346e-05, "epoch": 5.601572739187418, "percentage": 56.02, "elapsed_time": "0:36:06", "remaining_time": "0:28:21", "throughput": 2640.61, "total_tokens": 5722160} {"current_steps": 21375, "total_steps": 38150, "loss": 0.2906, "lr": 2.4104652321167638e-05, "epoch": 5.6028833551769335, "percentage": 56.03, "elapsed_time": "0:36:07", "remaining_time": "0:28:20", "throughput": 2640.65, "total_tokens": 5723392} {"current_steps": 21380, "total_steps": 38150, "loss": 0.2506, "lr": 2.4093222470428657e-05, "epoch": 5.604193971166448, "percentage": 56.04, "elapsed_time": "0:36:07", "remaining_time": "0:28:20", "throughput": 2640.66, "total_tokens": 5724528} {"current_steps": 21385, "total_steps": 38150, "loss": 0.2455, "lr": 2.4081792809476643e-05, "epoch": 5.605504587155964, "percentage": 56.06, "elapsed_time": "0:36:08", "remaining_time": "0:28:19", "throughput": 2640.79, "total_tokens": 5725984} {"current_steps": 21390, "total_steps": 38150, "loss": 0.412, "lr": 2.4070363340703812e-05, "epoch": 5.606815203145478, "percentage": 56.07, "elapsed_time": "0:36:08", "remaining_time": "0:28:19", "throughput": 2640.86, "total_tokens": 5727280} {"current_steps": 21395, "total_steps": 38150, "loss": 0.4993, "lr": 2.4058934066502333e-05, "epoch": 5.608125819134994, "percentage": 56.08, "elapsed_time": "0:36:09", "remaining_time": "0:28:18", "throughput": 2640.85, "total_tokens": 5728336} {"current_steps": 21400, "total_steps": 38150, "loss": 0.2863, "lr": 2.4047504989264318e-05, "epoch": 5.6094364351245085, "percentage": 56.09, "elapsed_time": "0:36:09", "remaining_time": "0:28:18", "throughput": 2640.87, "total_tokens": 5729600} {"current_steps": 21405, "total_steps": 38150, "loss": 0.3242, "lr": 2.4036076111381867e-05, "epoch": 5.610747051114023, "percentage": 56.11, "elapsed_time": "0:36:10", "remaining_time": "0:28:17", "throughput": 2640.95, "total_tokens": 5731008} {"current_steps": 21410, "total_steps": 38150, "loss": 0.3042, "lr": 2.4024647435247018e-05, "epoch": 5.612057667103539, "percentage": 56.12, "elapsed_time": "0:36:10", "remaining_time": "0:28:17", "throughput": 2641.0, "total_tokens": 5732224} {"current_steps": 21415, "total_steps": 38150, "loss": 0.4024, "lr": 2.4013218963251778e-05, "epoch": 5.613368283093053, "percentage": 56.13, "elapsed_time": "0:36:10", "remaining_time": "0:28:16", "throughput": 2641.12, "total_tokens": 5733760} {"current_steps": 21420, "total_steps": 38150, "loss": 0.2132, "lr": 2.4001790697788107e-05, "epoch": 5.614678899082569, "percentage": 56.15, "elapsed_time": "0:36:11", "remaining_time": "0:28:15", "throughput": 2641.23, "total_tokens": 5735264} {"current_steps": 21425, "total_steps": 38150, "loss": 0.2326, "lr": 2.3990362641247915e-05, "epoch": 5.6159895150720835, "percentage": 56.16, "elapsed_time": "0:36:11", "remaining_time": "0:28:15", "throughput": 2641.46, "total_tokens": 5737152} {"current_steps": 21430, "total_steps": 38150, "loss": 0.3823, "lr": 2.3978934796023076e-05, "epoch": 5.617300131061599, "percentage": 56.17, "elapsed_time": "0:36:12", "remaining_time": "0:28:14", "throughput": 2641.51, "total_tokens": 5738400} {"current_steps": 21435, "total_steps": 38150, "loss": 0.196, "lr": 2.3967507164505416e-05, "epoch": 5.618610747051114, "percentage": 56.19, "elapsed_time": "0:36:12", "remaining_time": "0:28:14", "throughput": 2641.54, "total_tokens": 5739632} {"current_steps": 21440, "total_steps": 38150, "loss": 0.3136, "lr": 2.3956079749086728e-05, "epoch": 5.619921363040629, "percentage": 56.2, "elapsed_time": "0:36:13", "remaining_time": "0:28:13", "throughput": 2641.63, "total_tokens": 5740976} {"current_steps": 21445, "total_steps": 38150, "loss": 0.298, "lr": 2.3944652552158742e-05, "epoch": 5.621231979030144, "percentage": 56.21, "elapsed_time": "0:36:13", "remaining_time": "0:28:13", "throughput": 2641.72, "total_tokens": 5742320} {"current_steps": 21450, "total_steps": 38150, "loss": 0.3339, "lr": 2.3933225576113154e-05, "epoch": 5.6225425950196595, "percentage": 56.23, "elapsed_time": "0:36:14", "remaining_time": "0:28:12", "throughput": 2641.8, "total_tokens": 5743728} {"current_steps": 21455, "total_steps": 38150, "loss": 0.2594, "lr": 2.392179882334162e-05, "epoch": 5.623853211009174, "percentage": 56.24, "elapsed_time": "0:36:14", "remaining_time": "0:28:12", "throughput": 2641.83, "total_tokens": 5744944} {"current_steps": 21460, "total_steps": 38150, "loss": 0.2234, "lr": 2.3910372296235717e-05, "epoch": 5.62516382699869, "percentage": 56.25, "elapsed_time": "0:36:15", "remaining_time": "0:28:11", "throughput": 2641.73, "total_tokens": 5745856} {"current_steps": 21465, "total_steps": 38150, "loss": 0.3708, "lr": 2.3898945997187012e-05, "epoch": 5.626474442988204, "percentage": 56.26, "elapsed_time": "0:36:15", "remaining_time": "0:28:11", "throughput": 2641.81, "total_tokens": 5747328} {"current_steps": 21470, "total_steps": 38150, "loss": 0.5686, "lr": 2.3887519928587007e-05, "epoch": 5.62778505897772, "percentage": 56.28, "elapsed_time": "0:36:15", "remaining_time": "0:28:10", "throughput": 2641.77, "total_tokens": 5748336} {"current_steps": 21475, "total_steps": 38150, "loss": 0.302, "lr": 2.387609409282716e-05, "epoch": 5.6290956749672345, "percentage": 56.29, "elapsed_time": "0:36:16", "remaining_time": "0:28:09", "throughput": 2641.85, "total_tokens": 5749712} {"current_steps": 21480, "total_steps": 38150, "loss": 0.2689, "lr": 2.3864668492298884e-05, "epoch": 5.63040629095675, "percentage": 56.3, "elapsed_time": "0:36:16", "remaining_time": "0:28:09", "throughput": 2642.01, "total_tokens": 5751328} {"current_steps": 21485, "total_steps": 38150, "loss": 0.2482, "lr": 2.3853243129393524e-05, "epoch": 5.631716906946265, "percentage": 56.32, "elapsed_time": "0:36:17", "remaining_time": "0:28:08", "throughput": 2641.97, "total_tokens": 5752352} {"current_steps": 21490, "total_steps": 38150, "loss": 0.2346, "lr": 2.384181800650239e-05, "epoch": 5.63302752293578, "percentage": 56.33, "elapsed_time": "0:36:17", "remaining_time": "0:28:08", "throughput": 2642.09, "total_tokens": 5753856} {"current_steps": 21495, "total_steps": 38150, "loss": 0.2436, "lr": 2.383039312601675e-05, "epoch": 5.634338138925295, "percentage": 56.34, "elapsed_time": "0:36:18", "remaining_time": "0:28:07", "throughput": 2642.18, "total_tokens": 5755216} {"current_steps": 21500, "total_steps": 38150, "loss": 0.333, "lr": 2.3818968490327813e-05, "epoch": 5.6356487549148095, "percentage": 56.36, "elapsed_time": "0:36:18", "remaining_time": "0:28:07", "throughput": 2642.24, "total_tokens": 5756512} {"current_steps": 21505, "total_steps": 38150, "loss": 0.2477, "lr": 2.3807544101826722e-05, "epoch": 5.636959370904325, "percentage": 56.37, "elapsed_time": "0:36:19", "remaining_time": "0:28:06", "throughput": 2642.36, "total_tokens": 5758160} {"current_steps": 21510, "total_steps": 38150, "loss": 0.2597, "lr": 2.3796119962904597e-05, "epoch": 5.63826998689384, "percentage": 56.38, "elapsed_time": "0:36:19", "remaining_time": "0:28:06", "throughput": 2642.49, "total_tokens": 5759776} {"current_steps": 21515, "total_steps": 38150, "loss": 0.1883, "lr": 2.3784696075952487e-05, "epoch": 5.639580602883355, "percentage": 56.4, "elapsed_time": "0:36:20", "remaining_time": "0:28:05", "throughput": 2642.5, "total_tokens": 5760944} {"current_steps": 21520, "total_steps": 38150, "loss": 0.3394, "lr": 2.3773272443361383e-05, "epoch": 5.64089121887287, "percentage": 56.41, "elapsed_time": "0:36:20", "remaining_time": "0:28:05", "throughput": 2642.58, "total_tokens": 5762288} {"current_steps": 21525, "total_steps": 38150, "loss": 0.271, "lr": 2.3761849067522235e-05, "epoch": 5.6422018348623855, "percentage": 56.42, "elapsed_time": "0:36:20", "remaining_time": "0:28:04", "throughput": 2642.61, "total_tokens": 5763488} {"current_steps": 21530, "total_steps": 38150, "loss": 0.3849, "lr": 2.3750425950825943e-05, "epoch": 5.6435124508519, "percentage": 56.44, "elapsed_time": "0:36:21", "remaining_time": "0:28:03", "throughput": 2642.69, "total_tokens": 5764896} {"current_steps": 21535, "total_steps": 38150, "loss": 0.3264, "lr": 2.3739003095663334e-05, "epoch": 5.644823066841416, "percentage": 56.45, "elapsed_time": "0:36:21", "remaining_time": "0:28:03", "throughput": 2642.72, "total_tokens": 5766112} {"current_steps": 21540, "total_steps": 38150, "loss": 0.2407, "lr": 2.3727580504425208e-05, "epoch": 5.64613368283093, "percentage": 56.46, "elapsed_time": "0:36:22", "remaining_time": "0:28:02", "throughput": 2642.78, "total_tokens": 5767472} {"current_steps": 21545, "total_steps": 38150, "loss": 0.342, "lr": 2.3716158179502277e-05, "epoch": 5.647444298820446, "percentage": 56.47, "elapsed_time": "0:36:22", "remaining_time": "0:28:02", "throughput": 2642.92, "total_tokens": 5769056} {"current_steps": 21550, "total_steps": 38150, "loss": 0.3598, "lr": 2.3704736123285214e-05, "epoch": 5.6487549148099605, "percentage": 56.49, "elapsed_time": "0:36:23", "remaining_time": "0:28:01", "throughput": 2643.0, "total_tokens": 5770448} {"current_steps": 21555, "total_steps": 38150, "loss": 0.577, "lr": 2.369331433816465e-05, "epoch": 5.650065530799476, "percentage": 56.5, "elapsed_time": "0:36:23", "remaining_time": "0:28:01", "throughput": 2643.09, "total_tokens": 5771808} {"current_steps": 21560, "total_steps": 38150, "loss": 0.2867, "lr": 2.3681892826531137e-05, "epoch": 5.651376146788991, "percentage": 56.51, "elapsed_time": "0:36:24", "remaining_time": "0:28:00", "throughput": 2643.3, "total_tokens": 5773760} {"current_steps": 21565, "total_steps": 38150, "loss": 0.2359, "lr": 2.3670471590775174e-05, "epoch": 5.652686762778506, "percentage": 56.53, "elapsed_time": "0:36:24", "remaining_time": "0:28:00", "throughput": 2643.49, "total_tokens": 5775584} {"current_steps": 21570, "total_steps": 38150, "loss": 0.2432, "lr": 2.3659050633287217e-05, "epoch": 5.653997378768021, "percentage": 56.54, "elapsed_time": "0:36:25", "remaining_time": "0:27:59", "throughput": 2643.51, "total_tokens": 5776768} {"current_steps": 21575, "total_steps": 38150, "loss": 0.3746, "lr": 2.3647629956457647e-05, "epoch": 5.655307994757536, "percentage": 56.55, "elapsed_time": "0:36:25", "remaining_time": "0:27:59", "throughput": 2643.64, "total_tokens": 5778336} {"current_steps": 21580, "total_steps": 38150, "loss": 0.3095, "lr": 2.3636209562676784e-05, "epoch": 5.656618610747051, "percentage": 56.57, "elapsed_time": "0:36:26", "remaining_time": "0:27:58", "throughput": 2643.8, "total_tokens": 5779952} {"current_steps": 21585, "total_steps": 38150, "loss": 0.3847, "lr": 2.3624789454334905e-05, "epoch": 5.657929226736567, "percentage": 56.58, "elapsed_time": "0:36:26", "remaining_time": "0:27:58", "throughput": 2643.86, "total_tokens": 5781376} {"current_steps": 21590, "total_steps": 38150, "loss": 0.3014, "lr": 2.3613369633822217e-05, "epoch": 5.659239842726081, "percentage": 56.59, "elapsed_time": "0:36:27", "remaining_time": "0:27:57", "throughput": 2644.14, "total_tokens": 5783424} {"current_steps": 21595, "total_steps": 38150, "loss": 0.3063, "lr": 2.360195010352887e-05, "epoch": 5.660550458715596, "percentage": 56.61, "elapsed_time": "0:36:27", "remaining_time": "0:27:57", "throughput": 2644.25, "total_tokens": 5784848} {"current_steps": 21600, "total_steps": 38150, "loss": 0.3197, "lr": 2.3590530865844952e-05, "epoch": 5.6618610747051115, "percentage": 56.62, "elapsed_time": "0:36:28", "remaining_time": "0:27:56", "throughput": 2644.28, "total_tokens": 5786128} {"current_steps": 21605, "total_steps": 38150, "loss": 0.3019, "lr": 2.357911192316047e-05, "epoch": 5.663171690694626, "percentage": 56.63, "elapsed_time": "0:36:28", "remaining_time": "0:27:56", "throughput": 2644.36, "total_tokens": 5787440} {"current_steps": 21610, "total_steps": 38150, "loss": 0.3071, "lr": 2.356769327786543e-05, "epoch": 5.664482306684142, "percentage": 56.64, "elapsed_time": "0:36:29", "remaining_time": "0:27:55", "throughput": 2644.5, "total_tokens": 5789056} {"current_steps": 21615, "total_steps": 38150, "loss": 0.3432, "lr": 2.3556274932349703e-05, "epoch": 5.665792922673656, "percentage": 56.66, "elapsed_time": "0:36:29", "remaining_time": "0:27:54", "throughput": 2644.55, "total_tokens": 5790416} {"current_steps": 21620, "total_steps": 38150, "loss": 0.3219, "lr": 2.354485688900314e-05, "epoch": 5.667103538663172, "percentage": 56.67, "elapsed_time": "0:36:30", "remaining_time": "0:27:54", "throughput": 2644.7, "total_tokens": 5792000} {"current_steps": 21625, "total_steps": 38150, "loss": 0.2459, "lr": 2.3533439150215517e-05, "epoch": 5.6684141546526865, "percentage": 56.68, "elapsed_time": "0:36:30", "remaining_time": "0:27:53", "throughput": 2644.89, "total_tokens": 5793792} {"current_steps": 21630, "total_steps": 38150, "loss": 0.2953, "lr": 2.352202171837655e-05, "epoch": 5.669724770642202, "percentage": 56.7, "elapsed_time": "0:36:30", "remaining_time": "0:27:53", "throughput": 2645.02, "total_tokens": 5795232} {"current_steps": 21635, "total_steps": 38150, "loss": 0.2443, "lr": 2.3510604595875877e-05, "epoch": 5.671035386631717, "percentage": 56.71, "elapsed_time": "0:36:31", "remaining_time": "0:27:52", "throughput": 2645.1, "total_tokens": 5796560} {"current_steps": 21640, "total_steps": 38150, "loss": 0.2551, "lr": 2.3499187785103087e-05, "epoch": 5.672346002621232, "percentage": 56.72, "elapsed_time": "0:36:31", "remaining_time": "0:27:52", "throughput": 2645.19, "total_tokens": 5797984} {"current_steps": 21645, "total_steps": 38150, "loss": 0.2691, "lr": 2.3487771288447705e-05, "epoch": 5.673656618610747, "percentage": 56.74, "elapsed_time": "0:36:32", "remaining_time": "0:27:51", "throughput": 2645.19, "total_tokens": 5799088} {"current_steps": 21650, "total_steps": 38150, "loss": 0.3829, "lr": 2.3476355108299174e-05, "epoch": 5.674967234600262, "percentage": 56.75, "elapsed_time": "0:36:32", "remaining_time": "0:27:51", "throughput": 2645.26, "total_tokens": 5800464} {"current_steps": 21655, "total_steps": 38150, "loss": 0.3598, "lr": 2.3464939247046896e-05, "epoch": 5.676277850589777, "percentage": 56.76, "elapsed_time": "0:36:33", "remaining_time": "0:27:50", "throughput": 2645.4, "total_tokens": 5802032} {"current_steps": 21660, "total_steps": 38150, "loss": 0.3917, "lr": 2.3453523707080165e-05, "epoch": 5.677588466579293, "percentage": 56.78, "elapsed_time": "0:36:33", "remaining_time": "0:27:50", "throughput": 2645.47, "total_tokens": 5803424} {"current_steps": 21665, "total_steps": 38150, "loss": 0.2507, "lr": 2.344210849078826e-05, "epoch": 5.678899082568807, "percentage": 56.79, "elapsed_time": "0:36:34", "remaining_time": "0:27:49", "throughput": 2645.58, "total_tokens": 5804896} {"current_steps": 21670, "total_steps": 38150, "loss": 0.2834, "lr": 2.343069360056036e-05, "epoch": 5.680209698558322, "percentage": 56.8, "elapsed_time": "0:36:34", "remaining_time": "0:27:49", "throughput": 2645.59, "total_tokens": 5806096} {"current_steps": 21675, "total_steps": 38150, "loss": 0.4172, "lr": 2.3419279038785575e-05, "epoch": 5.6815203145478375, "percentage": 56.82, "elapsed_time": "0:36:35", "remaining_time": "0:27:48", "throughput": 2645.74, "total_tokens": 5807616} {"current_steps": 21680, "total_steps": 38150, "loss": 0.193, "lr": 2.3407864807852952e-05, "epoch": 5.682830930537353, "percentage": 56.83, "elapsed_time": "0:36:35", "remaining_time": "0:27:47", "throughput": 2645.75, "total_tokens": 5808768} {"current_steps": 21685, "total_steps": 38150, "loss": 0.2129, "lr": 2.3396450910151476e-05, "epoch": 5.684141546526868, "percentage": 56.84, "elapsed_time": "0:36:35", "remaining_time": "0:27:47", "throughput": 2645.71, "total_tokens": 5809792} {"current_steps": 21690, "total_steps": 38150, "loss": 0.2838, "lr": 2.338503734807006e-05, "epoch": 5.685452162516382, "percentage": 56.85, "elapsed_time": "0:36:36", "remaining_time": "0:27:46", "throughput": 2645.93, "total_tokens": 5811600} {"current_steps": 21695, "total_steps": 38150, "loss": 0.3423, "lr": 2.337362412399753e-05, "epoch": 5.686762778505898, "percentage": 56.87, "elapsed_time": "0:36:36", "remaining_time": "0:27:46", "throughput": 2645.94, "total_tokens": 5812736} {"current_steps": 21700, "total_steps": 38150, "loss": 0.2249, "lr": 2.3362211240322663e-05, "epoch": 5.6880733944954125, "percentage": 56.88, "elapsed_time": "0:36:37", "remaining_time": "0:27:45", "throughput": 2645.83, "total_tokens": 5813600} {"current_steps": 21705, "total_steps": 38150, "loss": 0.3809, "lr": 2.335079869943415e-05, "epoch": 5.689384010484928, "percentage": 56.89, "elapsed_time": "0:36:37", "remaining_time": "0:27:45", "throughput": 2645.85, "total_tokens": 5814736} {"current_steps": 21710, "total_steps": 38150, "loss": 0.3422, "lr": 2.333938650372062e-05, "epoch": 5.690694626474443, "percentage": 56.91, "elapsed_time": "0:36:38", "remaining_time": "0:27:44", "throughput": 2645.93, "total_tokens": 5816032} {"current_steps": 21715, "total_steps": 38150, "loss": 0.2157, "lr": 2.3327974655570633e-05, "epoch": 5.692005242463958, "percentage": 56.92, "elapsed_time": "0:36:38", "remaining_time": "0:27:43", "throughput": 2645.87, "total_tokens": 5816992} {"current_steps": 21720, "total_steps": 38150, "loss": 0.3581, "lr": 2.3316563157372645e-05, "epoch": 5.693315858453473, "percentage": 56.93, "elapsed_time": "0:36:38", "remaining_time": "0:27:43", "throughput": 2645.83, "total_tokens": 5818032} {"current_steps": 21725, "total_steps": 38150, "loss": 0.1704, "lr": 2.3305152011515098e-05, "epoch": 5.694626474442988, "percentage": 56.95, "elapsed_time": "0:36:39", "remaining_time": "0:27:42", "throughput": 2645.86, "total_tokens": 5819232} {"current_steps": 21730, "total_steps": 38150, "loss": 0.3586, "lr": 2.3293741220386296e-05, "epoch": 5.695937090432503, "percentage": 56.96, "elapsed_time": "0:36:39", "remaining_time": "0:27:42", "throughput": 2645.93, "total_tokens": 5820608} {"current_steps": 21735, "total_steps": 38150, "loss": 0.2214, "lr": 2.328233078637451e-05, "epoch": 5.697247706422019, "percentage": 56.97, "elapsed_time": "0:36:40", "remaining_time": "0:27:41", "throughput": 2645.98, "total_tokens": 5821952} {"current_steps": 21740, "total_steps": 38150, "loss": 0.3962, "lr": 2.327092071186792e-05, "epoch": 5.698558322411533, "percentage": 56.99, "elapsed_time": "0:36:40", "remaining_time": "0:27:41", "throughput": 2646.04, "total_tokens": 5823296} {"current_steps": 21745, "total_steps": 38150, "loss": 0.2468, "lr": 2.3259510999254645e-05, "epoch": 5.699868938401049, "percentage": 57.0, "elapsed_time": "0:36:41", "remaining_time": "0:27:40", "throughput": 2646.08, "total_tokens": 5824624} {"current_steps": 21750, "total_steps": 38150, "loss": 0.2429, "lr": 2.324810165092271e-05, "epoch": 5.7011795543905635, "percentage": 57.01, "elapsed_time": "0:36:41", "remaining_time": "0:27:40", "throughput": 2646.04, "total_tokens": 5825632} {"current_steps": 21755, "total_steps": 38150, "loss": 0.2694, "lr": 2.323669266926007e-05, "epoch": 5.702490170380079, "percentage": 57.02, "elapsed_time": "0:36:42", "remaining_time": "0:27:39", "throughput": 2646.13, "total_tokens": 5827136} {"current_steps": 21760, "total_steps": 38150, "loss": 0.2318, "lr": 2.3225284056654607e-05, "epoch": 5.703800786369594, "percentage": 57.04, "elapsed_time": "0:36:42", "remaining_time": "0:27:39", "throughput": 2646.11, "total_tokens": 5828224} {"current_steps": 21765, "total_steps": 38150, "loss": 0.2095, "lr": 2.3213875815494122e-05, "epoch": 5.705111402359108, "percentage": 57.05, "elapsed_time": "0:36:42", "remaining_time": "0:27:38", "throughput": 2646.12, "total_tokens": 5829360} {"current_steps": 21770, "total_steps": 38150, "loss": 0.3488, "lr": 2.3202467948166343e-05, "epoch": 5.706422018348624, "percentage": 57.06, "elapsed_time": "0:36:43", "remaining_time": "0:27:37", "throughput": 2646.17, "total_tokens": 5830640} {"current_steps": 21775, "total_steps": 38150, "loss": 0.21, "lr": 2.319106045705891e-05, "epoch": 5.707732634338139, "percentage": 57.08, "elapsed_time": "0:36:43", "remaining_time": "0:27:37", "throughput": 2646.3, "total_tokens": 5832224} {"current_steps": 21780, "total_steps": 38150, "loss": 0.2263, "lr": 2.317965334455941e-05, "epoch": 5.709043250327654, "percentage": 57.09, "elapsed_time": "0:36:44", "remaining_time": "0:27:36", "throughput": 2646.41, "total_tokens": 5833712} {"current_steps": 21785, "total_steps": 38150, "loss": 0.3879, "lr": 2.3168246613055317e-05, "epoch": 5.710353866317169, "percentage": 57.1, "elapsed_time": "0:36:44", "remaining_time": "0:27:36", "throughput": 2646.43, "total_tokens": 5834880} {"current_steps": 21790, "total_steps": 38150, "loss": 0.3042, "lr": 2.3156840264934045e-05, "epoch": 5.711664482306684, "percentage": 57.12, "elapsed_time": "0:36:45", "remaining_time": "0:27:35", "throughput": 2646.52, "total_tokens": 5836304} {"current_steps": 21795, "total_steps": 38150, "loss": 0.3668, "lr": 2.3145434302582913e-05, "epoch": 5.712975098296199, "percentage": 57.13, "elapsed_time": "0:36:45", "remaining_time": "0:27:35", "throughput": 2646.67, "total_tokens": 5837920} {"current_steps": 21800, "total_steps": 38150, "loss": 0.2806, "lr": 2.313402872838918e-05, "epoch": 5.714285714285714, "percentage": 57.14, "elapsed_time": "0:36:46", "remaining_time": "0:27:34", "throughput": 2647.18, "total_tokens": 5841344} {"current_steps": 21805, "total_steps": 38150, "loss": 0.4863, "lr": 2.312262354474001e-05, "epoch": 5.715596330275229, "percentage": 57.16, "elapsed_time": "0:36:47", "remaining_time": "0:27:34", "throughput": 2647.22, "total_tokens": 5842592} {"current_steps": 21810, "total_steps": 38150, "loss": 0.2469, "lr": 2.3111218754022495e-05, "epoch": 5.716906946264745, "percentage": 57.17, "elapsed_time": "0:36:47", "remaining_time": "0:27:33", "throughput": 2647.23, "total_tokens": 5843712} {"current_steps": 21815, "total_steps": 38150, "loss": 0.3274, "lr": 2.309981435862363e-05, "epoch": 5.718217562254259, "percentage": 57.18, "elapsed_time": "0:36:47", "remaining_time": "0:27:33", "throughput": 2647.4, "total_tokens": 5845376} {"current_steps": 21820, "total_steps": 38150, "loss": 0.3245, "lr": 2.308841036093033e-05, "epoch": 5.719528178243775, "percentage": 57.2, "elapsed_time": "0:36:48", "remaining_time": "0:27:32", "throughput": 2647.52, "total_tokens": 5846896} {"current_steps": 21825, "total_steps": 38150, "loss": 0.4888, "lr": 2.307700676332944e-05, "epoch": 5.7208387942332894, "percentage": 57.21, "elapsed_time": "0:36:48", "remaining_time": "0:27:32", "throughput": 2647.6, "total_tokens": 5848240} {"current_steps": 21830, "total_steps": 38150, "loss": 0.2512, "lr": 2.3065603568207715e-05, "epoch": 5.722149410222805, "percentage": 57.22, "elapsed_time": "0:36:49", "remaining_time": "0:27:31", "throughput": 2647.63, "total_tokens": 5849456} {"current_steps": 21835, "total_steps": 38150, "loss": 0.2557, "lr": 2.3054200777951807e-05, "epoch": 5.72346002621232, "percentage": 57.23, "elapsed_time": "0:36:49", "remaining_time": "0:27:31", "throughput": 2647.72, "total_tokens": 5850928} {"current_steps": 21840, "total_steps": 38150, "loss": 0.2598, "lr": 2.3042798394948326e-05, "epoch": 5.724770642201835, "percentage": 57.25, "elapsed_time": "0:36:50", "remaining_time": "0:27:30", "throughput": 2647.8, "total_tokens": 5852320} {"current_steps": 21845, "total_steps": 38150, "loss": 0.3535, "lr": 2.303139642158376e-05, "epoch": 5.72608125819135, "percentage": 57.26, "elapsed_time": "0:36:50", "remaining_time": "0:27:30", "throughput": 2647.83, "total_tokens": 5853552} {"current_steps": 21850, "total_steps": 38150, "loss": 0.5215, "lr": 2.3019994860244523e-05, "epoch": 5.727391874180865, "percentage": 57.27, "elapsed_time": "0:36:51", "remaining_time": "0:27:29", "throughput": 2647.96, "total_tokens": 5855040} {"current_steps": 21855, "total_steps": 38150, "loss": 0.337, "lr": 2.3008593713316937e-05, "epoch": 5.72870249017038, "percentage": 57.29, "elapsed_time": "0:36:51", "remaining_time": "0:27:29", "throughput": 2648.22, "total_tokens": 5857152} {"current_steps": 21860, "total_steps": 38150, "loss": 0.2996, "lr": 2.2997192983187245e-05, "epoch": 5.730013106159895, "percentage": 57.3, "elapsed_time": "0:36:52", "remaining_time": "0:27:28", "throughput": 2648.22, "total_tokens": 5858272} {"current_steps": 21865, "total_steps": 38150, "loss": 0.2336, "lr": 2.2985792672241608e-05, "epoch": 5.73132372214941, "percentage": 57.31, "elapsed_time": "0:36:52", "remaining_time": "0:27:27", "throughput": 2648.27, "total_tokens": 5859504} {"current_steps": 21870, "total_steps": 38150, "loss": 0.3542, "lr": 2.2974392782866078e-05, "epoch": 5.732634338138926, "percentage": 57.33, "elapsed_time": "0:36:53", "remaining_time": "0:27:27", "throughput": 2648.41, "total_tokens": 5861072} {"current_steps": 21875, "total_steps": 38150, "loss": 0.2138, "lr": 2.296299331744664e-05, "epoch": 5.73394495412844, "percentage": 57.34, "elapsed_time": "0:36:53", "remaining_time": "0:27:26", "throughput": 2648.52, "total_tokens": 5862496} {"current_steps": 21880, "total_steps": 38150, "loss": 0.353, "lr": 2.2951594278369178e-05, "epoch": 5.735255570117955, "percentage": 57.35, "elapsed_time": "0:36:53", "remaining_time": "0:27:26", "throughput": 2648.62, "total_tokens": 5863872} {"current_steps": 21885, "total_steps": 38150, "loss": 0.4898, "lr": 2.2940195668019497e-05, "epoch": 5.736566186107471, "percentage": 57.37, "elapsed_time": "0:36:54", "remaining_time": "0:27:25", "throughput": 2648.71, "total_tokens": 5865216} {"current_steps": 21890, "total_steps": 38150, "loss": 0.3085, "lr": 2.2928797488783298e-05, "epoch": 5.737876802096985, "percentage": 57.38, "elapsed_time": "0:36:54", "remaining_time": "0:27:25", "throughput": 2648.79, "total_tokens": 5866656} {"current_steps": 21895, "total_steps": 38150, "loss": 0.247, "lr": 2.2917399743046208e-05, "epoch": 5.739187418086501, "percentage": 57.39, "elapsed_time": "0:36:55", "remaining_time": "0:27:24", "throughput": 2648.85, "total_tokens": 5867920} {"current_steps": 21900, "total_steps": 38150, "loss": 0.2964, "lr": 2.2906002433193757e-05, "epoch": 5.740498034076015, "percentage": 57.4, "elapsed_time": "0:36:55", "remaining_time": "0:27:24", "throughput": 2648.97, "total_tokens": 5869472} {"current_steps": 21905, "total_steps": 38150, "loss": 0.1761, "lr": 2.2894605561611382e-05, "epoch": 5.741808650065531, "percentage": 57.42, "elapsed_time": "0:36:56", "remaining_time": "0:27:23", "throughput": 2648.92, "total_tokens": 5870480} {"current_steps": 21910, "total_steps": 38150, "loss": 0.4182, "lr": 2.288320913068442e-05, "epoch": 5.743119266055046, "percentage": 57.43, "elapsed_time": "0:36:56", "remaining_time": "0:27:23", "throughput": 2649.0, "total_tokens": 5871888} {"current_steps": 21915, "total_steps": 38150, "loss": 0.2709, "lr": 2.2871813142798133e-05, "epoch": 5.744429882044561, "percentage": 57.44, "elapsed_time": "0:36:57", "remaining_time": "0:27:22", "throughput": 2649.07, "total_tokens": 5873216} {"current_steps": 21920, "total_steps": 38150, "loss": 0.2748, "lr": 2.2860417600337673e-05, "epoch": 5.745740498034076, "percentage": 57.46, "elapsed_time": "0:36:57", "remaining_time": "0:27:21", "throughput": 2649.07, "total_tokens": 5874320} {"current_steps": 21925, "total_steps": 38150, "loss": 0.4158, "lr": 2.284902250568812e-05, "epoch": 5.747051114023591, "percentage": 57.47, "elapsed_time": "0:36:57", "remaining_time": "0:27:21", "throughput": 2649.14, "total_tokens": 5875648} {"current_steps": 21930, "total_steps": 38150, "loss": 0.259, "lr": 2.2837627861234434e-05, "epoch": 5.748361730013106, "percentage": 57.48, "elapsed_time": "0:36:58", "remaining_time": "0:27:20", "throughput": 2649.08, "total_tokens": 5876624} {"current_steps": 21935, "total_steps": 38150, "loss": 0.2028, "lr": 2.2826233669361504e-05, "epoch": 5.749672346002622, "percentage": 57.5, "elapsed_time": "0:36:58", "remaining_time": "0:27:20", "throughput": 2649.09, "total_tokens": 5877760} {"current_steps": 21940, "total_steps": 38150, "loss": 0.4939, "lr": 2.2814839932454103e-05, "epoch": 5.750982961992136, "percentage": 57.51, "elapsed_time": "0:36:59", "remaining_time": "0:27:19", "throughput": 2649.15, "total_tokens": 5879152} {"current_steps": 21945, "total_steps": 38150, "loss": 0.3514, "lr": 2.2803446652896935e-05, "epoch": 5.752293577981652, "percentage": 57.52, "elapsed_time": "0:36:59", "remaining_time": "0:27:19", "throughput": 2649.25, "total_tokens": 5880640} {"current_steps": 21950, "total_steps": 38150, "loss": 0.5798, "lr": 2.279205383307458e-05, "epoch": 5.753604193971166, "percentage": 57.54, "elapsed_time": "0:37:00", "remaining_time": "0:27:18", "throughput": 2649.63, "total_tokens": 5883504} {"current_steps": 21955, "total_steps": 38150, "loss": 0.3043, "lr": 2.278066147537155e-05, "epoch": 5.754914809960681, "percentage": 57.55, "elapsed_time": "0:37:00", "remaining_time": "0:27:18", "throughput": 2649.66, "total_tokens": 5884768} {"current_steps": 21960, "total_steps": 38150, "loss": 0.3436, "lr": 2.276926958217224e-05, "epoch": 5.756225425950197, "percentage": 57.56, "elapsed_time": "0:37:01", "remaining_time": "0:27:17", "throughput": 2649.67, "total_tokens": 5885920} {"current_steps": 21965, "total_steps": 38150, "loss": 0.3424, "lr": 2.2757878155860948e-05, "epoch": 5.757536041939712, "percentage": 57.58, "elapsed_time": "0:37:01", "remaining_time": "0:27:17", "throughput": 2649.95, "total_tokens": 5887952} {"current_steps": 21970, "total_steps": 38150, "loss": 0.444, "lr": 2.2746487198821883e-05, "epoch": 5.758846657929227, "percentage": 57.59, "elapsed_time": "0:37:02", "remaining_time": "0:27:16", "throughput": 2650.18, "total_tokens": 5889872} {"current_steps": 21975, "total_steps": 38150, "loss": 0.3047, "lr": 2.2735096713439156e-05, "epoch": 5.760157273918741, "percentage": 57.6, "elapsed_time": "0:37:02", "remaining_time": "0:27:16", "throughput": 2650.3, "total_tokens": 5891408} {"current_steps": 21980, "total_steps": 38150, "loss": 0.4148, "lr": 2.2723706702096774e-05, "epoch": 5.761467889908257, "percentage": 57.61, "elapsed_time": "0:37:03", "remaining_time": "0:27:15", "throughput": 2650.27, "total_tokens": 5892448} {"current_steps": 21985, "total_steps": 38150, "loss": 0.3053, "lr": 2.2712317167178648e-05, "epoch": 5.762778505897772, "percentage": 57.63, "elapsed_time": "0:37:03", "remaining_time": "0:27:15", "throughput": 2650.44, "total_tokens": 5894208} {"current_steps": 21990, "total_steps": 38150, "loss": 0.2625, "lr": 2.2700928111068582e-05, "epoch": 5.764089121887287, "percentage": 57.64, "elapsed_time": "0:37:04", "remaining_time": "0:27:14", "throughput": 2650.37, "total_tokens": 5895184} {"current_steps": 21995, "total_steps": 38150, "loss": 0.3121, "lr": 2.2689539536150294e-05, "epoch": 5.765399737876802, "percentage": 57.65, "elapsed_time": "0:37:04", "remaining_time": "0:27:14", "throughput": 2650.34, "total_tokens": 5896240} {"current_steps": 22000, "total_steps": 38150, "loss": 0.4192, "lr": 2.2678151444807384e-05, "epoch": 5.766710353866317, "percentage": 57.67, "elapsed_time": "0:37:05", "remaining_time": "0:27:13", "throughput": 2650.42, "total_tokens": 5897584} {"current_steps": 22005, "total_steps": 38150, "loss": 0.3724, "lr": 2.266676383942336e-05, "epoch": 5.768020969855832, "percentage": 57.68, "elapsed_time": "0:37:05", "remaining_time": "0:27:12", "throughput": 2650.42, "total_tokens": 5898800} {"current_steps": 22010, "total_steps": 38150, "loss": 0.379, "lr": 2.265537672238164e-05, "epoch": 5.7693315858453476, "percentage": 57.69, "elapsed_time": "0:37:06", "remaining_time": "0:27:12", "throughput": 2650.48, "total_tokens": 5900080} {"current_steps": 22015, "total_steps": 38150, "loss": 0.3254, "lr": 2.2643990096065518e-05, "epoch": 5.770642201834862, "percentage": 57.71, "elapsed_time": "0:37:06", "remaining_time": "0:27:11", "throughput": 2650.48, "total_tokens": 5901200} {"current_steps": 22020, "total_steps": 38150, "loss": 0.1547, "lr": 2.2632603962858207e-05, "epoch": 5.771952817824378, "percentage": 57.72, "elapsed_time": "0:37:06", "remaining_time": "0:27:11", "throughput": 2650.51, "total_tokens": 5902416} {"current_steps": 22025, "total_steps": 38150, "loss": 0.3974, "lr": 2.2621218325142788e-05, "epoch": 5.773263433813892, "percentage": 57.73, "elapsed_time": "0:37:07", "remaining_time": "0:27:10", "throughput": 2650.58, "total_tokens": 5903712} {"current_steps": 22030, "total_steps": 38150, "loss": 0.5664, "lr": 2.2609833185302262e-05, "epoch": 5.774574049803408, "percentage": 57.75, "elapsed_time": "0:37:07", "remaining_time": "0:27:10", "throughput": 2650.7, "total_tokens": 5905216} {"current_steps": 22035, "total_steps": 38150, "loss": 0.3314, "lr": 2.2598448545719525e-05, "epoch": 5.775884665792923, "percentage": 57.76, "elapsed_time": "0:37:08", "remaining_time": "0:27:09", "throughput": 2650.75, "total_tokens": 5906576} {"current_steps": 22040, "total_steps": 38150, "loss": 0.2406, "lr": 2.2587064408777352e-05, "epoch": 5.777195281782438, "percentage": 57.77, "elapsed_time": "0:37:08", "remaining_time": "0:27:09", "throughput": 2650.74, "total_tokens": 5907648} {"current_steps": 22045, "total_steps": 38150, "loss": 0.43, "lr": 2.257568077685844e-05, "epoch": 5.778505897771953, "percentage": 57.79, "elapsed_time": "0:37:09", "remaining_time": "0:27:08", "throughput": 2650.92, "total_tokens": 5909440} {"current_steps": 22050, "total_steps": 38150, "loss": 0.3771, "lr": 2.2564297652345347e-05, "epoch": 5.779816513761467, "percentage": 57.8, "elapsed_time": "0:37:09", "remaining_time": "0:27:07", "throughput": 2650.87, "total_tokens": 5910432} {"current_steps": 22055, "total_steps": 38150, "loss": 0.252, "lr": 2.255291503762054e-05, "epoch": 5.781127129750983, "percentage": 57.81, "elapsed_time": "0:37:10", "remaining_time": "0:27:07", "throughput": 2650.9, "total_tokens": 5911648} {"current_steps": 22060, "total_steps": 38150, "loss": 0.3618, "lr": 2.2541532935066394e-05, "epoch": 5.7824377457404985, "percentage": 57.82, "elapsed_time": "0:37:10", "remaining_time": "0:27:06", "throughput": 2651.04, "total_tokens": 5913168} {"current_steps": 22065, "total_steps": 38150, "loss": 0.2216, "lr": 2.2530151347065153e-05, "epoch": 5.783748361730013, "percentage": 57.84, "elapsed_time": "0:37:10", "remaining_time": "0:27:06", "throughput": 2651.13, "total_tokens": 5914528} {"current_steps": 22070, "total_steps": 38150, "loss": 0.2714, "lr": 2.2518770275998967e-05, "epoch": 5.785058977719528, "percentage": 57.85, "elapsed_time": "0:37:11", "remaining_time": "0:27:05", "throughput": 2651.23, "total_tokens": 5915968} {"current_steps": 22075, "total_steps": 38150, "loss": 0.2736, "lr": 2.2507389724249878e-05, "epoch": 5.786369593709043, "percentage": 57.86, "elapsed_time": "0:37:11", "remaining_time": "0:27:05", "throughput": 2651.27, "total_tokens": 5917184} {"current_steps": 22080, "total_steps": 38150, "loss": 0.3139, "lr": 2.2496009694199815e-05, "epoch": 5.787680209698558, "percentage": 57.88, "elapsed_time": "0:37:12", "remaining_time": "0:27:04", "throughput": 2651.33, "total_tokens": 5918496} {"current_steps": 22085, "total_steps": 38150, "loss": 0.2597, "lr": 2.2484630188230596e-05, "epoch": 5.7889908256880735, "percentage": 57.89, "elapsed_time": "0:37:12", "remaining_time": "0:27:04", "throughput": 2651.47, "total_tokens": 5920096} {"current_steps": 22090, "total_steps": 38150, "loss": 0.4218, "lr": 2.2473251208723927e-05, "epoch": 5.790301441677588, "percentage": 57.9, "elapsed_time": "0:37:13", "remaining_time": "0:27:03", "throughput": 2651.68, "total_tokens": 5922176} {"current_steps": 22095, "total_steps": 38150, "loss": 0.407, "lr": 2.246187275806142e-05, "epoch": 5.791612057667104, "percentage": 57.92, "elapsed_time": "0:37:13", "remaining_time": "0:27:03", "throughput": 2651.7, "total_tokens": 5923328} {"current_steps": 22100, "total_steps": 38150, "loss": 0.3036, "lr": 2.2450494838624554e-05, "epoch": 5.792922673656618, "percentage": 57.93, "elapsed_time": "0:37:14", "remaining_time": "0:27:02", "throughput": 2651.83, "total_tokens": 5924912} {"current_steps": 22105, "total_steps": 38150, "loss": 0.3164, "lr": 2.2439117452794723e-05, "epoch": 5.794233289646134, "percentage": 57.94, "elapsed_time": "0:37:14", "remaining_time": "0:27:02", "throughput": 2651.93, "total_tokens": 5926512} {"current_steps": 22110, "total_steps": 38150, "loss": 0.2729, "lr": 2.2427740602953175e-05, "epoch": 5.795543905635649, "percentage": 57.96, "elapsed_time": "0:37:15", "remaining_time": "0:27:01", "throughput": 2651.91, "total_tokens": 5927584} {"current_steps": 22115, "total_steps": 38150, "loss": 0.3773, "lr": 2.2416364291481075e-05, "epoch": 5.796854521625164, "percentage": 57.97, "elapsed_time": "0:37:15", "remaining_time": "0:27:01", "throughput": 2651.97, "total_tokens": 5929040} {"current_steps": 22120, "total_steps": 38150, "loss": 0.3592, "lr": 2.240498852075946e-05, "epoch": 5.798165137614679, "percentage": 57.98, "elapsed_time": "0:37:16", "remaining_time": "0:27:00", "throughput": 2652.27, "total_tokens": 5931664} {"current_steps": 22125, "total_steps": 38150, "loss": 0.3059, "lr": 2.239361329316927e-05, "epoch": 5.799475753604194, "percentage": 57.99, "elapsed_time": "0:37:16", "remaining_time": "0:27:00", "throughput": 2652.23, "total_tokens": 5932704} {"current_steps": 22130, "total_steps": 38150, "loss": 0.2489, "lr": 2.2382238611091318e-05, "epoch": 5.800786369593709, "percentage": 58.01, "elapsed_time": "0:37:17", "remaining_time": "0:26:59", "throughput": 2652.27, "total_tokens": 5933936} {"current_steps": 22135, "total_steps": 38150, "loss": 0.2747, "lr": 2.2370864476906296e-05, "epoch": 5.8020969855832245, "percentage": 58.02, "elapsed_time": "0:37:17", "remaining_time": "0:26:59", "throughput": 2652.32, "total_tokens": 5935232} {"current_steps": 22140, "total_steps": 38150, "loss": 0.2922, "lr": 2.23594908929948e-05, "epoch": 5.803407601572739, "percentage": 58.03, "elapsed_time": "0:37:18", "remaining_time": "0:26:58", "throughput": 2652.31, "total_tokens": 5936400} {"current_steps": 22145, "total_steps": 38150, "loss": 0.5245, "lr": 2.2348117861737297e-05, "epoch": 5.804718217562254, "percentage": 58.05, "elapsed_time": "0:37:18", "remaining_time": "0:26:57", "throughput": 2652.36, "total_tokens": 5937648} {"current_steps": 22150, "total_steps": 38150, "loss": 0.2911, "lr": 2.233674538551414e-05, "epoch": 5.806028833551769, "percentage": 58.06, "elapsed_time": "0:37:19", "remaining_time": "0:26:57", "throughput": 2652.46, "total_tokens": 5939120} {"current_steps": 22155, "total_steps": 38150, "loss": 0.3958, "lr": 2.2325373466705573e-05, "epoch": 5.807339449541285, "percentage": 58.07, "elapsed_time": "0:37:19", "remaining_time": "0:26:56", "throughput": 2652.59, "total_tokens": 5940720} {"current_steps": 22160, "total_steps": 38150, "loss": 0.3262, "lr": 2.2314002107691727e-05, "epoch": 5.8086500655307995, "percentage": 58.09, "elapsed_time": "0:37:20", "remaining_time": "0:26:56", "throughput": 2652.75, "total_tokens": 5942320} {"current_steps": 22165, "total_steps": 38150, "loss": 0.2438, "lr": 2.230263131085259e-05, "epoch": 5.809960681520314, "percentage": 58.1, "elapsed_time": "0:37:20", "remaining_time": "0:26:55", "throughput": 2652.69, "total_tokens": 5943280} {"current_steps": 22170, "total_steps": 38150, "loss": 0.4411, "lr": 2.2291261078568057e-05, "epoch": 5.81127129750983, "percentage": 58.11, "elapsed_time": "0:37:20", "remaining_time": "0:26:55", "throughput": 2652.76, "total_tokens": 5944672} {"current_steps": 22175, "total_steps": 38150, "loss": 0.2584, "lr": 2.22798914132179e-05, "epoch": 5.812581913499344, "percentage": 58.13, "elapsed_time": "0:37:21", "remaining_time": "0:26:54", "throughput": 2652.88, "total_tokens": 5946208} {"current_steps": 22180, "total_steps": 38150, "loss": 0.3289, "lr": 2.226852231718177e-05, "epoch": 5.81389252948886, "percentage": 58.14, "elapsed_time": "0:37:21", "remaining_time": "0:26:54", "throughput": 2652.92, "total_tokens": 5947456} {"current_steps": 22185, "total_steps": 38150, "loss": 0.3576, "lr": 2.2257153792839202e-05, "epoch": 5.815203145478375, "percentage": 58.15, "elapsed_time": "0:37:22", "remaining_time": "0:26:53", "throughput": 2652.9, "total_tokens": 5948560} {"current_steps": 22190, "total_steps": 38150, "loss": 0.3617, "lr": 2.2245785842569604e-05, "epoch": 5.81651376146789, "percentage": 58.17, "elapsed_time": "0:37:22", "remaining_time": "0:26:53", "throughput": 2652.83, "total_tokens": 5949504} {"current_steps": 22195, "total_steps": 38150, "loss": 0.4386, "lr": 2.2234418468752276e-05, "epoch": 5.817824377457405, "percentage": 58.18, "elapsed_time": "0:37:23", "remaining_time": "0:26:52", "throughput": 2652.83, "total_tokens": 5950720} {"current_steps": 22200, "total_steps": 38150, "loss": 0.2512, "lr": 2.222305167376638e-05, "epoch": 5.81913499344692, "percentage": 58.19, "elapsed_time": "0:37:23", "remaining_time": "0:26:51", "throughput": 2652.84, "total_tokens": 5951856} {"current_steps": 22205, "total_steps": 38150, "loss": 0.2771, "lr": 2.221168545999097e-05, "epoch": 5.820445609436435, "percentage": 58.2, "elapsed_time": "0:37:24", "remaining_time": "0:26:51", "throughput": 2652.92, "total_tokens": 5953184} {"current_steps": 22210, "total_steps": 38150, "loss": 0.2769, "lr": 2.2200319829804978e-05, "epoch": 5.8217562254259505, "percentage": 58.22, "elapsed_time": "0:37:24", "remaining_time": "0:26:50", "throughput": 2652.88, "total_tokens": 5954208} {"current_steps": 22215, "total_steps": 38150, "loss": 0.199, "lr": 2.2188954785587207e-05, "epoch": 5.823066841415465, "percentage": 58.23, "elapsed_time": "0:37:24", "remaining_time": "0:26:50", "throughput": 2652.88, "total_tokens": 5955376} {"current_steps": 22220, "total_steps": 38150, "loss": 0.2959, "lr": 2.2177590329716345e-05, "epoch": 5.824377457404981, "percentage": 58.24, "elapsed_time": "0:37:25", "remaining_time": "0:26:49", "throughput": 2652.97, "total_tokens": 5956752} {"current_steps": 22225, "total_steps": 38150, "loss": 0.1849, "lr": 2.2166226464570947e-05, "epoch": 5.825688073394495, "percentage": 58.26, "elapsed_time": "0:37:25", "remaining_time": "0:26:49", "throughput": 2652.92, "total_tokens": 5957760} {"current_steps": 22230, "total_steps": 38150, "loss": 0.3648, "lr": 2.2154863192529453e-05, "epoch": 5.826998689384011, "percentage": 58.27, "elapsed_time": "0:37:26", "remaining_time": "0:26:48", "throughput": 2652.99, "total_tokens": 5959152} {"current_steps": 22235, "total_steps": 38150, "loss": 0.2452, "lr": 2.2143500515970173e-05, "epoch": 5.8283093053735255, "percentage": 58.28, "elapsed_time": "0:37:26", "remaining_time": "0:26:48", "throughput": 2653.02, "total_tokens": 5960368} {"current_steps": 22240, "total_steps": 38150, "loss": 0.3072, "lr": 2.21321384372713e-05, "epoch": 5.82961992136304, "percentage": 58.3, "elapsed_time": "0:37:27", "remaining_time": "0:26:47", "throughput": 2653.17, "total_tokens": 5962016} {"current_steps": 22245, "total_steps": 38150, "loss": 0.1924, "lr": 2.2120776958810902e-05, "epoch": 5.830930537352556, "percentage": 58.31, "elapsed_time": "0:37:27", "remaining_time": "0:26:46", "throughput": 2653.12, "total_tokens": 5963040} {"current_steps": 22250, "total_steps": 38150, "loss": 0.2743, "lr": 2.2109416082966907e-05, "epoch": 5.832241153342071, "percentage": 58.32, "elapsed_time": "0:37:27", "remaining_time": "0:26:46", "throughput": 2653.16, "total_tokens": 5964256} {"current_steps": 22255, "total_steps": 38150, "loss": 0.2723, "lr": 2.2098055812117143e-05, "epoch": 5.833551769331586, "percentage": 58.34, "elapsed_time": "0:37:28", "remaining_time": "0:26:45", "throughput": 2653.09, "total_tokens": 5965200} {"current_steps": 22260, "total_steps": 38150, "loss": 0.3606, "lr": 2.208669614863927e-05, "epoch": 5.834862385321101, "percentage": 58.35, "elapsed_time": "0:37:28", "remaining_time": "0:26:45", "throughput": 2653.23, "total_tokens": 5966784} {"current_steps": 22265, "total_steps": 38150, "loss": 0.4028, "lr": 2.2075337094910868e-05, "epoch": 5.836173001310616, "percentage": 58.36, "elapsed_time": "0:37:29", "remaining_time": "0:26:44", "throughput": 2653.22, "total_tokens": 5967872} {"current_steps": 22270, "total_steps": 38150, "loss": 0.4015, "lr": 2.2063978653309354e-05, "epoch": 5.837483617300131, "percentage": 58.37, "elapsed_time": "0:37:29", "remaining_time": "0:26:44", "throughput": 2653.36, "total_tokens": 5969648} {"current_steps": 22275, "total_steps": 38150, "loss": 0.4195, "lr": 2.2052620826212035e-05, "epoch": 5.838794233289646, "percentage": 58.39, "elapsed_time": "0:37:30", "remaining_time": "0:26:43", "throughput": 2653.48, "total_tokens": 5971168} {"current_steps": 22280, "total_steps": 38150, "loss": 0.3831, "lr": 2.204126361599609e-05, "epoch": 5.840104849279161, "percentage": 58.4, "elapsed_time": "0:37:30", "remaining_time": "0:26:43", "throughput": 2653.76, "total_tokens": 5973200} {"current_steps": 22285, "total_steps": 38150, "loss": 0.224, "lr": 2.2029907025038548e-05, "epoch": 5.8414154652686765, "percentage": 58.41, "elapsed_time": "0:37:31", "remaining_time": "0:26:42", "throughput": 2653.72, "total_tokens": 5974224} {"current_steps": 22290, "total_steps": 38150, "loss": 0.3928, "lr": 2.201855105571634e-05, "epoch": 5.842726081258191, "percentage": 58.43, "elapsed_time": "0:37:31", "remaining_time": "0:26:42", "throughput": 2653.78, "total_tokens": 5975504} {"current_steps": 22295, "total_steps": 38150, "loss": 0.261, "lr": 2.2007195710406236e-05, "epoch": 5.844036697247707, "percentage": 58.44, "elapsed_time": "0:37:32", "remaining_time": "0:26:41", "throughput": 2653.77, "total_tokens": 5976608} {"current_steps": 22300, "total_steps": 38150, "loss": 0.3355, "lr": 2.1995840991484906e-05, "epoch": 5.845347313237221, "percentage": 58.45, "elapsed_time": "0:37:32", "remaining_time": "0:26:41", "throughput": 2653.77, "total_tokens": 5977760} {"current_steps": 22305, "total_steps": 38150, "loss": 0.2618, "lr": 2.198448690132886e-05, "epoch": 5.846657929226737, "percentage": 58.47, "elapsed_time": "0:37:32", "remaining_time": "0:26:40", "throughput": 2653.77, "total_tokens": 5978896} {"current_steps": 22310, "total_steps": 38150, "loss": 0.3501, "lr": 2.19731334423145e-05, "epoch": 5.8479685452162515, "percentage": 58.48, "elapsed_time": "0:37:33", "remaining_time": "0:26:39", "throughput": 2653.94, "total_tokens": 5980576} {"current_steps": 22315, "total_steps": 38150, "loss": 0.3858, "lr": 2.196178061681809e-05, "epoch": 5.849279161205767, "percentage": 58.49, "elapsed_time": "0:37:33", "remaining_time": "0:26:39", "throughput": 2653.9, "total_tokens": 5981632} {"current_steps": 22320, "total_steps": 38150, "loss": 0.2392, "lr": 2.1950428427215737e-05, "epoch": 5.850589777195282, "percentage": 58.51, "elapsed_time": "0:37:34", "remaining_time": "0:26:38", "throughput": 2654.05, "total_tokens": 5983392} {"current_steps": 22325, "total_steps": 38150, "loss": 0.3328, "lr": 2.1939076875883448e-05, "epoch": 5.851900393184797, "percentage": 58.52, "elapsed_time": "0:37:34", "remaining_time": "0:26:38", "throughput": 2654.2, "total_tokens": 5985072} {"current_steps": 22330, "total_steps": 38150, "loss": 0.4737, "lr": 2.1927725965197074e-05, "epoch": 5.853211009174312, "percentage": 58.53, "elapsed_time": "0:37:35", "remaining_time": "0:26:37", "throughput": 2654.26, "total_tokens": 5986368} {"current_steps": 22335, "total_steps": 38150, "loss": 0.2781, "lr": 2.191637569753235e-05, "epoch": 5.854521625163827, "percentage": 58.55, "elapsed_time": "0:37:35", "remaining_time": "0:26:37", "throughput": 2654.16, "total_tokens": 5987264} {"current_steps": 22340, "total_steps": 38150, "loss": 0.2499, "lr": 2.1905026075264873e-05, "epoch": 5.855832241153342, "percentage": 58.56, "elapsed_time": "0:37:36", "remaining_time": "0:26:36", "throughput": 2654.14, "total_tokens": 5988320} {"current_steps": 22345, "total_steps": 38150, "loss": 0.2985, "lr": 2.1893677100770084e-05, "epoch": 5.857142857142857, "percentage": 58.57, "elapsed_time": "0:37:36", "remaining_time": "0:26:36", "throughput": 2654.16, "total_tokens": 5989600} {"current_steps": 22350, "total_steps": 38150, "loss": 0.4288, "lr": 2.18823287764233e-05, "epoch": 5.858453473132372, "percentage": 58.58, "elapsed_time": "0:37:37", "remaining_time": "0:26:35", "throughput": 2654.34, "total_tokens": 5991280} {"current_steps": 22355, "total_steps": 38150, "loss": 0.2603, "lr": 2.187098110459973e-05, "epoch": 5.859764089121887, "percentage": 58.6, "elapsed_time": "0:37:37", "remaining_time": "0:26:35", "throughput": 2654.34, "total_tokens": 5992416} {"current_steps": 22360, "total_steps": 38150, "loss": 0.312, "lr": 2.1859634087674398e-05, "epoch": 5.8610747051114025, "percentage": 58.61, "elapsed_time": "0:37:38", "remaining_time": "0:26:34", "throughput": 2654.36, "total_tokens": 5993680} {"current_steps": 22365, "total_steps": 38150, "loss": 0.2789, "lr": 2.1848287728022233e-05, "epoch": 5.862385321100917, "percentage": 58.62, "elapsed_time": "0:37:38", "remaining_time": "0:26:34", "throughput": 2654.4, "total_tokens": 5994912} {"current_steps": 22370, "total_steps": 38150, "loss": 0.3402, "lr": 2.1836942028018e-05, "epoch": 5.863695937090433, "percentage": 58.64, "elapsed_time": "0:37:38", "remaining_time": "0:26:33", "throughput": 2654.49, "total_tokens": 5996336} {"current_steps": 22375, "total_steps": 38150, "loss": 0.3084, "lr": 2.182559699003634e-05, "epoch": 5.865006553079947, "percentage": 58.65, "elapsed_time": "0:37:39", "remaining_time": "0:26:32", "throughput": 2654.5, "total_tokens": 5997504} {"current_steps": 22380, "total_steps": 38150, "loss": 0.3369, "lr": 2.1814252616451735e-05, "epoch": 5.866317169069463, "percentage": 58.66, "elapsed_time": "0:37:39", "remaining_time": "0:26:32", "throughput": 2654.62, "total_tokens": 5999040} {"current_steps": 22385, "total_steps": 38150, "loss": 0.2533, "lr": 2.1802908909638558e-05, "epoch": 5.8676277850589775, "percentage": 58.68, "elapsed_time": "0:37:40", "remaining_time": "0:26:31", "throughput": 2654.65, "total_tokens": 6000336} {"current_steps": 22390, "total_steps": 38150, "loss": 0.2464, "lr": 2.1791565871971024e-05, "epoch": 5.868938401048493, "percentage": 58.69, "elapsed_time": "0:37:40", "remaining_time": "0:26:31", "throughput": 2654.7, "total_tokens": 6001584} {"current_steps": 22395, "total_steps": 38150, "loss": 0.2989, "lr": 2.1780223505823212e-05, "epoch": 5.870249017038008, "percentage": 58.7, "elapsed_time": "0:37:41", "remaining_time": "0:26:30", "throughput": 2654.69, "total_tokens": 6002688} {"current_steps": 22400, "total_steps": 38150, "loss": 0.4203, "lr": 2.1768881813569046e-05, "epoch": 5.871559633027523, "percentage": 58.72, "elapsed_time": "0:37:41", "remaining_time": "0:26:30", "throughput": 2654.74, "total_tokens": 6003952} {"current_steps": 22405, "total_steps": 38150, "loss": 0.3378, "lr": 2.175754079758234e-05, "epoch": 5.872870249017038, "percentage": 58.73, "elapsed_time": "0:37:42", "remaining_time": "0:26:29", "throughput": 2654.79, "total_tokens": 6005184} {"current_steps": 22410, "total_steps": 38150, "loss": 0.3275, "lr": 2.1746200460236736e-05, "epoch": 5.8741808650065535, "percentage": 58.74, "elapsed_time": "0:37:42", "remaining_time": "0:26:29", "throughput": 2654.82, "total_tokens": 6006416} {"current_steps": 22415, "total_steps": 38150, "loss": 0.3323, "lr": 2.173486080390576e-05, "epoch": 5.875491480996068, "percentage": 58.75, "elapsed_time": "0:37:42", "remaining_time": "0:26:28", "throughput": 2654.85, "total_tokens": 6007616} {"current_steps": 22420, "total_steps": 38150, "loss": 0.3147, "lr": 2.1723521830962774e-05, "epoch": 5.876802096985584, "percentage": 58.77, "elapsed_time": "0:37:43", "remaining_time": "0:26:27", "throughput": 2654.95, "total_tokens": 6009040} {"current_steps": 22425, "total_steps": 38150, "loss": 0.2423, "lr": 2.1712183543781005e-05, "epoch": 5.878112712975098, "percentage": 58.78, "elapsed_time": "0:37:43", "remaining_time": "0:26:27", "throughput": 2654.95, "total_tokens": 6010144} {"current_steps": 22430, "total_steps": 38150, "loss": 0.2744, "lr": 2.1700845944733543e-05, "epoch": 5.879423328964613, "percentage": 58.79, "elapsed_time": "0:37:44", "remaining_time": "0:26:26", "throughput": 2654.93, "total_tokens": 6011232} {"current_steps": 22435, "total_steps": 38150, "loss": 0.263, "lr": 2.1689509036193333e-05, "epoch": 5.8807339449541285, "percentage": 58.81, "elapsed_time": "0:37:44", "remaining_time": "0:26:26", "throughput": 2654.83, "total_tokens": 6012096} {"current_steps": 22440, "total_steps": 38150, "loss": 0.4102, "lr": 2.167817282053315e-05, "epoch": 5.882044560943643, "percentage": 58.82, "elapsed_time": "0:37:45", "remaining_time": "0:26:25", "throughput": 2654.95, "total_tokens": 6013632} {"current_steps": 22445, "total_steps": 38150, "loss": 0.354, "lr": 2.166683730012566e-05, "epoch": 5.883355176933159, "percentage": 58.83, "elapsed_time": "0:37:45", "remaining_time": "0:26:25", "throughput": 2654.89, "total_tokens": 6014608} {"current_steps": 22450, "total_steps": 38150, "loss": 0.2816, "lr": 2.1655502477343363e-05, "epoch": 5.884665792922673, "percentage": 58.85, "elapsed_time": "0:37:45", "remaining_time": "0:26:24", "throughput": 2654.92, "total_tokens": 6015824} {"current_steps": 22455, "total_steps": 38150, "loss": 0.3447, "lr": 2.164416835455862e-05, "epoch": 5.885976408912189, "percentage": 58.86, "elapsed_time": "0:37:46", "remaining_time": "0:26:24", "throughput": 2655.05, "total_tokens": 6017440} {"current_steps": 22460, "total_steps": 38150, "loss": 0.2427, "lr": 2.1632834934143642e-05, "epoch": 5.8872870249017035, "percentage": 58.87, "elapsed_time": "0:37:46", "remaining_time": "0:26:23", "throughput": 2655.04, "total_tokens": 6018592} {"current_steps": 22465, "total_steps": 38150, "loss": 0.2509, "lr": 2.162150221847048e-05, "epoch": 5.888597640891219, "percentage": 58.89, "elapsed_time": "0:37:47", "remaining_time": "0:26:23", "throughput": 2655.07, "total_tokens": 6019776} {"current_steps": 22470, "total_steps": 38150, "loss": 0.4204, "lr": 2.1610170209911085e-05, "epoch": 5.889908256880734, "percentage": 58.9, "elapsed_time": "0:37:47", "remaining_time": "0:26:22", "throughput": 2655.13, "total_tokens": 6021056} {"current_steps": 22475, "total_steps": 38150, "loss": 0.2983, "lr": 2.15988389108372e-05, "epoch": 5.891218872870249, "percentage": 58.91, "elapsed_time": "0:37:48", "remaining_time": "0:26:21", "throughput": 2655.23, "total_tokens": 6022528} {"current_steps": 22480, "total_steps": 38150, "loss": 0.3481, "lr": 2.1587508323620452e-05, "epoch": 5.892529488859764, "percentage": 58.93, "elapsed_time": "0:37:48", "remaining_time": "0:26:21", "throughput": 2655.31, "total_tokens": 6023872} {"current_steps": 22485, "total_steps": 38150, "loss": 0.2839, "lr": 2.1576178450632324e-05, "epoch": 5.8938401048492794, "percentage": 58.94, "elapsed_time": "0:37:49", "remaining_time": "0:26:20", "throughput": 2655.49, "total_tokens": 6025600} {"current_steps": 22490, "total_steps": 38150, "loss": 0.2619, "lr": 2.1564849294244126e-05, "epoch": 5.895150720838794, "percentage": 58.95, "elapsed_time": "0:37:49", "remaining_time": "0:26:20", "throughput": 2655.51, "total_tokens": 6026864} {"current_steps": 22495, "total_steps": 38150, "loss": 0.3217, "lr": 2.1553520856827038e-05, "epoch": 5.89646133682831, "percentage": 58.96, "elapsed_time": "0:37:49", "remaining_time": "0:26:19", "throughput": 2655.52, "total_tokens": 6028016} {"current_steps": 22500, "total_steps": 38150, "loss": 0.3202, "lr": 2.1542193140752074e-05, "epoch": 5.897771952817824, "percentage": 58.98, "elapsed_time": "0:37:50", "remaining_time": "0:26:19", "throughput": 2655.66, "total_tokens": 6029584} {"current_steps": 22505, "total_steps": 38150, "loss": 0.3385, "lr": 2.1530866148390114e-05, "epoch": 5.89908256880734, "percentage": 58.99, "elapsed_time": "0:37:50", "remaining_time": "0:26:18", "throughput": 2655.63, "total_tokens": 6030640} {"current_steps": 22510, "total_steps": 38150, "loss": 0.3568, "lr": 2.151953988211187e-05, "epoch": 5.9003931847968545, "percentage": 59.0, "elapsed_time": "0:37:51", "remaining_time": "0:26:18", "throughput": 2655.69, "total_tokens": 6031904} {"current_steps": 22515, "total_steps": 38150, "loss": 0.3018, "lr": 2.150821434428793e-05, "epoch": 5.90170380078637, "percentage": 59.02, "elapsed_time": "0:37:51", "remaining_time": "0:26:17", "throughput": 2655.79, "total_tokens": 6033584} {"current_steps": 22520, "total_steps": 38150, "loss": 0.2466, "lr": 2.149688953728867e-05, "epoch": 5.903014416775885, "percentage": 59.03, "elapsed_time": "0:37:52", "remaining_time": "0:26:17", "throughput": 2655.78, "total_tokens": 6034704} {"current_steps": 22525, "total_steps": 38150, "loss": 0.5025, "lr": 2.1485565463484395e-05, "epoch": 5.904325032765399, "percentage": 59.04, "elapsed_time": "0:37:52", "remaining_time": "0:26:16", "throughput": 2656.01, "total_tokens": 6036624} {"current_steps": 22530, "total_steps": 38150, "loss": 0.3513, "lr": 2.1474242125245192e-05, "epoch": 5.905635648754915, "percentage": 59.06, "elapsed_time": "0:37:53", "remaining_time": "0:26:16", "throughput": 2656.01, "total_tokens": 6037840} {"current_steps": 22535, "total_steps": 38150, "loss": 0.3775, "lr": 2.1462919524941018e-05, "epoch": 5.9069462647444295, "percentage": 59.07, "elapsed_time": "0:37:53", "remaining_time": "0:26:15", "throughput": 2656.13, "total_tokens": 6039344} {"current_steps": 22540, "total_steps": 38150, "loss": 0.383, "lr": 2.145159766494168e-05, "epoch": 5.908256880733945, "percentage": 59.08, "elapsed_time": "0:37:54", "remaining_time": "0:26:15", "throughput": 2656.24, "total_tokens": 6040912} {"current_steps": 22545, "total_steps": 38150, "loss": 0.2177, "lr": 2.1440276547616815e-05, "epoch": 5.90956749672346, "percentage": 59.1, "elapsed_time": "0:37:54", "remaining_time": "0:26:14", "throughput": 2656.24, "total_tokens": 6042048} {"current_steps": 22550, "total_steps": 38150, "loss": 0.3166, "lr": 2.1428956175335922e-05, "epoch": 5.910878112712975, "percentage": 59.11, "elapsed_time": "0:37:55", "remaining_time": "0:26:13", "throughput": 2656.26, "total_tokens": 6043328} {"current_steps": 22555, "total_steps": 38150, "loss": 0.2565, "lr": 2.141763655046833e-05, "epoch": 5.91218872870249, "percentage": 59.12, "elapsed_time": "0:37:55", "remaining_time": "0:26:13", "throughput": 2656.2, "total_tokens": 6044288} {"current_steps": 22560, "total_steps": 38150, "loss": 0.2358, "lr": 2.140631767538322e-05, "epoch": 5.913499344692005, "percentage": 59.13, "elapsed_time": "0:37:55", "remaining_time": "0:26:12", "throughput": 2656.19, "total_tokens": 6045392} {"current_steps": 22565, "total_steps": 38150, "loss": 0.3135, "lr": 2.1394999552449608e-05, "epoch": 5.91480996068152, "percentage": 59.15, "elapsed_time": "0:37:56", "remaining_time": "0:26:12", "throughput": 2656.25, "total_tokens": 6046688} {"current_steps": 22570, "total_steps": 38150, "loss": 0.4586, "lr": 2.1383682184036357e-05, "epoch": 5.916120576671036, "percentage": 59.16, "elapsed_time": "0:37:56", "remaining_time": "0:26:11", "throughput": 2656.16, "total_tokens": 6047584} {"current_steps": 22575, "total_steps": 38150, "loss": 0.3766, "lr": 2.1372365572512188e-05, "epoch": 5.91743119266055, "percentage": 59.17, "elapsed_time": "0:37:57", "remaining_time": "0:26:11", "throughput": 2656.23, "total_tokens": 6048912} {"current_steps": 22580, "total_steps": 38150, "loss": 0.2742, "lr": 2.136104972024562e-05, "epoch": 5.918741808650066, "percentage": 59.19, "elapsed_time": "0:37:57", "remaining_time": "0:26:10", "throughput": 2656.17, "total_tokens": 6049856} {"current_steps": 22585, "total_steps": 38150, "loss": 0.2654, "lr": 2.134973462960507e-05, "epoch": 5.9200524246395805, "percentage": 59.2, "elapsed_time": "0:37:58", "remaining_time": "0:26:10", "throughput": 2656.2, "total_tokens": 6051152} {"current_steps": 22590, "total_steps": 38150, "loss": 0.2205, "lr": 2.133842030295875e-05, "epoch": 5.921363040629096, "percentage": 59.21, "elapsed_time": "0:37:58", "remaining_time": "0:26:09", "throughput": 2656.32, "total_tokens": 6052672} {"current_steps": 22595, "total_steps": 38150, "loss": 0.3506, "lr": 2.1327106742674735e-05, "epoch": 5.922673656618611, "percentage": 59.23, "elapsed_time": "0:37:59", "remaining_time": "0:26:08", "throughput": 2656.32, "total_tokens": 6053840} {"current_steps": 22600, "total_steps": 38150, "loss": 0.3251, "lr": 2.1315793951120934e-05, "epoch": 5.923984272608125, "percentage": 59.24, "elapsed_time": "0:37:59", "remaining_time": "0:26:08", "throughput": 2656.51, "total_tokens": 6055696} {"current_steps": 22605, "total_steps": 38150, "loss": 0.3285, "lr": 2.1304481930665095e-05, "epoch": 5.925294888597641, "percentage": 59.25, "elapsed_time": "0:37:59", "remaining_time": "0:26:07", "throughput": 2656.46, "total_tokens": 6056720} {"current_steps": 22610, "total_steps": 38150, "loss": 0.3336, "lr": 2.1293170683674803e-05, "epoch": 5.926605504587156, "percentage": 59.27, "elapsed_time": "0:38:00", "remaining_time": "0:26:07", "throughput": 2656.52, "total_tokens": 6058080} {"current_steps": 22615, "total_steps": 38150, "loss": 0.377, "lr": 2.1281860212517477e-05, "epoch": 5.927916120576671, "percentage": 59.28, "elapsed_time": "0:38:00", "remaining_time": "0:26:06", "throughput": 2656.64, "total_tokens": 6059616} {"current_steps": 22620, "total_steps": 38150, "loss": 0.3045, "lr": 2.1270550519560387e-05, "epoch": 5.929226736566186, "percentage": 59.29, "elapsed_time": "0:38:01", "remaining_time": "0:26:06", "throughput": 2656.84, "total_tokens": 6061408} {"current_steps": 22625, "total_steps": 38150, "loss": 0.2191, "lr": 2.125924160717063e-05, "epoch": 5.930537352555701, "percentage": 59.31, "elapsed_time": "0:38:01", "remaining_time": "0:26:05", "throughput": 2656.94, "total_tokens": 6062864} {"current_steps": 22630, "total_steps": 38150, "loss": 0.2838, "lr": 2.1247933477715145e-05, "epoch": 5.931847968545216, "percentage": 59.32, "elapsed_time": "0:38:02", "remaining_time": "0:26:05", "throughput": 2657.14, "total_tokens": 6064784} {"current_steps": 22635, "total_steps": 38150, "loss": 0.2735, "lr": 2.123662613356068e-05, "epoch": 5.933158584534731, "percentage": 59.33, "elapsed_time": "0:38:02", "remaining_time": "0:26:04", "throughput": 2657.29, "total_tokens": 6066464} {"current_steps": 22640, "total_steps": 38150, "loss": 0.2632, "lr": 2.1225319577073877e-05, "epoch": 5.934469200524246, "percentage": 59.34, "elapsed_time": "0:38:03", "remaining_time": "0:26:04", "throughput": 2657.29, "total_tokens": 6067584} {"current_steps": 22645, "total_steps": 38150, "loss": 0.368, "lr": 2.121401381062117e-05, "epoch": 5.935779816513762, "percentage": 59.36, "elapsed_time": "0:38:03", "remaining_time": "0:26:03", "throughput": 2657.27, "total_tokens": 6068672} {"current_steps": 22650, "total_steps": 38150, "loss": 0.2221, "lr": 2.1202708836568826e-05, "epoch": 5.937090432503276, "percentage": 59.37, "elapsed_time": "0:38:04", "remaining_time": "0:26:03", "throughput": 2657.39, "total_tokens": 6070352} {"current_steps": 22655, "total_steps": 38150, "loss": 0.3385, "lr": 2.1191404657282957e-05, "epoch": 5.938401048492792, "percentage": 59.38, "elapsed_time": "0:38:04", "remaining_time": "0:26:02", "throughput": 2657.43, "total_tokens": 6071648} {"current_steps": 22660, "total_steps": 38150, "loss": 0.2169, "lr": 2.1180101275129515e-05, "epoch": 5.9397116644823065, "percentage": 59.4, "elapsed_time": "0:38:05", "remaining_time": "0:26:02", "throughput": 2657.32, "total_tokens": 6072528} {"current_steps": 22665, "total_steps": 38150, "loss": 0.2464, "lr": 2.1168798692474277e-05, "epoch": 5.941022280471822, "percentage": 59.41, "elapsed_time": "0:38:05", "remaining_time": "0:26:01", "throughput": 2657.36, "total_tokens": 6073744} {"current_steps": 22670, "total_steps": 38150, "loss": 0.2838, "lr": 2.115749691168286e-05, "epoch": 5.942332896461337, "percentage": 59.42, "elapsed_time": "0:38:06", "remaining_time": "0:26:01", "throughput": 2657.35, "total_tokens": 6074848} {"current_steps": 22675, "total_steps": 38150, "loss": 0.2658, "lr": 2.114619593512069e-05, "epoch": 5.943643512450852, "percentage": 59.44, "elapsed_time": "0:38:06", "remaining_time": "0:26:00", "throughput": 2657.39, "total_tokens": 6076128} {"current_steps": 22680, "total_steps": 38150, "loss": 0.2399, "lr": 2.1134895765153057e-05, "epoch": 5.944954128440367, "percentage": 59.45, "elapsed_time": "0:38:06", "remaining_time": "0:25:59", "throughput": 2657.4, "total_tokens": 6077280} {"current_steps": 22685, "total_steps": 38150, "loss": 0.3779, "lr": 2.112359640414506e-05, "epoch": 5.946264744429882, "percentage": 59.46, "elapsed_time": "0:38:07", "remaining_time": "0:25:59", "throughput": 2657.53, "total_tokens": 6078768} {"current_steps": 22690, "total_steps": 38150, "loss": 0.352, "lr": 2.111229785446164e-05, "epoch": 5.947575360419397, "percentage": 59.48, "elapsed_time": "0:38:07", "remaining_time": "0:25:58", "throughput": 2657.7, "total_tokens": 6080528} {"current_steps": 22695, "total_steps": 38150, "loss": 0.3598, "lr": 2.110100011846755e-05, "epoch": 5.948885976408912, "percentage": 59.49, "elapsed_time": "0:38:08", "remaining_time": "0:25:58", "throughput": 2657.72, "total_tokens": 6081792} {"current_steps": 22700, "total_steps": 38150, "loss": 0.2017, "lr": 2.1089703198527407e-05, "epoch": 5.950196592398427, "percentage": 59.5, "elapsed_time": "0:38:08", "remaining_time": "0:25:57", "throughput": 2657.8, "total_tokens": 6083136} {"current_steps": 22705, "total_steps": 38150, "loss": 0.2815, "lr": 2.1078407097005632e-05, "epoch": 5.951507208387943, "percentage": 59.52, "elapsed_time": "0:38:09", "remaining_time": "0:25:57", "throughput": 2657.79, "total_tokens": 6084240} {"current_steps": 22710, "total_steps": 38150, "loss": 0.3472, "lr": 2.106711181626647e-05, "epoch": 5.952817824377457, "percentage": 59.53, "elapsed_time": "0:38:09", "remaining_time": "0:25:56", "throughput": 2658.05, "total_tokens": 6086384} {"current_steps": 22715, "total_steps": 38150, "loss": 0.3313, "lr": 2.105581735867401e-05, "epoch": 5.954128440366972, "percentage": 59.54, "elapsed_time": "0:38:10", "remaining_time": "0:25:56", "throughput": 2658.03, "total_tokens": 6087456} {"current_steps": 22720, "total_steps": 38150, "loss": 0.2307, "lr": 2.1044523726592165e-05, "epoch": 5.955439056356488, "percentage": 59.55, "elapsed_time": "0:38:10", "remaining_time": "0:25:55", "throughput": 2657.98, "total_tokens": 6088464} {"current_steps": 22725, "total_steps": 38150, "loss": 0.2865, "lr": 2.1033230922384672e-05, "epoch": 5.956749672346002, "percentage": 59.57, "elapsed_time": "0:38:11", "remaining_time": "0:25:55", "throughput": 2658.22, "total_tokens": 6090464} {"current_steps": 22730, "total_steps": 38150, "loss": 0.2249, "lr": 2.1021938948415086e-05, "epoch": 5.958060288335518, "percentage": 59.58, "elapsed_time": "0:38:11", "remaining_time": "0:25:54", "throughput": 2658.13, "total_tokens": 6091360} {"current_steps": 22735, "total_steps": 38150, "loss": 0.2436, "lr": 2.1010647807046806e-05, "epoch": 5.9593709043250325, "percentage": 59.59, "elapsed_time": "0:38:12", "remaining_time": "0:25:54", "throughput": 2658.26, "total_tokens": 6092912} {"current_steps": 22740, "total_steps": 38150, "loss": 0.3265, "lr": 2.099935750064305e-05, "epoch": 5.960681520314548, "percentage": 59.61, "elapsed_time": "0:38:12", "remaining_time": "0:25:53", "throughput": 2658.36, "total_tokens": 6094384} {"current_steps": 22745, "total_steps": 38150, "loss": 0.3902, "lr": 2.0988068031566854e-05, "epoch": 5.961992136304063, "percentage": 59.62, "elapsed_time": "0:38:12", "remaining_time": "0:25:53", "throughput": 2658.4, "total_tokens": 6095616} {"current_steps": 22750, "total_steps": 38150, "loss": 0.2906, "lr": 2.097677940218108e-05, "epoch": 5.963302752293578, "percentage": 59.63, "elapsed_time": "0:38:13", "remaining_time": "0:25:52", "throughput": 2658.39, "total_tokens": 6096720} {"current_steps": 22755, "total_steps": 38150, "loss": 0.4488, "lr": 2.0965491614848433e-05, "epoch": 5.964613368283093, "percentage": 59.65, "elapsed_time": "0:38:13", "remaining_time": "0:25:51", "throughput": 2658.62, "total_tokens": 6098592} {"current_steps": 22760, "total_steps": 38150, "loss": 0.3808, "lr": 2.095420467193142e-05, "epoch": 5.965923984272608, "percentage": 59.66, "elapsed_time": "0:38:14", "remaining_time": "0:25:51", "throughput": 2658.69, "total_tokens": 6099920} {"current_steps": 22765, "total_steps": 38150, "loss": 0.4014, "lr": 2.0942918575792382e-05, "epoch": 5.967234600262123, "percentage": 59.67, "elapsed_time": "0:38:14", "remaining_time": "0:25:50", "throughput": 2658.75, "total_tokens": 6101232} {"current_steps": 22770, "total_steps": 38150, "loss": 0.2717, "lr": 2.0931633328793472e-05, "epoch": 5.968545216251639, "percentage": 59.69, "elapsed_time": "0:38:15", "remaining_time": "0:25:50", "throughput": 2658.81, "total_tokens": 6102608} {"current_steps": 22775, "total_steps": 38150, "loss": 0.2786, "lr": 2.0920348933296678e-05, "epoch": 5.969855832241153, "percentage": 59.7, "elapsed_time": "0:38:15", "remaining_time": "0:25:49", "throughput": 2659.1, "total_tokens": 6104928} {"current_steps": 22780, "total_steps": 38150, "loss": 0.4099, "lr": 2.09090653916638e-05, "epoch": 5.971166448230669, "percentage": 59.71, "elapsed_time": "0:38:16", "remaining_time": "0:25:49", "throughput": 2659.11, "total_tokens": 6106096} {"current_steps": 22785, "total_steps": 38150, "loss": 0.2855, "lr": 2.0897782706256474e-05, "epoch": 5.972477064220183, "percentage": 59.72, "elapsed_time": "0:38:16", "remaining_time": "0:25:48", "throughput": 2659.16, "total_tokens": 6107584} {"current_steps": 22790, "total_steps": 38150, "loss": 0.3886, "lr": 2.0886500879436136e-05, "epoch": 5.973787680209698, "percentage": 59.74, "elapsed_time": "0:38:17", "remaining_time": "0:25:48", "throughput": 2659.33, "total_tokens": 6109232} {"current_steps": 22795, "total_steps": 38150, "loss": 0.3223, "lr": 2.0875219913564053e-05, "epoch": 5.975098296199214, "percentage": 59.75, "elapsed_time": "0:38:17", "remaining_time": "0:25:47", "throughput": 2659.31, "total_tokens": 6110384} {"current_steps": 22800, "total_steps": 38150, "loss": 0.2494, "lr": 2.0863939811001316e-05, "epoch": 5.976408912188729, "percentage": 59.76, "elapsed_time": "0:38:18", "remaining_time": "0:25:47", "throughput": 2659.41, "total_tokens": 6111840} {"current_steps": 22805, "total_steps": 38150, "loss": 0.2983, "lr": 2.0852660574108833e-05, "epoch": 5.977719528178244, "percentage": 59.78, "elapsed_time": "0:38:18", "remaining_time": "0:25:46", "throughput": 2659.56, "total_tokens": 6113504} {"current_steps": 22810, "total_steps": 38150, "loss": 0.233, "lr": 2.084138220524732e-05, "epoch": 5.9790301441677585, "percentage": 59.79, "elapsed_time": "0:38:19", "remaining_time": "0:25:46", "throughput": 2659.53, "total_tokens": 6114576} {"current_steps": 22815, "total_steps": 38150, "loss": 0.289, "lr": 2.0830104706777325e-05, "epoch": 5.980340760157274, "percentage": 59.8, "elapsed_time": "0:38:19", "remaining_time": "0:25:45", "throughput": 2659.51, "total_tokens": 6115632} {"current_steps": 22820, "total_steps": 38150, "loss": 0.2599, "lr": 2.081882808105922e-05, "epoch": 5.981651376146789, "percentage": 59.82, "elapsed_time": "0:38:20", "remaining_time": "0:25:45", "throughput": 2659.64, "total_tokens": 6117200} {"current_steps": 22825, "total_steps": 38150, "loss": 0.2292, "lr": 2.0807552330453166e-05, "epoch": 5.982961992136304, "percentage": 59.83, "elapsed_time": "0:38:20", "remaining_time": "0:25:44", "throughput": 2659.61, "total_tokens": 6118256} {"current_steps": 22830, "total_steps": 38150, "loss": 0.345, "lr": 2.079627745731917e-05, "epoch": 5.984272608125819, "percentage": 59.84, "elapsed_time": "0:38:20", "remaining_time": "0:25:44", "throughput": 2659.74, "total_tokens": 6119840} {"current_steps": 22835, "total_steps": 38150, "loss": 0.2819, "lr": 2.0785003464017032e-05, "epoch": 5.985583224115334, "percentage": 59.86, "elapsed_time": "0:38:21", "remaining_time": "0:25:43", "throughput": 2659.83, "total_tokens": 6121280} {"current_steps": 22840, "total_steps": 38150, "loss": 0.2161, "lr": 2.0773730352906394e-05, "epoch": 5.986893840104849, "percentage": 59.87, "elapsed_time": "0:38:21", "remaining_time": "0:25:42", "throughput": 2659.88, "total_tokens": 6122624} {"current_steps": 22845, "total_steps": 38150, "loss": 0.2645, "lr": 2.076245812634669e-05, "epoch": 5.988204456094365, "percentage": 59.88, "elapsed_time": "0:38:22", "remaining_time": "0:25:42", "throughput": 2659.79, "total_tokens": 6123504} {"current_steps": 22850, "total_steps": 38150, "loss": 0.2769, "lr": 2.0751186786697175e-05, "epoch": 5.989515072083879, "percentage": 59.9, "elapsed_time": "0:38:22", "remaining_time": "0:25:41", "throughput": 2659.74, "total_tokens": 6124496} {"current_steps": 22855, "total_steps": 38150, "loss": 0.397, "lr": 2.0739916336316924e-05, "epoch": 5.990825688073395, "percentage": 59.91, "elapsed_time": "0:38:23", "remaining_time": "0:25:41", "throughput": 2659.81, "total_tokens": 6125888} {"current_steps": 22860, "total_steps": 38150, "loss": 0.3974, "lr": 2.072864677756482e-05, "epoch": 5.992136304062909, "percentage": 59.92, "elapsed_time": "0:38:23", "remaining_time": "0:25:40", "throughput": 2659.95, "total_tokens": 6127520} {"current_steps": 22865, "total_steps": 38150, "loss": 0.2947, "lr": 2.0717378112799563e-05, "epoch": 5.993446920052425, "percentage": 59.93, "elapsed_time": "0:38:24", "remaining_time": "0:25:40", "throughput": 2660.07, "total_tokens": 6128992} {"current_steps": 22870, "total_steps": 38150, "loss": 0.2927, "lr": 2.070611034437967e-05, "epoch": 5.99475753604194, "percentage": 59.95, "elapsed_time": "0:38:24", "remaining_time": "0:25:39", "throughput": 2660.05, "total_tokens": 6130128} {"current_steps": 22875, "total_steps": 38150, "loss": 0.2242, "lr": 2.0694843474663465e-05, "epoch": 5.996068152031455, "percentage": 59.96, "elapsed_time": "0:38:24", "remaining_time": "0:25:39", "throughput": 2660.15, "total_tokens": 6131616} {"current_steps": 22880, "total_steps": 38150, "loss": 0.3423, "lr": 2.0683577506009087e-05, "epoch": 5.99737876802097, "percentage": 59.97, "elapsed_time": "0:38:25", "remaining_time": "0:25:38", "throughput": 2660.25, "total_tokens": 6133120} {"current_steps": 22885, "total_steps": 38150, "loss": 0.1497, "lr": 2.0672312440774473e-05, "epoch": 5.9986893840104845, "percentage": 59.99, "elapsed_time": "0:38:25", "remaining_time": "0:25:38", "throughput": 2660.24, "total_tokens": 6134224} {"current_steps": 22890, "total_steps": 38150, "loss": 0.3128, "lr": 2.0661048281317388e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:38:26", "remaining_time": "0:25:37", "throughput": 2660.21, "total_tokens": 6135704} {"current_steps": 22895, "total_steps": 38150, "loss": 0.2143, "lr": 2.06497850299954e-05, "epoch": 6.001310615989515, "percentage": 60.01, "elapsed_time": "0:38:27", "remaining_time": "0:25:37", "throughput": 2660.1, "total_tokens": 6137080} {"current_steps": 22896, "total_steps": 38150, "eval_loss": 0.5941077470779419, "epoch": 6.001572739187418, "percentage": 60.02, "elapsed_time": "0:38:44", "remaining_time": "0:25:48", "throughput": 2640.8, "total_tokens": 6137320} {"current_steps": 22900, "total_steps": 38150, "loss": 0.2131, "lr": 2.063852268916589e-05, "epoch": 6.00262123197903, "percentage": 60.03, "elapsed_time": "0:38:45", "remaining_time": "0:25:48", "throughput": 2639.15, "total_tokens": 6138248} {"current_steps": 22905, "total_steps": 38150, "loss": 0.2009, "lr": 2.062726126118605e-05, "epoch": 6.003931847968545, "percentage": 60.04, "elapsed_time": "0:38:46", "remaining_time": "0:25:48", "throughput": 2639.31, "total_tokens": 6139960} {"current_steps": 22910, "total_steps": 38150, "loss": 0.2314, "lr": 2.0616000748412864e-05, "epoch": 6.00524246395806, "percentage": 60.05, "elapsed_time": "0:38:46", "remaining_time": "0:25:47", "throughput": 2639.4, "total_tokens": 6141400} {"current_steps": 22915, "total_steps": 38150, "loss": 0.2027, "lr": 2.060474115320315e-05, "epoch": 6.006553079947575, "percentage": 60.07, "elapsed_time": "0:38:47", "remaining_time": "0:25:47", "throughput": 2639.41, "total_tokens": 6142536} {"current_steps": 22920, "total_steps": 38150, "loss": 0.3213, "lr": 2.059348247791352e-05, "epoch": 6.007863695937091, "percentage": 60.08, "elapsed_time": "0:38:47", "remaining_time": "0:25:46", "throughput": 2639.46, "total_tokens": 6143800} {"current_steps": 22925, "total_steps": 38150, "loss": 0.2734, "lr": 2.058222472490038e-05, "epoch": 6.009174311926605, "percentage": 60.09, "elapsed_time": "0:38:48", "remaining_time": "0:25:46", "throughput": 2639.46, "total_tokens": 6144936} {"current_steps": 22930, "total_steps": 38150, "loss": 0.2642, "lr": 2.0570967896519983e-05, "epoch": 6.010484927916121, "percentage": 60.1, "elapsed_time": "0:38:48", "remaining_time": "0:25:45", "throughput": 2639.57, "total_tokens": 6146504} {"current_steps": 22935, "total_steps": 38150, "loss": 0.2467, "lr": 2.0559711995128353e-05, "epoch": 6.011795543905635, "percentage": 60.12, "elapsed_time": "0:38:49", "remaining_time": "0:25:45", "throughput": 2639.51, "total_tokens": 6147464} {"current_steps": 22940, "total_steps": 38150, "loss": 0.1647, "lr": 2.0548457023081333e-05, "epoch": 6.013106159895151, "percentage": 60.13, "elapsed_time": "0:38:49", "remaining_time": "0:25:44", "throughput": 2639.64, "total_tokens": 6148952} {"current_steps": 22945, "total_steps": 38150, "loss": 0.1782, "lr": 2.0537202982734564e-05, "epoch": 6.014416775884666, "percentage": 60.14, "elapsed_time": "0:38:49", "remaining_time": "0:25:43", "throughput": 2639.66, "total_tokens": 6150152} {"current_steps": 22950, "total_steps": 38150, "loss": 0.2718, "lr": 2.0525949876443497e-05, "epoch": 6.015727391874181, "percentage": 60.16, "elapsed_time": "0:38:50", "remaining_time": "0:25:43", "throughput": 2639.74, "total_tokens": 6151592} {"current_steps": 22955, "total_steps": 38150, "loss": 0.2357, "lr": 2.051469770656339e-05, "epoch": 6.017038007863696, "percentage": 60.17, "elapsed_time": "0:38:50", "remaining_time": "0:25:42", "throughput": 2639.79, "total_tokens": 6152920} {"current_steps": 22960, "total_steps": 38150, "loss": 0.3069, "lr": 2.050344647544931e-05, "epoch": 6.018348623853211, "percentage": 60.18, "elapsed_time": "0:38:51", "remaining_time": "0:25:42", "throughput": 2639.95, "total_tokens": 6154696} {"current_steps": 22965, "total_steps": 38150, "loss": 0.2869, "lr": 2.0492196185456108e-05, "epoch": 6.019659239842726, "percentage": 60.2, "elapsed_time": "0:38:51", "remaining_time": "0:25:41", "throughput": 2640.06, "total_tokens": 6156200} {"current_steps": 22970, "total_steps": 38150, "loss": 0.2128, "lr": 2.0480946838938455e-05, "epoch": 6.0209698558322415, "percentage": 60.21, "elapsed_time": "0:38:52", "remaining_time": "0:25:41", "throughput": 2640.13, "total_tokens": 6157496} {"current_steps": 22975, "total_steps": 38150, "loss": 0.2268, "lr": 2.046969843825082e-05, "epoch": 6.022280471821756, "percentage": 60.22, "elapsed_time": "0:38:52", "remaining_time": "0:25:40", "throughput": 2640.12, "total_tokens": 6158584} {"current_steps": 22980, "total_steps": 38150, "loss": 0.2273, "lr": 2.0458450985747468e-05, "epoch": 6.023591087811272, "percentage": 60.24, "elapsed_time": "0:38:53", "remaining_time": "0:25:40", "throughput": 2640.23, "total_tokens": 6160120} {"current_steps": 22985, "total_steps": 38150, "loss": 0.2509, "lr": 2.0447204483782482e-05, "epoch": 6.024901703800786, "percentage": 60.25, "elapsed_time": "0:38:53", "remaining_time": "0:25:39", "throughput": 2640.22, "total_tokens": 6161240} {"current_steps": 22990, "total_steps": 38150, "loss": 0.1686, "lr": 2.0435958934709738e-05, "epoch": 6.026212319790301, "percentage": 60.26, "elapsed_time": "0:38:54", "remaining_time": "0:25:39", "throughput": 2640.21, "total_tokens": 6162408} {"current_steps": 22995, "total_steps": 38150, "loss": 0.1392, "lr": 2.0424714340882893e-05, "epoch": 6.027522935779817, "percentage": 60.28, "elapsed_time": "0:38:54", "remaining_time": "0:25:38", "throughput": 2640.27, "total_tokens": 6163704} {"current_steps": 23000, "total_steps": 38150, "loss": 0.2448, "lr": 2.0413470704655445e-05, "epoch": 6.028833551769331, "percentage": 60.29, "elapsed_time": "0:38:54", "remaining_time": "0:25:38", "throughput": 2640.32, "total_tokens": 6164968} {"current_steps": 23005, "total_steps": 38150, "loss": 0.2715, "lr": 2.0402228028380644e-05, "epoch": 6.030144167758847, "percentage": 60.3, "elapsed_time": "0:38:55", "remaining_time": "0:25:37", "throughput": 2640.78, "total_tokens": 6168184} {"current_steps": 23010, "total_steps": 38150, "loss": 0.0806, "lr": 2.0390986314411573e-05, "epoch": 6.031454783748361, "percentage": 60.31, "elapsed_time": "0:38:56", "remaining_time": "0:25:37", "throughput": 2640.77, "total_tokens": 6169304} {"current_steps": 23015, "total_steps": 38150, "loss": 0.1949, "lr": 2.03797455651011e-05, "epoch": 6.032765399737877, "percentage": 60.33, "elapsed_time": "0:38:56", "remaining_time": "0:25:36", "throughput": 2640.73, "total_tokens": 6170328} {"current_steps": 23020, "total_steps": 38150, "loss": 0.2034, "lr": 2.0368505782801904e-05, "epoch": 6.034076015727392, "percentage": 60.34, "elapsed_time": "0:38:57", "remaining_time": "0:25:36", "throughput": 2640.6, "total_tokens": 6171112} {"current_steps": 23025, "total_steps": 38150, "loss": 0.2577, "lr": 2.0357266969866443e-05, "epoch": 6.035386631716907, "percentage": 60.35, "elapsed_time": "0:38:57", "remaining_time": "0:25:35", "throughput": 2640.65, "total_tokens": 6172376} {"current_steps": 23030, "total_steps": 38150, "loss": 0.2855, "lr": 2.034602912864698e-05, "epoch": 6.036697247706422, "percentage": 60.37, "elapsed_time": "0:38:57", "remaining_time": "0:25:34", "throughput": 2640.71, "total_tokens": 6173800} {"current_steps": 23035, "total_steps": 38150, "loss": 0.2702, "lr": 2.0334792261495576e-05, "epoch": 6.038007863695937, "percentage": 60.38, "elapsed_time": "0:38:58", "remaining_time": "0:25:34", "throughput": 2640.81, "total_tokens": 6175176} {"current_steps": 23040, "total_steps": 38150, "loss": 0.2479, "lr": 2.032355637076409e-05, "epoch": 6.039318479685452, "percentage": 60.39, "elapsed_time": "0:38:58", "remaining_time": "0:25:33", "throughput": 2640.98, "total_tokens": 6176856} {"current_steps": 23045, "total_steps": 38150, "loss": 0.2433, "lr": 2.031232145880418e-05, "epoch": 6.0406290956749675, "percentage": 60.41, "elapsed_time": "0:38:59", "remaining_time": "0:25:33", "throughput": 2641.01, "total_tokens": 6178072} {"current_steps": 23050, "total_steps": 38150, "loss": 0.23, "lr": 2.030108752796729e-05, "epoch": 6.041939711664482, "percentage": 60.42, "elapsed_time": "0:38:59", "remaining_time": "0:25:32", "throughput": 2641.01, "total_tokens": 6179224} {"current_steps": 23055, "total_steps": 38150, "loss": 0.2068, "lr": 2.0289854580604667e-05, "epoch": 6.043250327653998, "percentage": 60.43, "elapsed_time": "0:39:00", "remaining_time": "0:25:32", "throughput": 2641.0, "total_tokens": 6180312} {"current_steps": 23060, "total_steps": 38150, "loss": 0.2516, "lr": 2.0278622619067334e-05, "epoch": 6.044560943643512, "percentage": 60.45, "elapsed_time": "0:39:00", "remaining_time": "0:25:31", "throughput": 2641.13, "total_tokens": 6181896} {"current_steps": 23065, "total_steps": 38150, "loss": 0.2532, "lr": 2.026739164570613e-05, "epoch": 6.045871559633028, "percentage": 60.46, "elapsed_time": "0:39:01", "remaining_time": "0:25:31", "throughput": 2641.22, "total_tokens": 6183272} {"current_steps": 23070, "total_steps": 38150, "loss": 0.2225, "lr": 2.0256161662871675e-05, "epoch": 6.047182175622543, "percentage": 60.47, "elapsed_time": "0:39:01", "remaining_time": "0:25:30", "throughput": 2641.29, "total_tokens": 6184648} {"current_steps": 23075, "total_steps": 38150, "loss": 0.1913, "lr": 2.0244932672914392e-05, "epoch": 6.048492791612058, "percentage": 60.48, "elapsed_time": "0:39:01", "remaining_time": "0:25:29", "throughput": 2641.26, "total_tokens": 6185656} {"current_steps": 23080, "total_steps": 38150, "loss": 0.1586, "lr": 2.0233704678184485e-05, "epoch": 6.049803407601573, "percentage": 60.5, "elapsed_time": "0:39:02", "remaining_time": "0:25:29", "throughput": 2641.25, "total_tokens": 6186760} {"current_steps": 23085, "total_steps": 38150, "loss": 0.2555, "lr": 2.0222477681031947e-05, "epoch": 6.051114023591087, "percentage": 60.51, "elapsed_time": "0:39:02", "remaining_time": "0:25:28", "throughput": 2641.29, "total_tokens": 6188008} {"current_steps": 23090, "total_steps": 38150, "loss": 0.2777, "lr": 2.021125168380658e-05, "epoch": 6.052424639580603, "percentage": 60.52, "elapsed_time": "0:39:03", "remaining_time": "0:25:28", "throughput": 2641.48, "total_tokens": 6189944} {"current_steps": 23095, "total_steps": 38150, "loss": 0.1128, "lr": 2.0200026688857955e-05, "epoch": 6.053735255570118, "percentage": 60.54, "elapsed_time": "0:39:03", "remaining_time": "0:25:27", "throughput": 2641.43, "total_tokens": 6190952} {"current_steps": 23100, "total_steps": 38150, "loss": 0.2504, "lr": 2.0188802698535455e-05, "epoch": 6.055045871559633, "percentage": 60.55, "elapsed_time": "0:39:04", "remaining_time": "0:25:27", "throughput": 2641.61, "total_tokens": 6192840} {"current_steps": 23105, "total_steps": 38150, "loss": 0.1608, "lr": 2.0177579715188234e-05, "epoch": 6.056356487549148, "percentage": 60.56, "elapsed_time": "0:39:04", "remaining_time": "0:25:26", "throughput": 2641.61, "total_tokens": 6193944} {"current_steps": 23110, "total_steps": 38150, "loss": 0.2891, "lr": 2.016635774116525e-05, "epoch": 6.057667103538663, "percentage": 60.58, "elapsed_time": "0:39:05", "remaining_time": "0:25:26", "throughput": 2641.71, "total_tokens": 6195368} {"current_steps": 23115, "total_steps": 38150, "loss": 0.2633, "lr": 2.0155136778815246e-05, "epoch": 6.058977719528178, "percentage": 60.59, "elapsed_time": "0:39:05", "remaining_time": "0:25:25", "throughput": 2641.7, "total_tokens": 6196536} {"current_steps": 23120, "total_steps": 38150, "loss": 0.2418, "lr": 2.0143916830486734e-05, "epoch": 6.0602883355176935, "percentage": 60.6, "elapsed_time": "0:39:06", "remaining_time": "0:25:25", "throughput": 2641.76, "total_tokens": 6197896} {"current_steps": 23125, "total_steps": 38150, "loss": 0.2121, "lr": 2.0132697898528037e-05, "epoch": 6.061598951507208, "percentage": 60.62, "elapsed_time": "0:39:06", "remaining_time": "0:25:24", "throughput": 2641.8, "total_tokens": 6199112} {"current_steps": 23130, "total_steps": 38150, "loss": 0.2621, "lr": 2.0121479985287264e-05, "epoch": 6.062909567496724, "percentage": 60.63, "elapsed_time": "0:39:07", "remaining_time": "0:25:24", "throughput": 2641.95, "total_tokens": 6200760} {"current_steps": 23135, "total_steps": 38150, "loss": 0.2228, "lr": 2.01102630931123e-05, "epoch": 6.064220183486238, "percentage": 60.64, "elapsed_time": "0:39:07", "remaining_time": "0:25:23", "throughput": 2641.92, "total_tokens": 6201816} {"current_steps": 23140, "total_steps": 38150, "loss": 0.3893, "lr": 2.0099047224350825e-05, "epoch": 6.065530799475754, "percentage": 60.66, "elapsed_time": "0:39:07", "remaining_time": "0:25:23", "throughput": 2642.09, "total_tokens": 6203512} {"current_steps": 23145, "total_steps": 38150, "loss": 0.2346, "lr": 2.0087832381350295e-05, "epoch": 6.066841415465269, "percentage": 60.67, "elapsed_time": "0:39:08", "remaining_time": "0:25:22", "throughput": 2642.11, "total_tokens": 6204712} {"current_steps": 23150, "total_steps": 38150, "loss": 0.2198, "lr": 2.007661856645796e-05, "epoch": 6.068152031454784, "percentage": 60.68, "elapsed_time": "0:39:08", "remaining_time": "0:25:21", "throughput": 2642.04, "total_tokens": 6205640} {"current_steps": 23155, "total_steps": 38150, "loss": 0.1677, "lr": 2.0065405782020844e-05, "epoch": 6.069462647444299, "percentage": 60.69, "elapsed_time": "0:39:09", "remaining_time": "0:25:21", "throughput": 2641.95, "total_tokens": 6206520} {"current_steps": 23160, "total_steps": 38150, "loss": 0.2687, "lr": 2.0054194030385774e-05, "epoch": 6.070773263433814, "percentage": 60.71, "elapsed_time": "0:39:09", "remaining_time": "0:25:20", "throughput": 2641.95, "total_tokens": 6207656} {"current_steps": 23165, "total_steps": 38150, "loss": 0.2296, "lr": 2.0042983313899356e-05, "epoch": 6.072083879423329, "percentage": 60.72, "elapsed_time": "0:39:10", "remaining_time": "0:25:20", "throughput": 2641.96, "total_tokens": 6208792} {"current_steps": 23170, "total_steps": 38150, "loss": 0.2826, "lr": 2.0031773634907962e-05, "epoch": 6.073394495412844, "percentage": 60.73, "elapsed_time": "0:39:10", "remaining_time": "0:25:19", "throughput": 2642.1, "total_tokens": 6210456} {"current_steps": 23175, "total_steps": 38150, "loss": 0.1481, "lr": 2.0020564995757765e-05, "epoch": 6.074705111402359, "percentage": 60.75, "elapsed_time": "0:39:11", "remaining_time": "0:25:19", "throughput": 2642.07, "total_tokens": 6211512} {"current_steps": 23180, "total_steps": 38150, "loss": 0.2387, "lr": 2.0009357398794707e-05, "epoch": 6.076015727391874, "percentage": 60.76, "elapsed_time": "0:39:11", "remaining_time": "0:25:18", "throughput": 2642.19, "total_tokens": 6213032} {"current_steps": 23185, "total_steps": 38150, "loss": 0.1905, "lr": 1.999815084636452e-05, "epoch": 6.077326343381389, "percentage": 60.77, "elapsed_time": "0:39:11", "remaining_time": "0:25:18", "throughput": 2642.18, "total_tokens": 6214152} {"current_steps": 23190, "total_steps": 38150, "loss": 0.2294, "lr": 1.9986945340812722e-05, "epoch": 6.078636959370904, "percentage": 60.79, "elapsed_time": "0:39:12", "remaining_time": "0:25:17", "throughput": 2642.28, "total_tokens": 6215656} {"current_steps": 23195, "total_steps": 38150, "loss": 0.3766, "lr": 1.9975740884484606e-05, "epoch": 6.0799475753604195, "percentage": 60.8, "elapsed_time": "0:39:12", "remaining_time": "0:25:16", "throughput": 2642.31, "total_tokens": 6216840} {"current_steps": 23200, "total_steps": 38150, "loss": 0.2079, "lr": 1.9964537479725234e-05, "epoch": 6.081258191349934, "percentage": 60.81, "elapsed_time": "0:39:13", "remaining_time": "0:25:16", "throughput": 2642.34, "total_tokens": 6218024} {"current_steps": 23205, "total_steps": 38150, "loss": 0.2251, "lr": 1.9953335128879468e-05, "epoch": 6.08256880733945, "percentage": 60.83, "elapsed_time": "0:39:13", "remaining_time": "0:25:15", "throughput": 2642.38, "total_tokens": 6219256} {"current_steps": 23210, "total_steps": 38150, "loss": 0.2764, "lr": 1.9942133834291936e-05, "epoch": 6.083879423328964, "percentage": 60.84, "elapsed_time": "0:39:14", "remaining_time": "0:25:15", "throughput": 2642.52, "total_tokens": 6220872} {"current_steps": 23215, "total_steps": 38150, "loss": 0.2013, "lr": 1.9930933598307058e-05, "epoch": 6.08519003931848, "percentage": 60.85, "elapsed_time": "0:39:14", "remaining_time": "0:25:14", "throughput": 2642.59, "total_tokens": 6222216} {"current_steps": 23220, "total_steps": 38150, "loss": 0.1792, "lr": 1.991973442326902e-05, "epoch": 6.086500655307995, "percentage": 60.87, "elapsed_time": "0:39:15", "remaining_time": "0:25:14", "throughput": 2642.59, "total_tokens": 6223368} {"current_steps": 23225, "total_steps": 38150, "loss": 0.2297, "lr": 1.990853631152179e-05, "epoch": 6.08781127129751, "percentage": 60.88, "elapsed_time": "0:39:15", "remaining_time": "0:25:13", "throughput": 2642.65, "total_tokens": 6224696} {"current_steps": 23230, "total_steps": 38150, "loss": 0.226, "lr": 1.989733926540911e-05, "epoch": 6.089121887287025, "percentage": 60.89, "elapsed_time": "0:39:15", "remaining_time": "0:25:13", "throughput": 2642.63, "total_tokens": 6225768} {"current_steps": 23235, "total_steps": 38150, "loss": 0.1735, "lr": 1.988614328727451e-05, "epoch": 6.09043250327654, "percentage": 60.9, "elapsed_time": "0:39:16", "remaining_time": "0:25:12", "throughput": 2642.6, "total_tokens": 6226808} {"current_steps": 23240, "total_steps": 38150, "loss": 0.3401, "lr": 1.9874948379461277e-05, "epoch": 6.091743119266055, "percentage": 60.92, "elapsed_time": "0:39:16", "remaining_time": "0:25:12", "throughput": 2642.69, "total_tokens": 6228248} {"current_steps": 23245, "total_steps": 38150, "loss": 0.1551, "lr": 1.9863754544312495e-05, "epoch": 6.0930537352555705, "percentage": 60.93, "elapsed_time": "0:39:17", "remaining_time": "0:25:11", "throughput": 2642.9, "total_tokens": 6230104} {"current_steps": 23250, "total_steps": 38150, "loss": 0.1837, "lr": 1.9852561784171014e-05, "epoch": 6.094364351245085, "percentage": 60.94, "elapsed_time": "0:39:17", "remaining_time": "0:25:10", "throughput": 2642.95, "total_tokens": 6231448} {"current_steps": 23255, "total_steps": 38150, "loss": 0.2984, "lr": 1.9841370101379463e-05, "epoch": 6.095674967234601, "percentage": 60.96, "elapsed_time": "0:39:18", "remaining_time": "0:25:10", "throughput": 2642.98, "total_tokens": 6232664} {"current_steps": 23260, "total_steps": 38150, "loss": 0.272, "lr": 1.983017949828023e-05, "epoch": 6.096985583224115, "percentage": 60.97, "elapsed_time": "0:39:18", "remaining_time": "0:25:09", "throughput": 2643.1, "total_tokens": 6234280} {"current_steps": 23265, "total_steps": 38150, "loss": 0.4531, "lr": 1.981898997721548e-05, "epoch": 6.09829619921363, "percentage": 60.98, "elapsed_time": "0:39:19", "remaining_time": "0:25:09", "throughput": 2643.14, "total_tokens": 6235528} {"current_steps": 23270, "total_steps": 38150, "loss": 0.1953, "lr": 1.98078015405272e-05, "epoch": 6.0996068152031455, "percentage": 61.0, "elapsed_time": "0:39:19", "remaining_time": "0:25:08", "throughput": 2643.11, "total_tokens": 6236536} {"current_steps": 23275, "total_steps": 38150, "loss": 0.2953, "lr": 1.9796614190557074e-05, "epoch": 6.10091743119266, "percentage": 61.01, "elapsed_time": "0:39:19", "remaining_time": "0:25:08", "throughput": 2643.26, "total_tokens": 6238088} {"current_steps": 23280, "total_steps": 38150, "loss": 0.242, "lr": 1.978542792964661e-05, "epoch": 6.102228047182176, "percentage": 61.02, "elapsed_time": "0:39:20", "remaining_time": "0:25:07", "throughput": 2643.29, "total_tokens": 6239336} {"current_steps": 23285, "total_steps": 38150, "loss": 0.278, "lr": 1.977424276013707e-05, "epoch": 6.10353866317169, "percentage": 61.04, "elapsed_time": "0:39:20", "remaining_time": "0:25:07", "throughput": 2643.34, "total_tokens": 6240680} {"current_steps": 23290, "total_steps": 38150, "loss": 0.2068, "lr": 1.9763058684369495e-05, "epoch": 6.104849279161206, "percentage": 61.05, "elapsed_time": "0:39:21", "remaining_time": "0:25:06", "throughput": 2643.47, "total_tokens": 6242296} {"current_steps": 23295, "total_steps": 38150, "loss": 0.1236, "lr": 1.9751875704684684e-05, "epoch": 6.1061598951507206, "percentage": 61.06, "elapsed_time": "0:39:21", "remaining_time": "0:25:06", "throughput": 2643.61, "total_tokens": 6243880} {"current_steps": 23300, "total_steps": 38150, "loss": 0.3905, "lr": 1.974069382342322e-05, "epoch": 6.107470511140236, "percentage": 61.07, "elapsed_time": "0:39:22", "remaining_time": "0:25:05", "throughput": 2643.63, "total_tokens": 6245160} {"current_steps": 23305, "total_steps": 38150, "loss": 0.2123, "lr": 1.9729513042925455e-05, "epoch": 6.108781127129751, "percentage": 61.09, "elapsed_time": "0:39:22", "remaining_time": "0:25:05", "throughput": 2643.63, "total_tokens": 6246280} {"current_steps": 23310, "total_steps": 38150, "loss": 0.1199, "lr": 1.97183333655315e-05, "epoch": 6.110091743119266, "percentage": 61.1, "elapsed_time": "0:39:23", "remaining_time": "0:25:04", "throughput": 2643.63, "total_tokens": 6247416} {"current_steps": 23315, "total_steps": 38150, "loss": 0.406, "lr": 1.970715479358125e-05, "epoch": 6.111402359108781, "percentage": 61.11, "elapsed_time": "0:39:23", "remaining_time": "0:25:03", "throughput": 2643.59, "total_tokens": 6248440} {"current_steps": 23320, "total_steps": 38150, "loss": 0.154, "lr": 1.9695977329414352e-05, "epoch": 6.1127129750982965, "percentage": 61.13, "elapsed_time": "0:39:24", "remaining_time": "0:25:03", "throughput": 2643.64, "total_tokens": 6249800} {"current_steps": 23325, "total_steps": 38150, "loss": 0.1485, "lr": 1.9684800975370224e-05, "epoch": 6.114023591087811, "percentage": 61.14, "elapsed_time": "0:39:24", "remaining_time": "0:25:02", "throughput": 2643.61, "total_tokens": 6250856} {"current_steps": 23330, "total_steps": 38150, "loss": 0.2499, "lr": 1.9673625733788084e-05, "epoch": 6.115334207077327, "percentage": 61.15, "elapsed_time": "0:39:24", "remaining_time": "0:25:02", "throughput": 2643.72, "total_tokens": 6252376} {"current_steps": 23335, "total_steps": 38150, "loss": 0.1415, "lr": 1.966245160700687e-05, "epoch": 6.116644823066841, "percentage": 61.17, "elapsed_time": "0:39:25", "remaining_time": "0:25:01", "throughput": 2643.76, "total_tokens": 6253592} {"current_steps": 23340, "total_steps": 38150, "loss": 0.1449, "lr": 1.965127859736531e-05, "epoch": 6.117955439056357, "percentage": 61.18, "elapsed_time": "0:39:25", "remaining_time": "0:25:01", "throughput": 2643.9, "total_tokens": 6255208} {"current_steps": 23345, "total_steps": 38150, "loss": 0.2409, "lr": 1.96401067072019e-05, "epoch": 6.1192660550458715, "percentage": 61.19, "elapsed_time": "0:39:26", "remaining_time": "0:25:00", "throughput": 2643.86, "total_tokens": 6256216} {"current_steps": 23350, "total_steps": 38150, "loss": 0.1805, "lr": 1.9628935938854897e-05, "epoch": 6.120576671035387, "percentage": 61.21, "elapsed_time": "0:39:26", "remaining_time": "0:25:00", "throughput": 2643.96, "total_tokens": 6257752} {"current_steps": 23355, "total_steps": 38150, "loss": 0.2447, "lr": 1.961776629466232e-05, "epoch": 6.121887287024902, "percentage": 61.22, "elapsed_time": "0:39:27", "remaining_time": "0:24:59", "throughput": 2643.94, "total_tokens": 6258904} {"current_steps": 23360, "total_steps": 38150, "loss": 0.263, "lr": 1.9606597776961955e-05, "epoch": 6.123197903014416, "percentage": 61.23, "elapsed_time": "0:39:27", "remaining_time": "0:24:59", "throughput": 2643.97, "total_tokens": 6260120} {"current_steps": 23365, "total_steps": 38150, "loss": 0.1526, "lr": 1.9595430388091358e-05, "epoch": 6.124508519003932, "percentage": 61.25, "elapsed_time": "0:39:28", "remaining_time": "0:24:58", "throughput": 2644.02, "total_tokens": 6261448} {"current_steps": 23370, "total_steps": 38150, "loss": 0.2601, "lr": 1.958426413038784e-05, "epoch": 6.1258191349934465, "percentage": 61.26, "elapsed_time": "0:39:28", "remaining_time": "0:24:57", "throughput": 2644.08, "total_tokens": 6262728} {"current_steps": 23375, "total_steps": 38150, "loss": 0.2582, "lr": 1.957309900618849e-05, "epoch": 6.127129750982962, "percentage": 61.27, "elapsed_time": "0:39:29", "remaining_time": "0:24:57", "throughput": 2644.18, "total_tokens": 6264216} {"current_steps": 23380, "total_steps": 38150, "loss": 0.2313, "lr": 1.956193501783012e-05, "epoch": 6.128440366972477, "percentage": 61.28, "elapsed_time": "0:39:29", "remaining_time": "0:24:56", "throughput": 2644.24, "total_tokens": 6265464} {"current_steps": 23385, "total_steps": 38150, "loss": 0.128, "lr": 1.9550772167649378e-05, "epoch": 6.129750982961992, "percentage": 61.3, "elapsed_time": "0:39:29", "remaining_time": "0:24:56", "throughput": 2644.27, "total_tokens": 6266680} {"current_steps": 23390, "total_steps": 38150, "loss": 0.4278, "lr": 1.9539610457982596e-05, "epoch": 6.131061598951507, "percentage": 61.31, "elapsed_time": "0:39:30", "remaining_time": "0:24:55", "throughput": 2644.2, "total_tokens": 6267640} {"current_steps": 23395, "total_steps": 38150, "loss": 0.2789, "lr": 1.9528449891165913e-05, "epoch": 6.1323722149410225, "percentage": 61.32, "elapsed_time": "0:39:30", "remaining_time": "0:24:55", "throughput": 2644.29, "total_tokens": 6269080} {"current_steps": 23400, "total_steps": 38150, "loss": 0.2138, "lr": 1.951729046953521e-05, "epoch": 6.133682830930537, "percentage": 61.34, "elapsed_time": "0:39:31", "remaining_time": "0:24:54", "throughput": 2644.34, "total_tokens": 6270360} {"current_steps": 23405, "total_steps": 38150, "loss": 0.2762, "lr": 1.9506132195426138e-05, "epoch": 6.134993446920053, "percentage": 61.35, "elapsed_time": "0:39:31", "remaining_time": "0:24:54", "throughput": 2644.42, "total_tokens": 6271720} {"current_steps": 23410, "total_steps": 38150, "loss": 0.2735, "lr": 1.9494975071174112e-05, "epoch": 6.136304062909567, "percentage": 61.36, "elapsed_time": "0:39:32", "remaining_time": "0:24:53", "throughput": 2644.57, "total_tokens": 6273352} {"current_steps": 23415, "total_steps": 38150, "loss": 0.2626, "lr": 1.9483819099114286e-05, "epoch": 6.137614678899083, "percentage": 61.38, "elapsed_time": "0:39:32", "remaining_time": "0:24:53", "throughput": 2644.66, "total_tokens": 6274808} {"current_steps": 23420, "total_steps": 38150, "loss": 0.2521, "lr": 1.9472664281581594e-05, "epoch": 6.1389252948885975, "percentage": 61.39, "elapsed_time": "0:39:33", "remaining_time": "0:24:52", "throughput": 2644.58, "total_tokens": 6275704} {"current_steps": 23425, "total_steps": 38150, "loss": 0.2331, "lr": 1.9461510620910713e-05, "epoch": 6.140235910878113, "percentage": 61.4, "elapsed_time": "0:39:33", "remaining_time": "0:24:52", "throughput": 2644.75, "total_tokens": 6277400} {"current_steps": 23430, "total_steps": 38150, "loss": 0.2608, "lr": 1.94503581194361e-05, "epoch": 6.141546526867628, "percentage": 61.42, "elapsed_time": "0:39:33", "remaining_time": "0:24:51", "throughput": 2644.82, "total_tokens": 6278696} {"current_steps": 23435, "total_steps": 38150, "loss": 0.2084, "lr": 1.9439206779491934e-05, "epoch": 6.142857142857143, "percentage": 61.43, "elapsed_time": "0:39:34", "remaining_time": "0:24:50", "throughput": 2644.9, "total_tokens": 6280024} {"current_steps": 23440, "total_steps": 38150, "loss": 0.339, "lr": 1.942805660341217e-05, "epoch": 6.144167758846658, "percentage": 61.44, "elapsed_time": "0:39:34", "remaining_time": "0:24:50", "throughput": 2644.87, "total_tokens": 6281048} {"current_steps": 23445, "total_steps": 38150, "loss": 0.1825, "lr": 1.9416907593530548e-05, "epoch": 6.145478374836173, "percentage": 61.45, "elapsed_time": "0:39:35", "remaining_time": "0:24:49", "throughput": 2644.93, "total_tokens": 6282360} {"current_steps": 23450, "total_steps": 38150, "loss": 0.1212, "lr": 1.9405759752180515e-05, "epoch": 6.146788990825688, "percentage": 61.47, "elapsed_time": "0:39:35", "remaining_time": "0:24:49", "throughput": 2644.77, "total_tokens": 6283080} {"current_steps": 23455, "total_steps": 38150, "loss": 0.168, "lr": 1.9394613081695302e-05, "epoch": 6.148099606815203, "percentage": 61.48, "elapsed_time": "0:39:36", "remaining_time": "0:24:48", "throughput": 2644.94, "total_tokens": 6284824} {"current_steps": 23460, "total_steps": 38150, "loss": 0.2038, "lr": 1.9383467584407883e-05, "epoch": 6.149410222804718, "percentage": 61.49, "elapsed_time": "0:39:36", "remaining_time": "0:24:48", "throughput": 2644.92, "total_tokens": 6285896} {"current_steps": 23465, "total_steps": 38150, "loss": 0.3275, "lr": 1.9372323262650992e-05, "epoch": 6.150720838794233, "percentage": 61.51, "elapsed_time": "0:39:37", "remaining_time": "0:24:47", "throughput": 2644.93, "total_tokens": 6287080} {"current_steps": 23470, "total_steps": 38150, "loss": 0.2459, "lr": 1.936118011875713e-05, "epoch": 6.1520314547837485, "percentage": 61.52, "elapsed_time": "0:39:37", "remaining_time": "0:24:47", "throughput": 2644.89, "total_tokens": 6288088} {"current_steps": 23475, "total_steps": 38150, "loss": 0.2402, "lr": 1.9350038155058515e-05, "epoch": 6.153342070773263, "percentage": 61.53, "elapsed_time": "0:39:37", "remaining_time": "0:24:46", "throughput": 2644.88, "total_tokens": 6289176} {"current_steps": 23480, "total_steps": 38150, "loss": 0.2596, "lr": 1.9338897373887154e-05, "epoch": 6.154652686762779, "percentage": 61.55, "elapsed_time": "0:39:38", "remaining_time": "0:24:45", "throughput": 2644.89, "total_tokens": 6290376} {"current_steps": 23485, "total_steps": 38150, "loss": 0.3145, "lr": 1.932775777757479e-05, "epoch": 6.155963302752293, "percentage": 61.56, "elapsed_time": "0:39:38", "remaining_time": "0:24:45", "throughput": 2644.95, "total_tokens": 6291688} {"current_steps": 23490, "total_steps": 38150, "loss": 0.1655, "lr": 1.9316619368452928e-05, "epoch": 6.157273918741809, "percentage": 61.57, "elapsed_time": "0:39:39", "remaining_time": "0:24:44", "throughput": 2644.94, "total_tokens": 6292792} {"current_steps": 23495, "total_steps": 38150, "loss": 0.2341, "lr": 1.9305482148852794e-05, "epoch": 6.1585845347313235, "percentage": 61.59, "elapsed_time": "0:39:39", "remaining_time": "0:24:44", "throughput": 2645.04, "total_tokens": 6294184} {"current_steps": 23500, "total_steps": 38150, "loss": 0.1901, "lr": 1.929434612110542e-05, "epoch": 6.159895150720839, "percentage": 61.6, "elapsed_time": "0:39:40", "remaining_time": "0:24:43", "throughput": 2645.04, "total_tokens": 6295384} {"current_steps": 23505, "total_steps": 38150, "loss": 0.2422, "lr": 1.9283211287541548e-05, "epoch": 6.161205766710354, "percentage": 61.61, "elapsed_time": "0:39:40", "remaining_time": "0:24:43", "throughput": 2645.07, "total_tokens": 6296568} {"current_steps": 23510, "total_steps": 38150, "loss": 0.2354, "lr": 1.9272077650491673e-05, "epoch": 6.162516382699869, "percentage": 61.63, "elapsed_time": "0:39:40", "remaining_time": "0:24:42", "throughput": 2645.11, "total_tokens": 6297880} {"current_steps": 23515, "total_steps": 38150, "loss": 0.3579, "lr": 1.9260945212286047e-05, "epoch": 6.163826998689384, "percentage": 61.64, "elapsed_time": "0:39:41", "remaining_time": "0:24:42", "throughput": 2645.05, "total_tokens": 6298824} {"current_steps": 23520, "total_steps": 38150, "loss": 0.156, "lr": 1.9249813975254673e-05, "epoch": 6.165137614678899, "percentage": 61.65, "elapsed_time": "0:39:41", "remaining_time": "0:24:41", "throughput": 2645.05, "total_tokens": 6299960} {"current_steps": 23525, "total_steps": 38150, "loss": 0.2367, "lr": 1.92386839417273e-05, "epoch": 6.166448230668414, "percentage": 61.66, "elapsed_time": "0:39:42", "remaining_time": "0:24:40", "throughput": 2645.1, "total_tokens": 6301272} {"current_steps": 23530, "total_steps": 38150, "loss": 0.3056, "lr": 1.9227555114033422e-05, "epoch": 6.16775884665793, "percentage": 61.68, "elapsed_time": "0:39:42", "remaining_time": "0:24:40", "throughput": 2645.1, "total_tokens": 6302504} {"current_steps": 23535, "total_steps": 38150, "loss": 0.2398, "lr": 1.921642749450228e-05, "epoch": 6.169069462647444, "percentage": 61.69, "elapsed_time": "0:39:43", "remaining_time": "0:24:39", "throughput": 2645.17, "total_tokens": 6303832} {"current_steps": 23540, "total_steps": 38150, "loss": 0.2267, "lr": 1.9205301085462877e-05, "epoch": 6.17038007863696, "percentage": 61.7, "elapsed_time": "0:39:43", "remaining_time": "0:24:39", "throughput": 2645.29, "total_tokens": 6305336} {"current_steps": 23545, "total_steps": 38150, "loss": 0.3185, "lr": 1.919417588924394e-05, "epoch": 6.1716906946264745, "percentage": 61.72, "elapsed_time": "0:39:44", "remaining_time": "0:24:38", "throughput": 2645.32, "total_tokens": 6306568} {"current_steps": 23550, "total_steps": 38150, "loss": 0.2472, "lr": 1.9183051908173963e-05, "epoch": 6.173001310615989, "percentage": 61.73, "elapsed_time": "0:39:44", "remaining_time": "0:24:38", "throughput": 2645.39, "total_tokens": 6307880} {"current_steps": 23555, "total_steps": 38150, "loss": 0.2072, "lr": 1.9171929144581156e-05, "epoch": 6.174311926605505, "percentage": 61.74, "elapsed_time": "0:39:44", "remaining_time": "0:24:37", "throughput": 2645.51, "total_tokens": 6309448} {"current_steps": 23560, "total_steps": 38150, "loss": 0.2293, "lr": 1.9160807600793517e-05, "epoch": 6.175622542595019, "percentage": 61.76, "elapsed_time": "0:39:45", "remaining_time": "0:24:37", "throughput": 2645.56, "total_tokens": 6310888} {"current_steps": 23565, "total_steps": 38150, "loss": 0.377, "lr": 1.9149687279138768e-05, "epoch": 6.176933158584535, "percentage": 61.77, "elapsed_time": "0:39:45", "remaining_time": "0:24:36", "throughput": 2645.65, "total_tokens": 6312344} {"current_steps": 23570, "total_steps": 38150, "loss": 0.3616, "lr": 1.9138568181944357e-05, "epoch": 6.1782437745740495, "percentage": 61.78, "elapsed_time": "0:39:46", "remaining_time": "0:24:36", "throughput": 2645.73, "total_tokens": 6313704} {"current_steps": 23575, "total_steps": 38150, "loss": 0.2368, "lr": 1.9127450311537494e-05, "epoch": 6.179554390563565, "percentage": 61.8, "elapsed_time": "0:39:46", "remaining_time": "0:24:35", "throughput": 2645.79, "total_tokens": 6315016} {"current_steps": 23580, "total_steps": 38150, "loss": 0.1969, "lr": 1.9116333670245135e-05, "epoch": 6.18086500655308, "percentage": 61.81, "elapsed_time": "0:39:47", "remaining_time": "0:24:35", "throughput": 2645.75, "total_tokens": 6315992} {"current_steps": 23585, "total_steps": 38150, "loss": 0.2694, "lr": 1.9105218260393975e-05, "epoch": 6.182175622542595, "percentage": 61.82, "elapsed_time": "0:39:47", "remaining_time": "0:24:34", "throughput": 2645.79, "total_tokens": 6317320} {"current_steps": 23590, "total_steps": 38150, "loss": 0.4943, "lr": 1.9094104084310446e-05, "epoch": 6.18348623853211, "percentage": 61.83, "elapsed_time": "0:39:48", "remaining_time": "0:24:33", "throughput": 2645.78, "total_tokens": 6318424} {"current_steps": 23595, "total_steps": 38150, "loss": 0.2474, "lr": 1.908299114432073e-05, "epoch": 6.184796854521625, "percentage": 61.85, "elapsed_time": "0:39:48", "remaining_time": "0:24:33", "throughput": 2645.84, "total_tokens": 6319736} {"current_steps": 23600, "total_steps": 38150, "loss": 0.1775, "lr": 1.907187944275074e-05, "epoch": 6.18610747051114, "percentage": 61.86, "elapsed_time": "0:39:48", "remaining_time": "0:24:32", "throughput": 2645.85, "total_tokens": 6320904} {"current_steps": 23605, "total_steps": 38150, "loss": 0.3734, "lr": 1.9060768981926137e-05, "epoch": 6.187418086500656, "percentage": 61.87, "elapsed_time": "0:39:49", "remaining_time": "0:24:32", "throughput": 2645.81, "total_tokens": 6321896} {"current_steps": 23610, "total_steps": 38150, "loss": 0.184, "lr": 1.904965976417232e-05, "epoch": 6.18872870249017, "percentage": 61.89, "elapsed_time": "0:39:49", "remaining_time": "0:24:31", "throughput": 2645.86, "total_tokens": 6323176} {"current_steps": 23615, "total_steps": 38150, "loss": 0.2088, "lr": 1.9038551791814446e-05, "epoch": 6.190039318479686, "percentage": 61.9, "elapsed_time": "0:39:50", "remaining_time": "0:24:31", "throughput": 2645.97, "total_tokens": 6324776} {"current_steps": 23620, "total_steps": 38150, "loss": 0.2582, "lr": 1.902744506717738e-05, "epoch": 6.1913499344692005, "percentage": 61.91, "elapsed_time": "0:39:50", "remaining_time": "0:24:30", "throughput": 2646.04, "total_tokens": 6326152} {"current_steps": 23625, "total_steps": 38150, "loss": 0.1507, "lr": 1.9016339592585737e-05, "epoch": 6.192660550458716, "percentage": 61.93, "elapsed_time": "0:39:51", "remaining_time": "0:24:30", "throughput": 2645.98, "total_tokens": 6327112} {"current_steps": 23630, "total_steps": 38150, "loss": 0.3352, "lr": 1.9005235370363877e-05, "epoch": 6.193971166448231, "percentage": 61.94, "elapsed_time": "0:39:51", "remaining_time": "0:24:29", "throughput": 2646.06, "total_tokens": 6328616} {"current_steps": 23635, "total_steps": 38150, "loss": 0.2145, "lr": 1.89941324028359e-05, "epoch": 6.195281782437746, "percentage": 61.95, "elapsed_time": "0:39:52", "remaining_time": "0:24:29", "throughput": 2646.07, "total_tokens": 6329736} {"current_steps": 23640, "total_steps": 38150, "loss": 0.217, "lr": 1.8983030692325632e-05, "epoch": 6.196592398427261, "percentage": 61.97, "elapsed_time": "0:39:52", "remaining_time": "0:24:28", "throughput": 2646.11, "total_tokens": 6330984} {"current_steps": 23645, "total_steps": 38150, "loss": 0.2225, "lr": 1.8971930241156646e-05, "epoch": 6.1979030144167755, "percentage": 61.98, "elapsed_time": "0:39:52", "remaining_time": "0:24:27", "throughput": 2646.14, "total_tokens": 6332168} {"current_steps": 23650, "total_steps": 38150, "loss": 0.1661, "lr": 1.8960831051652243e-05, "epoch": 6.199213630406291, "percentage": 61.99, "elapsed_time": "0:39:53", "remaining_time": "0:24:27", "throughput": 2646.14, "total_tokens": 6333320} {"current_steps": 23655, "total_steps": 38150, "loss": 0.2249, "lr": 1.8949733126135464e-05, "epoch": 6.200524246395806, "percentage": 62.01, "elapsed_time": "0:39:53", "remaining_time": "0:24:26", "throughput": 2646.22, "total_tokens": 6334712} {"current_steps": 23660, "total_steps": 38150, "loss": 0.2928, "lr": 1.8938636466929088e-05, "epoch": 6.201834862385321, "percentage": 62.02, "elapsed_time": "0:39:54", "remaining_time": "0:24:26", "throughput": 2646.19, "total_tokens": 6335752} {"current_steps": 23665, "total_steps": 38150, "loss": 0.1857, "lr": 1.8927541076355626e-05, "epoch": 6.203145478374836, "percentage": 62.03, "elapsed_time": "0:39:54", "remaining_time": "0:24:25", "throughput": 2646.18, "total_tokens": 6336872} {"current_steps": 23670, "total_steps": 38150, "loss": 0.4782, "lr": 1.8916446956737317e-05, "epoch": 6.204456094364351, "percentage": 62.04, "elapsed_time": "0:39:55", "remaining_time": "0:24:25", "throughput": 2646.25, "total_tokens": 6338296} {"current_steps": 23675, "total_steps": 38150, "loss": 0.2599, "lr": 1.890535411039616e-05, "epoch": 6.205766710353866, "percentage": 62.06, "elapsed_time": "0:39:55", "remaining_time": "0:24:24", "throughput": 2646.29, "total_tokens": 6339560} {"current_steps": 23680, "total_steps": 38150, "loss": 0.1993, "lr": 1.8894262539653858e-05, "epoch": 6.207077326343382, "percentage": 62.07, "elapsed_time": "0:39:56", "remaining_time": "0:24:24", "throughput": 2646.29, "total_tokens": 6340744} {"current_steps": 23685, "total_steps": 38150, "loss": 0.2072, "lr": 1.888317224683185e-05, "epoch": 6.208387942332896, "percentage": 62.08, "elapsed_time": "0:39:56", "remaining_time": "0:24:23", "throughput": 2646.35, "total_tokens": 6342040} {"current_steps": 23690, "total_steps": 38150, "loss": 0.2162, "lr": 1.8872083234251324e-05, "epoch": 6.209698558322412, "percentage": 62.1, "elapsed_time": "0:39:56", "remaining_time": "0:24:23", "throughput": 2646.3, "total_tokens": 6343000} {"current_steps": 23695, "total_steps": 38150, "loss": 0.2386, "lr": 1.8860995504233188e-05, "epoch": 6.2110091743119265, "percentage": 62.11, "elapsed_time": "0:39:57", "remaining_time": "0:24:22", "throughput": 2646.25, "total_tokens": 6343992} {"current_steps": 23700, "total_steps": 38150, "loss": 0.4022, "lr": 1.8849909059098087e-05, "epoch": 6.212319790301442, "percentage": 62.12, "elapsed_time": "0:39:57", "remaining_time": "0:24:21", "throughput": 2646.39, "total_tokens": 6345640} {"current_steps": 23705, "total_steps": 38150, "loss": 0.2033, "lr": 1.8838823901166396e-05, "epoch": 6.213630406290957, "percentage": 62.14, "elapsed_time": "0:39:58", "remaining_time": "0:24:21", "throughput": 2646.52, "total_tokens": 6347128} {"current_steps": 23710, "total_steps": 38150, "loss": 0.2805, "lr": 1.8827740032758215e-05, "epoch": 6.214941022280472, "percentage": 62.15, "elapsed_time": "0:39:58", "remaining_time": "0:24:20", "throughput": 2646.69, "total_tokens": 6348872} {"current_steps": 23715, "total_steps": 38150, "loss": 0.2333, "lr": 1.8816657456193376e-05, "epoch": 6.216251638269987, "percentage": 62.16, "elapsed_time": "0:39:59", "remaining_time": "0:24:20", "throughput": 2646.83, "total_tokens": 6350536} {"current_steps": 23720, "total_steps": 38150, "loss": 0.1608, "lr": 1.880557617379145e-05, "epoch": 6.217562254259502, "percentage": 62.18, "elapsed_time": "0:39:59", "remaining_time": "0:24:19", "throughput": 2646.97, "total_tokens": 6352200} {"current_steps": 23725, "total_steps": 38150, "loss": 0.3079, "lr": 1.8794496187871725e-05, "epoch": 6.218872870249017, "percentage": 62.19, "elapsed_time": "0:40:00", "remaining_time": "0:24:19", "throughput": 2647.01, "total_tokens": 6353528} {"current_steps": 23730, "total_steps": 38150, "loss": 0.2708, "lr": 1.8783417500753224e-05, "epoch": 6.220183486238533, "percentage": 62.2, "elapsed_time": "0:40:00", "remaining_time": "0:24:18", "throughput": 2647.11, "total_tokens": 6355016} {"current_steps": 23735, "total_steps": 38150, "loss": 0.1723, "lr": 1.8772340114754705e-05, "epoch": 6.221494102228047, "percentage": 62.21, "elapsed_time": "0:40:01", "remaining_time": "0:24:18", "throughput": 2647.22, "total_tokens": 6356536} {"current_steps": 23740, "total_steps": 38150, "loss": 0.2158, "lr": 1.8761264032194642e-05, "epoch": 6.222804718217562, "percentage": 62.23, "elapsed_time": "0:40:01", "remaining_time": "0:24:17", "throughput": 2647.37, "total_tokens": 6358200} {"current_steps": 23745, "total_steps": 38150, "loss": 0.137, "lr": 1.875018925539123e-05, "epoch": 6.224115334207077, "percentage": 62.24, "elapsed_time": "0:40:02", "remaining_time": "0:24:17", "throughput": 2647.34, "total_tokens": 6359240} {"current_steps": 23750, "total_steps": 38150, "loss": 0.2209, "lr": 1.8739115786662415e-05, "epoch": 6.225425950196592, "percentage": 62.25, "elapsed_time": "0:40:02", "remaining_time": "0:24:16", "throughput": 2647.51, "total_tokens": 6361096} {"current_steps": 23755, "total_steps": 38150, "loss": 0.1755, "lr": 1.872804362832584e-05, "epoch": 6.226736566186108, "percentage": 62.27, "elapsed_time": "0:40:03", "remaining_time": "0:24:16", "throughput": 2647.49, "total_tokens": 6362200} {"current_steps": 23760, "total_steps": 38150, "loss": 0.1273, "lr": 1.8716972782698905e-05, "epoch": 6.228047182175622, "percentage": 62.28, "elapsed_time": "0:40:03", "remaining_time": "0:24:15", "throughput": 2647.53, "total_tokens": 6363448} {"current_steps": 23765, "total_steps": 38150, "loss": 0.1686, "lr": 1.8705903252098704e-05, "epoch": 6.229357798165138, "percentage": 62.29, "elapsed_time": "0:40:03", "remaining_time": "0:24:15", "throughput": 2647.45, "total_tokens": 6364376} {"current_steps": 23770, "total_steps": 38150, "loss": 0.2758, "lr": 1.869483503884208e-05, "epoch": 6.2306684141546524, "percentage": 62.31, "elapsed_time": "0:40:04", "remaining_time": "0:24:14", "throughput": 2647.5, "total_tokens": 6365688} {"current_steps": 23775, "total_steps": 38150, "loss": 0.1727, "lr": 1.8683768145245586e-05, "epoch": 6.231979030144168, "percentage": 62.32, "elapsed_time": "0:40:04", "remaining_time": "0:24:14", "throughput": 2647.49, "total_tokens": 6366808} {"current_steps": 23780, "total_steps": 38150, "loss": 0.3485, "lr": 1.8672702573625505e-05, "epoch": 6.233289646133683, "percentage": 62.33, "elapsed_time": "0:40:05", "remaining_time": "0:24:13", "throughput": 2647.59, "total_tokens": 6368296} {"current_steps": 23785, "total_steps": 38150, "loss": 0.2934, "lr": 1.866163832629784e-05, "epoch": 6.234600262123198, "percentage": 62.35, "elapsed_time": "0:40:05", "remaining_time": "0:24:12", "throughput": 2647.52, "total_tokens": 6369224} {"current_steps": 23790, "total_steps": 38150, "loss": 0.2129, "lr": 1.8650575405578324e-05, "epoch": 6.235910878112713, "percentage": 62.36, "elapsed_time": "0:40:06", "remaining_time": "0:24:12", "throughput": 2647.48, "total_tokens": 6370232} {"current_steps": 23795, "total_steps": 38150, "loss": 0.236, "lr": 1.8639513813782407e-05, "epoch": 6.237221494102228, "percentage": 62.37, "elapsed_time": "0:40:06", "remaining_time": "0:24:11", "throughput": 2647.47, "total_tokens": 6371336} {"current_steps": 23800, "total_steps": 38150, "loss": 0.2761, "lr": 1.8628453553225262e-05, "epoch": 6.238532110091743, "percentage": 62.39, "elapsed_time": "0:40:07", "remaining_time": "0:24:11", "throughput": 2647.57, "total_tokens": 6372824} {"current_steps": 23805, "total_steps": 38150, "loss": 0.234, "lr": 1.8617394626221774e-05, "epoch": 6.239842726081259, "percentage": 62.4, "elapsed_time": "0:40:07", "remaining_time": "0:24:10", "throughput": 2647.63, "total_tokens": 6374168} {"current_steps": 23810, "total_steps": 38150, "loss": 0.2396, "lr": 1.8606337035086564e-05, "epoch": 6.241153342070773, "percentage": 62.41, "elapsed_time": "0:40:07", "remaining_time": "0:24:10", "throughput": 2647.73, "total_tokens": 6375576} {"current_steps": 23815, "total_steps": 38150, "loss": 0.3501, "lr": 1.859528078213396e-05, "epoch": 6.242463958060289, "percentage": 62.42, "elapsed_time": "0:40:08", "remaining_time": "0:24:09", "throughput": 2647.68, "total_tokens": 6376584} {"current_steps": 23820, "total_steps": 38150, "loss": 0.238, "lr": 1.8584225869678033e-05, "epoch": 6.243774574049803, "percentage": 62.44, "elapsed_time": "0:40:08", "remaining_time": "0:24:09", "throughput": 2647.68, "total_tokens": 6377752} {"current_steps": 23825, "total_steps": 38150, "loss": 0.2709, "lr": 1.8573172300032538e-05, "epoch": 6.245085190039318, "percentage": 62.45, "elapsed_time": "0:40:09", "remaining_time": "0:24:08", "throughput": 2647.64, "total_tokens": 6378776} {"current_steps": 23830, "total_steps": 38150, "loss": 0.1619, "lr": 1.8562120075510976e-05, "epoch": 6.246395806028834, "percentage": 62.46, "elapsed_time": "0:40:09", "remaining_time": "0:24:08", "throughput": 2647.65, "total_tokens": 6379976} {"current_steps": 23835, "total_steps": 38150, "loss": 0.1666, "lr": 1.8551069198426556e-05, "epoch": 6.247706422018348, "percentage": 62.48, "elapsed_time": "0:40:10", "remaining_time": "0:24:07", "throughput": 2647.84, "total_tokens": 6381768} {"current_steps": 23840, "total_steps": 38150, "loss": 0.4169, "lr": 1.854001967109221e-05, "epoch": 6.249017038007864, "percentage": 62.49, "elapsed_time": "0:40:10", "remaining_time": "0:24:06", "throughput": 2647.95, "total_tokens": 6383256} {"current_steps": 23845, "total_steps": 38150, "loss": 0.2085, "lr": 1.8528971495820584e-05, "epoch": 6.250327653997378, "percentage": 62.5, "elapsed_time": "0:40:11", "remaining_time": "0:24:06", "throughput": 2648.05, "total_tokens": 6384744} {"current_steps": 23850, "total_steps": 38150, "loss": 0.2708, "lr": 1.8517924674924048e-05, "epoch": 6.251638269986894, "percentage": 62.52, "elapsed_time": "0:40:11", "remaining_time": "0:24:05", "throughput": 2648.12, "total_tokens": 6386136} {"current_steps": 23855, "total_steps": 38150, "loss": 0.1497, "lr": 1.8506879210714685e-05, "epoch": 6.252948885976409, "percentage": 62.53, "elapsed_time": "0:40:11", "remaining_time": "0:24:05", "throughput": 2648.09, "total_tokens": 6387160} {"current_steps": 23860, "total_steps": 38150, "loss": 0.1553, "lr": 1.849583510550427e-05, "epoch": 6.254259501965924, "percentage": 62.54, "elapsed_time": "0:40:12", "remaining_time": "0:24:04", "throughput": 2648.32, "total_tokens": 6389128} {"current_steps": 23865, "total_steps": 38150, "loss": 0.219, "lr": 1.8484792361604336e-05, "epoch": 6.255570117955439, "percentage": 62.56, "elapsed_time": "0:40:12", "remaining_time": "0:24:04", "throughput": 2648.27, "total_tokens": 6390120} {"current_steps": 23870, "total_steps": 38150, "loss": 0.205, "lr": 1.84737509813261e-05, "epoch": 6.256880733944954, "percentage": 62.57, "elapsed_time": "0:40:13", "remaining_time": "0:24:03", "throughput": 2648.37, "total_tokens": 6391544} {"current_steps": 23875, "total_steps": 38150, "loss": 0.2279, "lr": 1.8462710966980506e-05, "epoch": 6.258191349934469, "percentage": 62.58, "elapsed_time": "0:40:13", "remaining_time": "0:24:03", "throughput": 2648.42, "total_tokens": 6392792} {"current_steps": 23880, "total_steps": 38150, "loss": 0.2422, "lr": 1.845167232087822e-05, "epoch": 6.259501965923985, "percentage": 62.6, "elapsed_time": "0:40:14", "remaining_time": "0:24:02", "throughput": 2648.5, "total_tokens": 6394248} {"current_steps": 23885, "total_steps": 38150, "loss": 0.1791, "lr": 1.8440635045329595e-05, "epoch": 6.260812581913499, "percentage": 62.61, "elapsed_time": "0:40:14", "remaining_time": "0:24:02", "throughput": 2648.52, "total_tokens": 6395416} {"current_steps": 23890, "total_steps": 38150, "loss": 0.2051, "lr": 1.8429599142644724e-05, "epoch": 6.262123197903015, "percentage": 62.62, "elapsed_time": "0:40:15", "remaining_time": "0:24:01", "throughput": 2648.51, "total_tokens": 6396536} {"current_steps": 23895, "total_steps": 38150, "loss": 0.2333, "lr": 1.84185646151334e-05, "epoch": 6.263433813892529, "percentage": 62.63, "elapsed_time": "0:40:15", "remaining_time": "0:24:01", "throughput": 2648.53, "total_tokens": 6397704} {"current_steps": 23900, "total_steps": 38150, "loss": 0.2519, "lr": 1.840753146510512e-05, "epoch": 6.264744429882045, "percentage": 62.65, "elapsed_time": "0:40:15", "remaining_time": "0:24:00", "throughput": 2648.53, "total_tokens": 6398840} {"current_steps": 23905, "total_steps": 38150, "loss": 0.2565, "lr": 1.8396499694869123e-05, "epoch": 6.26605504587156, "percentage": 62.66, "elapsed_time": "0:40:16", "remaining_time": "0:23:59", "throughput": 2648.62, "total_tokens": 6400264} {"current_steps": 23910, "total_steps": 38150, "loss": 0.2272, "lr": 1.8385469306734327e-05, "epoch": 6.267365661861074, "percentage": 62.67, "elapsed_time": "0:40:16", "remaining_time": "0:23:59", "throughput": 2648.56, "total_tokens": 6401224} {"current_steps": 23915, "total_steps": 38150, "loss": 0.3154, "lr": 1.8374440303009382e-05, "epoch": 6.26867627785059, "percentage": 62.69, "elapsed_time": "0:40:17", "remaining_time": "0:23:58", "throughput": 2648.75, "total_tokens": 6403080} {"current_steps": 23920, "total_steps": 38150, "loss": 0.2004, "lr": 1.836341268600263e-05, "epoch": 6.269986893840104, "percentage": 62.7, "elapsed_time": "0:40:17", "remaining_time": "0:23:58", "throughput": 2648.78, "total_tokens": 6404280} {"current_steps": 23925, "total_steps": 38150, "loss": 0.2674, "lr": 1.8352386458022135e-05, "epoch": 6.27129750982962, "percentage": 62.71, "elapsed_time": "0:40:18", "remaining_time": "0:23:57", "throughput": 2648.84, "total_tokens": 6405656} {"current_steps": 23930, "total_steps": 38150, "loss": 0.266, "lr": 1.8341361621375666e-05, "epoch": 6.272608125819135, "percentage": 62.73, "elapsed_time": "0:40:18", "remaining_time": "0:23:57", "throughput": 2648.89, "total_tokens": 6406936} {"current_steps": 23935, "total_steps": 38150, "loss": 0.2305, "lr": 1.8330338178370706e-05, "epoch": 6.27391874180865, "percentage": 62.74, "elapsed_time": "0:40:19", "remaining_time": "0:23:56", "throughput": 2648.96, "total_tokens": 6408216} {"current_steps": 23940, "total_steps": 38150, "loss": 0.195, "lr": 1.8319316131314447e-05, "epoch": 6.275229357798165, "percentage": 62.75, "elapsed_time": "0:40:19", "remaining_time": "0:23:56", "throughput": 2648.9, "total_tokens": 6409208} {"current_steps": 23945, "total_steps": 38150, "loss": 0.2469, "lr": 1.830829548251377e-05, "epoch": 6.27653997378768, "percentage": 62.77, "elapsed_time": "0:40:20", "remaining_time": "0:23:55", "throughput": 2649.23, "total_tokens": 6411704} {"current_steps": 23950, "total_steps": 38150, "loss": 0.2713, "lr": 1.829727623427529e-05, "epoch": 6.277850589777195, "percentage": 62.78, "elapsed_time": "0:40:20", "remaining_time": "0:23:55", "throughput": 2649.34, "total_tokens": 6413256} {"current_steps": 23955, "total_steps": 38150, "loss": 0.1597, "lr": 1.8286258388905308e-05, "epoch": 6.2791612057667106, "percentage": 62.79, "elapsed_time": "0:40:21", "remaining_time": "0:23:54", "throughput": 2649.36, "total_tokens": 6414440} {"current_steps": 23960, "total_steps": 38150, "loss": 0.2247, "lr": 1.8275241948709847e-05, "epoch": 6.280471821756225, "percentage": 62.8, "elapsed_time": "0:40:21", "remaining_time": "0:23:54", "throughput": 2649.28, "total_tokens": 6415336} {"current_steps": 23965, "total_steps": 38150, "loss": 0.1673, "lr": 1.8264226915994627e-05, "epoch": 6.281782437745741, "percentage": 62.82, "elapsed_time": "0:40:22", "remaining_time": "0:23:53", "throughput": 2649.5, "total_tokens": 6417224} {"current_steps": 23970, "total_steps": 38150, "loss": 0.2593, "lr": 1.8253213293065077e-05, "epoch": 6.283093053735255, "percentage": 62.83, "elapsed_time": "0:40:22", "remaining_time": "0:23:53", "throughput": 2649.53, "total_tokens": 6418456} {"current_steps": 23975, "total_steps": 38150, "loss": 0.3963, "lr": 1.8242201082226332e-05, "epoch": 6.284403669724771, "percentage": 62.84, "elapsed_time": "0:40:22", "remaining_time": "0:23:52", "throughput": 2649.59, "total_tokens": 6419768} {"current_steps": 23980, "total_steps": 38150, "loss": 0.4556, "lr": 1.8231190285783216e-05, "epoch": 6.285714285714286, "percentage": 62.86, "elapsed_time": "0:40:23", "remaining_time": "0:23:51", "throughput": 2649.67, "total_tokens": 6421128} {"current_steps": 23985, "total_steps": 38150, "loss": 0.2993, "lr": 1.822018090604028e-05, "epoch": 6.287024901703801, "percentage": 62.87, "elapsed_time": "0:40:23", "remaining_time": "0:23:51", "throughput": 2649.79, "total_tokens": 6422712} {"current_steps": 23990, "total_steps": 38150, "loss": 0.2144, "lr": 1.8209172945301768e-05, "epoch": 6.288335517693316, "percentage": 62.88, "elapsed_time": "0:40:24", "remaining_time": "0:23:50", "throughput": 2649.7, "total_tokens": 6423608} {"current_steps": 23995, "total_steps": 38150, "loss": 0.205, "lr": 1.819816640587162e-05, "epoch": 6.289646133682831, "percentage": 62.9, "elapsed_time": "0:40:24", "remaining_time": "0:23:50", "throughput": 2649.75, "total_tokens": 6424888} {"current_steps": 24000, "total_steps": 38150, "loss": 0.2622, "lr": 1.8187161290053498e-05, "epoch": 6.290956749672346, "percentage": 62.91, "elapsed_time": "0:40:25", "remaining_time": "0:23:49", "throughput": 2649.71, "total_tokens": 6425896} {"current_steps": 24005, "total_steps": 38150, "loss": 0.1905, "lr": 1.817615760015074e-05, "epoch": 6.292267365661861, "percentage": 62.92, "elapsed_time": "0:40:25", "remaining_time": "0:23:49", "throughput": 2649.73, "total_tokens": 6427144} {"current_steps": 24010, "total_steps": 38150, "loss": 0.1547, "lr": 1.8165155338466404e-05, "epoch": 6.293577981651376, "percentage": 62.94, "elapsed_time": "0:40:26", "remaining_time": "0:23:48", "throughput": 2649.78, "total_tokens": 6428424} {"current_steps": 24015, "total_steps": 38150, "loss": 0.1584, "lr": 1.8154154507303245e-05, "epoch": 6.294888597640891, "percentage": 62.95, "elapsed_time": "0:40:26", "remaining_time": "0:23:48", "throughput": 2649.84, "total_tokens": 6429848} {"current_steps": 24020, "total_steps": 38150, "loss": 0.2728, "lr": 1.814315510896372e-05, "epoch": 6.296199213630406, "percentage": 62.96, "elapsed_time": "0:40:26", "remaining_time": "0:23:47", "throughput": 2649.89, "total_tokens": 6431096} {"current_steps": 24025, "total_steps": 38150, "loss": 0.2323, "lr": 1.813215714574999e-05, "epoch": 6.297509829619921, "percentage": 62.98, "elapsed_time": "0:40:27", "remaining_time": "0:23:47", "throughput": 2649.89, "total_tokens": 6432232} {"current_steps": 24030, "total_steps": 38150, "loss": 0.1682, "lr": 1.8121160619963894e-05, "epoch": 6.2988204456094365, "percentage": 62.99, "elapsed_time": "0:40:27", "remaining_time": "0:23:46", "throughput": 2649.94, "total_tokens": 6433624} {"current_steps": 24035, "total_steps": 38150, "loss": 0.2476, "lr": 1.8110165533907007e-05, "epoch": 6.300131061598951, "percentage": 63.0, "elapsed_time": "0:40:28", "remaining_time": "0:23:46", "throughput": 2649.92, "total_tokens": 6434696} {"current_steps": 24040, "total_steps": 38150, "loss": 0.2018, "lr": 1.809917188988056e-05, "epoch": 6.301441677588467, "percentage": 63.01, "elapsed_time": "0:40:28", "remaining_time": "0:23:45", "throughput": 2649.96, "total_tokens": 6436104} {"current_steps": 24045, "total_steps": 38150, "loss": 0.2909, "lr": 1.8088179690185515e-05, "epoch": 6.302752293577981, "percentage": 63.03, "elapsed_time": "0:40:29", "remaining_time": "0:23:44", "throughput": 2650.0, "total_tokens": 6437336} {"current_steps": 24050, "total_steps": 38150, "loss": 0.1841, "lr": 1.8077188937122515e-05, "epoch": 6.304062909567497, "percentage": 63.04, "elapsed_time": "0:40:29", "remaining_time": "0:23:44", "throughput": 2650.0, "total_tokens": 6438504} {"current_steps": 24055, "total_steps": 38150, "loss": 0.2193, "lr": 1.8066199632991913e-05, "epoch": 6.305373525557012, "percentage": 63.05, "elapsed_time": "0:40:30", "remaining_time": "0:23:43", "throughput": 2649.99, "total_tokens": 6439592} {"current_steps": 24060, "total_steps": 38150, "loss": 0.3532, "lr": 1.805521178009375e-05, "epoch": 6.306684141546527, "percentage": 63.07, "elapsed_time": "0:40:30", "remaining_time": "0:23:43", "throughput": 2650.08, "total_tokens": 6441000} {"current_steps": 24065, "total_steps": 38150, "loss": 0.2159, "lr": 1.804422538072775e-05, "epoch": 6.307994757536042, "percentage": 63.08, "elapsed_time": "0:40:30", "remaining_time": "0:23:42", "throughput": 2650.14, "total_tokens": 6442376} {"current_steps": 24070, "total_steps": 38150, "loss": 0.1965, "lr": 1.8033240437193364e-05, "epoch": 6.309305373525557, "percentage": 63.09, "elapsed_time": "0:40:31", "remaining_time": "0:23:42", "throughput": 2650.2, "total_tokens": 6443688} {"current_steps": 24075, "total_steps": 38150, "loss": 0.2984, "lr": 1.8022256951789718e-05, "epoch": 6.310615989515072, "percentage": 63.11, "elapsed_time": "0:40:31", "remaining_time": "0:23:41", "throughput": 2650.3, "total_tokens": 6445176} {"current_steps": 24080, "total_steps": 38150, "loss": 0.1791, "lr": 1.8011274926815635e-05, "epoch": 6.3119266055045875, "percentage": 63.12, "elapsed_time": "0:40:32", "remaining_time": "0:23:41", "throughput": 2650.32, "total_tokens": 6446360} {"current_steps": 24085, "total_steps": 38150, "loss": 0.487, "lr": 1.8000294364569636e-05, "epoch": 6.313237221494102, "percentage": 63.13, "elapsed_time": "0:40:32", "remaining_time": "0:23:40", "throughput": 2650.35, "total_tokens": 6447560} {"current_steps": 24090, "total_steps": 38150, "loss": 0.2176, "lr": 1.7989315267349936e-05, "epoch": 6.314547837483618, "percentage": 63.15, "elapsed_time": "0:40:33", "remaining_time": "0:23:40", "throughput": 2650.4, "total_tokens": 6448792} {"current_steps": 24095, "total_steps": 38150, "loss": 0.1891, "lr": 1.7978337637454433e-05, "epoch": 6.315858453473132, "percentage": 63.16, "elapsed_time": "0:40:33", "remaining_time": "0:23:39", "throughput": 2650.48, "total_tokens": 6450232} {"current_steps": 24100, "total_steps": 38150, "loss": 0.2986, "lr": 1.7967361477180727e-05, "epoch": 6.317169069462647, "percentage": 63.17, "elapsed_time": "0:40:34", "remaining_time": "0:23:39", "throughput": 2650.61, "total_tokens": 6451736} {"current_steps": 24105, "total_steps": 38150, "loss": 0.2703, "lr": 1.7956386788826112e-05, "epoch": 6.3184796854521625, "percentage": 63.18, "elapsed_time": "0:40:34", "remaining_time": "0:23:38", "throughput": 2650.55, "total_tokens": 6452696} {"current_steps": 24110, "total_steps": 38150, "loss": 0.3036, "lr": 1.7945413574687574e-05, "epoch": 6.319790301441677, "percentage": 63.2, "elapsed_time": "0:40:34", "remaining_time": "0:23:37", "throughput": 2650.64, "total_tokens": 6454168} {"current_steps": 24115, "total_steps": 38150, "loss": 0.3831, "lr": 1.7934441837061795e-05, "epoch": 6.321100917431193, "percentage": 63.21, "elapsed_time": "0:40:35", "remaining_time": "0:23:37", "throughput": 2650.69, "total_tokens": 6455480} {"current_steps": 24120, "total_steps": 38150, "loss": 0.1871, "lr": 1.792347157824512e-05, "epoch": 6.322411533420707, "percentage": 63.22, "elapsed_time": "0:40:35", "remaining_time": "0:23:36", "throughput": 2650.73, "total_tokens": 6456728} {"current_steps": 24125, "total_steps": 38150, "loss": 0.2614, "lr": 1.7912502800533604e-05, "epoch": 6.323722149410223, "percentage": 63.24, "elapsed_time": "0:40:36", "remaining_time": "0:23:36", "throughput": 2650.81, "total_tokens": 6458152} {"current_steps": 24130, "total_steps": 38150, "loss": 0.2017, "lr": 1.7901535506223027e-05, "epoch": 6.325032765399738, "percentage": 63.25, "elapsed_time": "0:40:36", "remaining_time": "0:23:35", "throughput": 2650.82, "total_tokens": 6459304} {"current_steps": 24135, "total_steps": 38150, "loss": 0.3047, "lr": 1.7890569697608793e-05, "epoch": 6.326343381389253, "percentage": 63.26, "elapsed_time": "0:40:37", "remaining_time": "0:23:35", "throughput": 2650.81, "total_tokens": 6460376} {"current_steps": 24140, "total_steps": 38150, "loss": 0.2369, "lr": 1.787960537698604e-05, "epoch": 6.327653997378768, "percentage": 63.28, "elapsed_time": "0:40:37", "remaining_time": "0:23:34", "throughput": 2650.82, "total_tokens": 6461528} {"current_steps": 24145, "total_steps": 38150, "loss": 0.1855, "lr": 1.786864254664958e-05, "epoch": 6.328964613368283, "percentage": 63.29, "elapsed_time": "0:40:38", "remaining_time": "0:23:34", "throughput": 2651.01, "total_tokens": 6463512} {"current_steps": 24150, "total_steps": 38150, "loss": 0.1832, "lr": 1.785768120889392e-05, "epoch": 6.330275229357798, "percentage": 63.3, "elapsed_time": "0:40:38", "remaining_time": "0:23:33", "throughput": 2650.97, "total_tokens": 6464568} {"current_steps": 24155, "total_steps": 38150, "loss": 0.252, "lr": 1.784672136601323e-05, "epoch": 6.3315858453473135, "percentage": 63.32, "elapsed_time": "0:40:38", "remaining_time": "0:23:33", "throughput": 2650.97, "total_tokens": 6465688} {"current_steps": 24160, "total_steps": 38150, "loss": 0.1645, "lr": 1.7835763020301403e-05, "epoch": 6.332896461336828, "percentage": 63.33, "elapsed_time": "0:40:39", "remaining_time": "0:23:32", "throughput": 2651.13, "total_tokens": 6467288} {"current_steps": 24165, "total_steps": 38150, "loss": 0.1554, "lr": 1.7824806174051995e-05, "epoch": 6.334207077326344, "percentage": 63.34, "elapsed_time": "0:40:39", "remaining_time": "0:23:32", "throughput": 2651.06, "total_tokens": 6468232} {"current_steps": 24170, "total_steps": 38150, "loss": 0.2408, "lr": 1.7813850829558257e-05, "epoch": 6.335517693315858, "percentage": 63.36, "elapsed_time": "0:40:40", "remaining_time": "0:23:31", "throughput": 2651.09, "total_tokens": 6469512} {"current_steps": 24175, "total_steps": 38150, "loss": 0.2936, "lr": 1.7802896989113127e-05, "epoch": 6.336828309305374, "percentage": 63.37, "elapsed_time": "0:40:40", "remaining_time": "0:23:30", "throughput": 2651.12, "total_tokens": 6470744} {"current_steps": 24180, "total_steps": 38150, "loss": 0.2489, "lr": 1.779194465500922e-05, "epoch": 6.3381389252948885, "percentage": 63.38, "elapsed_time": "0:40:41", "remaining_time": "0:23:30", "throughput": 2651.13, "total_tokens": 6471864} {"current_steps": 24185, "total_steps": 38150, "loss": 0.2717, "lr": 1.7780993829538836e-05, "epoch": 6.339449541284404, "percentage": 63.39, "elapsed_time": "0:40:41", "remaining_time": "0:23:29", "throughput": 2651.09, "total_tokens": 6472904} {"current_steps": 24190, "total_steps": 38150, "loss": 0.2948, "lr": 1.7770044514993973e-05, "epoch": 6.340760157273919, "percentage": 63.41, "elapsed_time": "0:40:42", "remaining_time": "0:23:29", "throughput": 2651.29, "total_tokens": 6474808} {"current_steps": 24195, "total_steps": 38150, "loss": 0.4005, "lr": 1.7759096713666305e-05, "epoch": 6.342070773263433, "percentage": 63.42, "elapsed_time": "0:40:42", "remaining_time": "0:23:28", "throughput": 2651.37, "total_tokens": 6476168} {"current_steps": 24200, "total_steps": 38150, "loss": 0.1159, "lr": 1.774815042784718e-05, "epoch": 6.343381389252949, "percentage": 63.43, "elapsed_time": "0:40:42", "remaining_time": "0:23:28", "throughput": 2651.33, "total_tokens": 6477160} {"current_steps": 24205, "total_steps": 38150, "loss": 0.2619, "lr": 1.773720565982764e-05, "epoch": 6.344692005242464, "percentage": 63.45, "elapsed_time": "0:40:43", "remaining_time": "0:23:27", "throughput": 2651.4, "total_tokens": 6478600} {"current_steps": 24210, "total_steps": 38150, "loss": 0.2731, "lr": 1.7726262411898413e-05, "epoch": 6.346002621231979, "percentage": 63.46, "elapsed_time": "0:40:44", "remaining_time": "0:23:27", "throughput": 2651.55, "total_tokens": 6480408} {"current_steps": 24215, "total_steps": 38150, "loss": 0.3357, "lr": 1.771532068634989e-05, "epoch": 6.347313237221494, "percentage": 63.47, "elapsed_time": "0:40:44", "remaining_time": "0:23:26", "throughput": 2651.5, "total_tokens": 6481416} {"current_steps": 24220, "total_steps": 38150, "loss": 0.4477, "lr": 1.770438048547216e-05, "epoch": 6.348623853211009, "percentage": 63.49, "elapsed_time": "0:40:44", "remaining_time": "0:23:26", "throughput": 2651.58, "total_tokens": 6482840} {"current_steps": 24225, "total_steps": 38150, "loss": 0.294, "lr": 1.769344181155499e-05, "epoch": 6.349934469200524, "percentage": 63.5, "elapsed_time": "0:40:45", "remaining_time": "0:23:25", "throughput": 2651.59, "total_tokens": 6484024} {"current_steps": 24230, "total_steps": 38150, "loss": 0.2279, "lr": 1.7682504666887823e-05, "epoch": 6.3512450851900395, "percentage": 63.51, "elapsed_time": "0:40:45", "remaining_time": "0:23:25", "throughput": 2651.6, "total_tokens": 6485192} {"current_steps": 24235, "total_steps": 38150, "loss": 0.1947, "lr": 1.767156905375979e-05, "epoch": 6.352555701179554, "percentage": 63.53, "elapsed_time": "0:40:46", "remaining_time": "0:23:24", "throughput": 2651.72, "total_tokens": 6486760} {"current_steps": 24240, "total_steps": 38150, "loss": 0.2758, "lr": 1.7660634974459674e-05, "epoch": 6.35386631716907, "percentage": 63.54, "elapsed_time": "0:40:46", "remaining_time": "0:23:24", "throughput": 2651.74, "total_tokens": 6487960} {"current_steps": 24245, "total_steps": 38150, "loss": 0.4716, "lr": 1.7649702431275994e-05, "epoch": 6.355176933158584, "percentage": 63.55, "elapsed_time": "0:40:47", "remaining_time": "0:23:23", "throughput": 2651.71, "total_tokens": 6489096} {"current_steps": 24250, "total_steps": 38150, "loss": 0.2635, "lr": 1.7638771426496893e-05, "epoch": 6.3564875491481, "percentage": 63.56, "elapsed_time": "0:40:47", "remaining_time": "0:23:22", "throughput": 2651.76, "total_tokens": 6490344} {"current_steps": 24255, "total_steps": 38150, "loss": 0.3211, "lr": 1.7627841962410208e-05, "epoch": 6.3577981651376145, "percentage": 63.58, "elapsed_time": "0:40:48", "remaining_time": "0:23:22", "throughput": 2651.86, "total_tokens": 6491832} {"current_steps": 24260, "total_steps": 38150, "loss": 0.324, "lr": 1.7616914041303463e-05, "epoch": 6.35910878112713, "percentage": 63.59, "elapsed_time": "0:40:48", "remaining_time": "0:23:21", "throughput": 2651.83, "total_tokens": 6492952} {"current_steps": 24265, "total_steps": 38150, "loss": 0.1863, "lr": 1.7605987665463854e-05, "epoch": 6.360419397116645, "percentage": 63.6, "elapsed_time": "0:40:48", "remaining_time": "0:23:21", "throughput": 2651.86, "total_tokens": 6494248} {"current_steps": 24270, "total_steps": 38150, "loss": 0.131, "lr": 1.7595062837178254e-05, "epoch": 6.36173001310616, "percentage": 63.62, "elapsed_time": "0:40:49", "remaining_time": "0:23:20", "throughput": 2651.85, "total_tokens": 6495336} {"current_steps": 24275, "total_steps": 38150, "loss": 0.1565, "lr": 1.7584139558733205e-05, "epoch": 6.363040629095675, "percentage": 63.63, "elapsed_time": "0:40:49", "remaining_time": "0:23:20", "throughput": 2651.8, "total_tokens": 6496312} {"current_steps": 24280, "total_steps": 38150, "loss": 0.2096, "lr": 1.757321783241493e-05, "epoch": 6.3643512450851905, "percentage": 63.64, "elapsed_time": "0:40:50", "remaining_time": "0:23:19", "throughput": 2651.81, "total_tokens": 6497528} {"current_steps": 24285, "total_steps": 38150, "loss": 0.3641, "lr": 1.7562297660509334e-05, "epoch": 6.365661861074705, "percentage": 63.66, "elapsed_time": "0:40:50", "remaining_time": "0:23:19", "throughput": 2651.89, "total_tokens": 6498936} {"current_steps": 24290, "total_steps": 38150, "loss": 0.2273, "lr": 1.7551379045301987e-05, "epoch": 6.36697247706422, "percentage": 63.67, "elapsed_time": "0:40:51", "remaining_time": "0:23:18", "throughput": 2651.87, "total_tokens": 6500024} {"current_steps": 24295, "total_steps": 38150, "loss": 0.3539, "lr": 1.7540461989078132e-05, "epoch": 6.368283093053735, "percentage": 63.68, "elapsed_time": "0:40:51", "remaining_time": "0:23:18", "throughput": 2652.01, "total_tokens": 6501640} {"current_steps": 24300, "total_steps": 38150, "loss": 0.2426, "lr": 1.7529546494122685e-05, "epoch": 6.36959370904325, "percentage": 63.7, "elapsed_time": "0:40:52", "remaining_time": "0:23:17", "throughput": 2652.12, "total_tokens": 6503144} {"current_steps": 24305, "total_steps": 38150, "loss": 0.3061, "lr": 1.7518632562720263e-05, "epoch": 6.3709043250327655, "percentage": 63.71, "elapsed_time": "0:40:52", "remaining_time": "0:23:17", "throughput": 2652.15, "total_tokens": 6504360} {"current_steps": 24310, "total_steps": 38150, "loss": 0.2366, "lr": 1.7507720197155114e-05, "epoch": 6.37221494102228, "percentage": 63.72, "elapsed_time": "0:40:52", "remaining_time": "0:23:16", "throughput": 2652.3, "total_tokens": 6505992} {"current_steps": 24315, "total_steps": 38150, "loss": 0.4744, "lr": 1.749680939971118e-05, "epoch": 6.373525557011796, "percentage": 63.74, "elapsed_time": "0:40:53", "remaining_time": "0:23:15", "throughput": 2652.44, "total_tokens": 6507608} {"current_steps": 24320, "total_steps": 38150, "loss": 0.2382, "lr": 1.7485900172672076e-05, "epoch": 6.37483617300131, "percentage": 63.75, "elapsed_time": "0:40:53", "remaining_time": "0:23:15", "throughput": 2652.53, "total_tokens": 6509112} {"current_steps": 24325, "total_steps": 38150, "loss": 0.1497, "lr": 1.7474992518321083e-05, "epoch": 6.376146788990826, "percentage": 63.76, "elapsed_time": "0:40:54", "remaining_time": "0:23:14", "throughput": 2652.57, "total_tokens": 6510408} {"current_steps": 24330, "total_steps": 38150, "loss": 0.417, "lr": 1.7464086438941156e-05, "epoch": 6.3774574049803405, "percentage": 63.77, "elapsed_time": "0:40:54", "remaining_time": "0:23:14", "throughput": 2652.68, "total_tokens": 6511992} {"current_steps": 24335, "total_steps": 38150, "loss": 0.2196, "lr": 1.7453181936814915e-05, "epoch": 6.378768020969856, "percentage": 63.79, "elapsed_time": "0:40:55", "remaining_time": "0:23:13", "throughput": 2652.7, "total_tokens": 6513288} {"current_steps": 24340, "total_steps": 38150, "loss": 0.2782, "lr": 1.7442279014224654e-05, "epoch": 6.380078636959371, "percentage": 63.8, "elapsed_time": "0:40:55", "remaining_time": "0:23:13", "throughput": 2652.69, "total_tokens": 6514456} {"current_steps": 24345, "total_steps": 38150, "loss": 0.2153, "lr": 1.7431377673452336e-05, "epoch": 6.381389252948886, "percentage": 63.81, "elapsed_time": "0:40:56", "remaining_time": "0:23:12", "throughput": 2652.75, "total_tokens": 6515832} {"current_steps": 24350, "total_steps": 38150, "loss": 0.2869, "lr": 1.74204779167796e-05, "epoch": 6.382699868938401, "percentage": 63.83, "elapsed_time": "0:40:56", "remaining_time": "0:23:12", "throughput": 2652.74, "total_tokens": 6517000} {"current_steps": 24355, "total_steps": 38150, "loss": 0.2947, "lr": 1.740957974648772e-05, "epoch": 6.3840104849279165, "percentage": 63.84, "elapsed_time": "0:40:57", "remaining_time": "0:23:11", "throughput": 2652.94, "total_tokens": 6519128} {"current_steps": 24360, "total_steps": 38150, "loss": 0.1577, "lr": 1.7398683164857697e-05, "epoch": 6.385321100917431, "percentage": 63.85, "elapsed_time": "0:40:57", "remaining_time": "0:23:11", "throughput": 2652.89, "total_tokens": 6520104} {"current_steps": 24365, "total_steps": 38150, "loss": 0.2763, "lr": 1.7387788174170157e-05, "epoch": 6.386631716906947, "percentage": 63.87, "elapsed_time": "0:40:58", "remaining_time": "0:23:10", "throughput": 2653.02, "total_tokens": 6521720} {"current_steps": 24370, "total_steps": 38150, "loss": 0.2115, "lr": 1.7376894776705397e-05, "epoch": 6.387942332896461, "percentage": 63.88, "elapsed_time": "0:40:58", "remaining_time": "0:23:10", "throughput": 2653.17, "total_tokens": 6523304} {"current_steps": 24375, "total_steps": 38150, "loss": 0.2122, "lr": 1.7366002974743383e-05, "epoch": 6.389252948885977, "percentage": 63.89, "elapsed_time": "0:40:59", "remaining_time": "0:23:09", "throughput": 2653.21, "total_tokens": 6524536} {"current_steps": 24380, "total_steps": 38150, "loss": 0.3208, "lr": 1.7355112770563764e-05, "epoch": 6.3905635648754915, "percentage": 63.91, "elapsed_time": "0:40:59", "remaining_time": "0:23:09", "throughput": 2653.31, "total_tokens": 6526024} {"current_steps": 24385, "total_steps": 38150, "loss": 0.3404, "lr": 1.734422416644583e-05, "epoch": 6.391874180865006, "percentage": 63.92, "elapsed_time": "0:40:59", "remaining_time": "0:23:08", "throughput": 2653.3, "total_tokens": 6527112} {"current_steps": 24390, "total_steps": 38150, "loss": 0.34, "lr": 1.733333716466855e-05, "epoch": 6.393184796854522, "percentage": 63.93, "elapsed_time": "0:41:00", "remaining_time": "0:23:08", "throughput": 2653.39, "total_tokens": 6528552} {"current_steps": 24395, "total_steps": 38150, "loss": 0.2912, "lr": 1.732245176751055e-05, "epoch": 6.394495412844036, "percentage": 63.94, "elapsed_time": "0:41:00", "remaining_time": "0:23:07", "throughput": 2653.38, "total_tokens": 6529688} {"current_steps": 24400, "total_steps": 38150, "loss": 0.3077, "lr": 1.7311567977250133e-05, "epoch": 6.395806028833552, "percentage": 63.96, "elapsed_time": "0:41:01", "remaining_time": "0:23:07", "throughput": 2653.46, "total_tokens": 6531032} {"current_steps": 24405, "total_steps": 38150, "loss": 0.1641, "lr": 1.7300685796165255e-05, "epoch": 6.3971166448230665, "percentage": 63.97, "elapsed_time": "0:41:01", "remaining_time": "0:23:06", "throughput": 2653.39, "total_tokens": 6531944} {"current_steps": 24410, "total_steps": 38150, "loss": 0.1929, "lr": 1.728980522653354e-05, "epoch": 6.398427260812582, "percentage": 63.98, "elapsed_time": "0:41:02", "remaining_time": "0:23:05", "throughput": 2653.34, "total_tokens": 6532968} {"current_steps": 24415, "total_steps": 38150, "loss": 0.2341, "lr": 1.727892627063225e-05, "epoch": 6.399737876802097, "percentage": 64.0, "elapsed_time": "0:41:02", "remaining_time": "0:23:05", "throughput": 2653.36, "total_tokens": 6534152} {"current_steps": 24420, "total_steps": 38150, "loss": 0.2893, "lr": 1.726804893073837e-05, "epoch": 6.401048492791612, "percentage": 64.01, "elapsed_time": "0:41:03", "remaining_time": "0:23:04", "throughput": 2653.44, "total_tokens": 6535608} {"current_steps": 24425, "total_steps": 38150, "loss": 0.3891, "lr": 1.725717320912848e-05, "epoch": 6.402359108781127, "percentage": 64.02, "elapsed_time": "0:41:03", "remaining_time": "0:23:04", "throughput": 2653.45, "total_tokens": 6536760} {"current_steps": 24430, "total_steps": 38150, "loss": 0.3451, "lr": 1.724629910807886e-05, "epoch": 6.4036697247706424, "percentage": 64.04, "elapsed_time": "0:41:03", "remaining_time": "0:23:03", "throughput": 2653.54, "total_tokens": 6538232} {"current_steps": 24435, "total_steps": 38150, "loss": 0.1314, "lr": 1.7235426629865445e-05, "epoch": 6.404980340760157, "percentage": 64.05, "elapsed_time": "0:41:04", "remaining_time": "0:23:03", "throughput": 2653.55, "total_tokens": 6539464} {"current_steps": 24440, "total_steps": 38150, "loss": 0.191, "lr": 1.7224555776763814e-05, "epoch": 6.406290956749673, "percentage": 64.06, "elapsed_time": "0:41:04", "remaining_time": "0:23:02", "throughput": 2653.52, "total_tokens": 6540568} {"current_steps": 24445, "total_steps": 38150, "loss": 0.2988, "lr": 1.7213686551049233e-05, "epoch": 6.407601572739187, "percentage": 64.08, "elapsed_time": "0:41:05", "remaining_time": "0:23:02", "throughput": 2653.95, "total_tokens": 6543944} {"current_steps": 24450, "total_steps": 38150, "loss": 0.2112, "lr": 1.7202818954996597e-05, "epoch": 6.408912188728703, "percentage": 64.09, "elapsed_time": "0:41:06", "remaining_time": "0:23:01", "throughput": 2653.89, "total_tokens": 6544920} {"current_steps": 24455, "total_steps": 38150, "loss": 0.265, "lr": 1.7191952990880476e-05, "epoch": 6.4102228047182175, "percentage": 64.1, "elapsed_time": "0:41:06", "remaining_time": "0:23:01", "throughput": 2653.92, "total_tokens": 6546136} {"current_steps": 24460, "total_steps": 38150, "loss": 0.24, "lr": 1.7181088660975107e-05, "epoch": 6.411533420707733, "percentage": 64.12, "elapsed_time": "0:41:07", "remaining_time": "0:23:00", "throughput": 2653.92, "total_tokens": 6547272} {"current_steps": 24465, "total_steps": 38150, "loss": 0.176, "lr": 1.7170225967554374e-05, "epoch": 6.412844036697248, "percentage": 64.13, "elapsed_time": "0:41:07", "remaining_time": "0:23:00", "throughput": 2653.92, "total_tokens": 6548376} {"current_steps": 24470, "total_steps": 38150, "loss": 0.2579, "lr": 1.715936491289181e-05, "epoch": 6.414154652686763, "percentage": 64.14, "elapsed_time": "0:41:07", "remaining_time": "0:22:59", "throughput": 2654.09, "total_tokens": 6550072} {"current_steps": 24475, "total_steps": 38150, "loss": 0.2947, "lr": 1.7148505499260627e-05, "epoch": 6.415465268676278, "percentage": 64.15, "elapsed_time": "0:41:08", "remaining_time": "0:22:59", "throughput": 2654.24, "total_tokens": 6551736} {"current_steps": 24480, "total_steps": 38150, "loss": 0.242, "lr": 1.713764772893368e-05, "epoch": 6.4167758846657925, "percentage": 64.17, "elapsed_time": "0:41:08", "remaining_time": "0:22:58", "throughput": 2654.31, "total_tokens": 6553144} {"current_steps": 24485, "total_steps": 38150, "loss": 0.2276, "lr": 1.7126791604183474e-05, "epoch": 6.418086500655308, "percentage": 64.18, "elapsed_time": "0:41:09", "remaining_time": "0:22:58", "throughput": 2654.28, "total_tokens": 6554152} {"current_steps": 24490, "total_steps": 38150, "loss": 0.1903, "lr": 1.7115937127282182e-05, "epoch": 6.419397116644823, "percentage": 64.19, "elapsed_time": "0:41:09", "remaining_time": "0:22:57", "throughput": 2654.24, "total_tokens": 6555160} {"current_steps": 24495, "total_steps": 38150, "loss": 0.2461, "lr": 1.7105084300501627e-05, "epoch": 6.420707732634338, "percentage": 64.21, "elapsed_time": "0:41:10", "remaining_time": "0:22:56", "throughput": 2654.23, "total_tokens": 6556232} {"current_steps": 24500, "total_steps": 38150, "loss": 0.3941, "lr": 1.7094233126113285e-05, "epoch": 6.422018348623853, "percentage": 64.22, "elapsed_time": "0:41:10", "remaining_time": "0:22:56", "throughput": 2654.27, "total_tokens": 6557448} {"current_steps": 24505, "total_steps": 38150, "loss": 0.2356, "lr": 1.70833836063883e-05, "epoch": 6.423328964613368, "percentage": 64.23, "elapsed_time": "0:41:10", "remaining_time": "0:22:55", "throughput": 2654.28, "total_tokens": 6558680} {"current_steps": 24510, "total_steps": 38150, "loss": 0.3006, "lr": 1.7072535743597433e-05, "epoch": 6.424639580602883, "percentage": 64.25, "elapsed_time": "0:41:11", "remaining_time": "0:22:55", "throughput": 2654.29, "total_tokens": 6559848} {"current_steps": 24515, "total_steps": 38150, "loss": 0.1915, "lr": 1.7061689540011144e-05, "epoch": 6.425950196592399, "percentage": 64.26, "elapsed_time": "0:41:11", "remaining_time": "0:22:54", "throughput": 2654.27, "total_tokens": 6560904} {"current_steps": 24520, "total_steps": 38150, "loss": 0.2399, "lr": 1.7050844997899517e-05, "epoch": 6.427260812581913, "percentage": 64.27, "elapsed_time": "0:41:12", "remaining_time": "0:22:54", "throughput": 2654.32, "total_tokens": 6562184} {"current_steps": 24525, "total_steps": 38150, "loss": 0.2031, "lr": 1.70400021195323e-05, "epoch": 6.428571428571429, "percentage": 64.29, "elapsed_time": "0:41:12", "remaining_time": "0:22:53", "throughput": 2654.41, "total_tokens": 6563656} {"current_steps": 24530, "total_steps": 38150, "loss": 0.2655, "lr": 1.702916090717887e-05, "epoch": 6.4298820445609435, "percentage": 64.3, "elapsed_time": "0:41:13", "remaining_time": "0:22:53", "throughput": 2654.42, "total_tokens": 6564808} {"current_steps": 24535, "total_steps": 38150, "loss": 0.2304, "lr": 1.7018321363108303e-05, "epoch": 6.431192660550459, "percentage": 64.31, "elapsed_time": "0:41:13", "remaining_time": "0:22:52", "throughput": 2654.31, "total_tokens": 6565656} {"current_steps": 24540, "total_steps": 38150, "loss": 0.2822, "lr": 1.700748348958929e-05, "epoch": 6.432503276539974, "percentage": 64.33, "elapsed_time": "0:41:14", "remaining_time": "0:22:52", "throughput": 2654.42, "total_tokens": 6567176} {"current_steps": 24545, "total_steps": 38150, "loss": 0.2212, "lr": 1.699664728889016e-05, "epoch": 6.433813892529489, "percentage": 64.34, "elapsed_time": "0:41:14", "remaining_time": "0:22:51", "throughput": 2654.47, "total_tokens": 6568520} {"current_steps": 24550, "total_steps": 38150, "loss": 0.2069, "lr": 1.698581276327893e-05, "epoch": 6.435124508519004, "percentage": 64.35, "elapsed_time": "0:41:14", "remaining_time": "0:22:51", "throughput": 2654.45, "total_tokens": 6569592} {"current_steps": 24555, "total_steps": 38150, "loss": 0.2036, "lr": 1.6974979915023237e-05, "epoch": 6.436435124508519, "percentage": 64.36, "elapsed_time": "0:41:15", "remaining_time": "0:22:50", "throughput": 2654.46, "total_tokens": 6570744} {"current_steps": 24560, "total_steps": 38150, "loss": 0.1597, "lr": 1.6964148746390383e-05, "epoch": 6.437745740498034, "percentage": 64.38, "elapsed_time": "0:41:15", "remaining_time": "0:22:49", "throughput": 2654.4, "total_tokens": 6571704} {"current_steps": 24565, "total_steps": 38150, "loss": 0.3337, "lr": 1.6953319259647323e-05, "epoch": 6.43905635648755, "percentage": 64.39, "elapsed_time": "0:41:16", "remaining_time": "0:22:49", "throughput": 2654.4, "total_tokens": 6572904} {"current_steps": 24570, "total_steps": 38150, "loss": 0.4859, "lr": 1.6942491457060626e-05, "epoch": 6.440366972477064, "percentage": 64.4, "elapsed_time": "0:41:16", "remaining_time": "0:22:48", "throughput": 2654.53, "total_tokens": 6574520} {"current_steps": 24575, "total_steps": 38150, "loss": 0.2933, "lr": 1.6931665340896545e-05, "epoch": 6.441677588466579, "percentage": 64.42, "elapsed_time": "0:41:17", "remaining_time": "0:22:48", "throughput": 2654.66, "total_tokens": 6576152} {"current_steps": 24580, "total_steps": 38150, "loss": 0.2903, "lr": 1.692084091342097e-05, "epoch": 6.442988204456094, "percentage": 64.43, "elapsed_time": "0:41:17", "remaining_time": "0:22:47", "throughput": 2654.73, "total_tokens": 6577512} {"current_steps": 24585, "total_steps": 38150, "loss": 0.1503, "lr": 1.6910018176899424e-05, "epoch": 6.444298820445609, "percentage": 64.44, "elapsed_time": "0:41:18", "remaining_time": "0:22:47", "throughput": 2654.74, "total_tokens": 6578648} {"current_steps": 24590, "total_steps": 38150, "loss": 0.2222, "lr": 1.68991971335971e-05, "epoch": 6.445609436435125, "percentage": 64.46, "elapsed_time": "0:41:18", "remaining_time": "0:22:46", "throughput": 2654.81, "total_tokens": 6579992} {"current_steps": 24595, "total_steps": 38150, "loss": 0.1797, "lr": 1.688837778577882e-05, "epoch": 6.446920052424639, "percentage": 64.47, "elapsed_time": "0:41:18", "remaining_time": "0:22:46", "throughput": 2654.8, "total_tokens": 6581096} {"current_steps": 24600, "total_steps": 38150, "loss": 0.2566, "lr": 1.687756013570906e-05, "epoch": 6.448230668414155, "percentage": 64.48, "elapsed_time": "0:41:19", "remaining_time": "0:22:45", "throughput": 2654.83, "total_tokens": 6582344} {"current_steps": 24605, "total_steps": 38150, "loss": 0.2607, "lr": 1.6866744185651922e-05, "epoch": 6.4495412844036695, "percentage": 64.5, "elapsed_time": "0:41:19", "remaining_time": "0:22:45", "throughput": 2654.92, "total_tokens": 6583800} {"current_steps": 24610, "total_steps": 38150, "loss": 0.2794, "lr": 1.6855929937871175e-05, "epoch": 6.450851900393185, "percentage": 64.51, "elapsed_time": "0:41:20", "remaining_time": "0:22:44", "throughput": 2655.15, "total_tokens": 6585896} {"current_steps": 24615, "total_steps": 38150, "loss": 0.2299, "lr": 1.6845117394630223e-05, "epoch": 6.4521625163827, "percentage": 64.52, "elapsed_time": "0:41:20", "remaining_time": "0:22:44", "throughput": 2655.21, "total_tokens": 6587224} {"current_steps": 24620, "total_steps": 38150, "loss": 0.274, "lr": 1.683430655819211e-05, "epoch": 6.453473132372215, "percentage": 64.53, "elapsed_time": "0:41:21", "remaining_time": "0:22:43", "throughput": 2655.34, "total_tokens": 6588792} {"current_steps": 24625, "total_steps": 38150, "loss": 0.2232, "lr": 1.6823497430819518e-05, "epoch": 6.45478374836173, "percentage": 64.55, "elapsed_time": "0:41:21", "remaining_time": "0:22:43", "throughput": 2655.4, "total_tokens": 6590104} {"current_steps": 24630, "total_steps": 38150, "loss": 0.2478, "lr": 1.681269001477479e-05, "epoch": 6.456094364351245, "percentage": 64.56, "elapsed_time": "0:41:22", "remaining_time": "0:22:42", "throughput": 2655.33, "total_tokens": 6591032} {"current_steps": 24635, "total_steps": 38150, "loss": 0.2801, "lr": 1.6801884312319895e-05, "epoch": 6.45740498034076, "percentage": 64.57, "elapsed_time": "0:41:22", "remaining_time": "0:22:42", "throughput": 2655.43, "total_tokens": 6592664} {"current_steps": 24640, "total_steps": 38150, "loss": 0.2147, "lr": 1.6791080325716445e-05, "epoch": 6.458715596330276, "percentage": 64.59, "elapsed_time": "0:41:23", "remaining_time": "0:22:41", "throughput": 2655.5, "total_tokens": 6594184} {"current_steps": 24645, "total_steps": 38150, "loss": 0.1609, "lr": 1.6780278057225697e-05, "epoch": 6.46002621231979, "percentage": 64.6, "elapsed_time": "0:41:23", "remaining_time": "0:22:40", "throughput": 2655.5, "total_tokens": 6595320} {"current_steps": 24650, "total_steps": 38150, "loss": 0.3378, "lr": 1.6769477509108556e-05, "epoch": 6.461336828309306, "percentage": 64.61, "elapsed_time": "0:41:24", "remaining_time": "0:22:40", "throughput": 2655.57, "total_tokens": 6596680} {"current_steps": 24655, "total_steps": 38150, "loss": 0.2921, "lr": 1.675867868362555e-05, "epoch": 6.46264744429882, "percentage": 64.63, "elapsed_time": "0:41:24", "remaining_time": "0:22:40", "throughput": 2655.81, "total_tokens": 6598840} {"current_steps": 24660, "total_steps": 38150, "loss": 0.2671, "lr": 1.6747881583036858e-05, "epoch": 6.463958060288336, "percentage": 64.64, "elapsed_time": "0:41:25", "remaining_time": "0:22:39", "throughput": 2655.84, "total_tokens": 6600088} {"current_steps": 24665, "total_steps": 38150, "loss": 0.2526, "lr": 1.673708620960229e-05, "epoch": 6.465268676277851, "percentage": 64.65, "elapsed_time": "0:41:25", "remaining_time": "0:22:38", "throughput": 2655.87, "total_tokens": 6601320} {"current_steps": 24670, "total_steps": 38150, "loss": 0.1584, "lr": 1.6726292565581298e-05, "epoch": 6.466579292267365, "percentage": 64.67, "elapsed_time": "0:41:25", "remaining_time": "0:22:38", "throughput": 2655.84, "total_tokens": 6602376} {"current_steps": 24675, "total_steps": 38150, "loss": 0.2319, "lr": 1.6715500653232974e-05, "epoch": 6.467889908256881, "percentage": 64.68, "elapsed_time": "0:41:26", "remaining_time": "0:22:37", "throughput": 2656.0, "total_tokens": 6604344} {"current_steps": 24680, "total_steps": 38150, "loss": 0.2927, "lr": 1.670471047481606e-05, "epoch": 6.4692005242463955, "percentage": 64.69, "elapsed_time": "0:41:27", "remaining_time": "0:22:37", "throughput": 2656.16, "total_tokens": 6606088} {"current_steps": 24685, "total_steps": 38150, "loss": 0.1923, "lr": 1.66939220325889e-05, "epoch": 6.470511140235911, "percentage": 64.71, "elapsed_time": "0:41:27", "remaining_time": "0:22:36", "throughput": 2656.25, "total_tokens": 6607560} {"current_steps": 24690, "total_steps": 38150, "loss": 0.2636, "lr": 1.6683135328809512e-05, "epoch": 6.471821756225426, "percentage": 64.72, "elapsed_time": "0:41:27", "remaining_time": "0:22:36", "throughput": 2656.31, "total_tokens": 6608904} {"current_steps": 24695, "total_steps": 38150, "loss": 0.2658, "lr": 1.6672350365735528e-05, "epoch": 6.473132372214941, "percentage": 64.73, "elapsed_time": "0:41:28", "remaining_time": "0:22:35", "throughput": 2656.34, "total_tokens": 6610088} {"current_steps": 24700, "total_steps": 38150, "loss": 0.3331, "lr": 1.6661567145624215e-05, "epoch": 6.474442988204456, "percentage": 64.74, "elapsed_time": "0:41:28", "remaining_time": "0:22:35", "throughput": 2656.44, "total_tokens": 6611640} {"current_steps": 24705, "total_steps": 38150, "loss": 0.242, "lr": 1.6650785670732498e-05, "epoch": 6.475753604193971, "percentage": 64.76, "elapsed_time": "0:41:29", "remaining_time": "0:22:34", "throughput": 2656.5, "total_tokens": 6612968} {"current_steps": 24710, "total_steps": 38150, "loss": 0.1642, "lr": 1.6640005943316914e-05, "epoch": 6.477064220183486, "percentage": 64.77, "elapsed_time": "0:41:29", "remaining_time": "0:22:34", "throughput": 2656.5, "total_tokens": 6614072} {"current_steps": 24715, "total_steps": 38150, "loss": 0.1821, "lr": 1.6629227965633644e-05, "epoch": 6.478374836173002, "percentage": 64.78, "elapsed_time": "0:41:30", "remaining_time": "0:22:33", "throughput": 2656.54, "total_tokens": 6615384} {"current_steps": 24720, "total_steps": 38150, "loss": 0.3327, "lr": 1.6618451739938495e-05, "epoch": 6.479685452162516, "percentage": 64.8, "elapsed_time": "0:41:30", "remaining_time": "0:22:33", "throughput": 2656.64, "total_tokens": 6616904} {"current_steps": 24725, "total_steps": 38150, "loss": 0.5217, "lr": 1.6607677268486914e-05, "epoch": 6.480996068152032, "percentage": 64.81, "elapsed_time": "0:41:31", "remaining_time": "0:22:32", "throughput": 2656.68, "total_tokens": 6618152} {"current_steps": 24730, "total_steps": 38150, "loss": 0.2993, "lr": 1.659690455353398e-05, "epoch": 6.482306684141546, "percentage": 64.82, "elapsed_time": "0:41:31", "remaining_time": "0:22:32", "throughput": 2656.72, "total_tokens": 6619432} {"current_steps": 24735, "total_steps": 38150, "loss": 0.2132, "lr": 1.65861335973344e-05, "epoch": 6.483617300131062, "percentage": 64.84, "elapsed_time": "0:41:32", "remaining_time": "0:22:31", "throughput": 2656.79, "total_tokens": 6620760} {"current_steps": 24740, "total_steps": 38150, "loss": 0.3772, "lr": 1.6575364402142528e-05, "epoch": 6.484927916120577, "percentage": 64.85, "elapsed_time": "0:41:32", "remaining_time": "0:22:30", "throughput": 2656.87, "total_tokens": 6622104} {"current_steps": 24745, "total_steps": 38150, "loss": 0.2464, "lr": 1.6564596970212327e-05, "epoch": 6.486238532110092, "percentage": 64.86, "elapsed_time": "0:41:32", "remaining_time": "0:22:30", "throughput": 2656.87, "total_tokens": 6623224} {"current_steps": 24750, "total_steps": 38150, "loss": 0.2232, "lr": 1.6553831303797405e-05, "epoch": 6.487549148099607, "percentage": 64.88, "elapsed_time": "0:41:33", "remaining_time": "0:22:29", "throughput": 2656.85, "total_tokens": 6624264} {"current_steps": 24755, "total_steps": 38150, "loss": 0.3139, "lr": 1.6543067405150994e-05, "epoch": 6.488859764089122, "percentage": 64.89, "elapsed_time": "0:41:33", "remaining_time": "0:22:29", "throughput": 2656.79, "total_tokens": 6625240} {"current_steps": 24760, "total_steps": 38150, "loss": 0.2612, "lr": 1.653230527652596e-05, "epoch": 6.490170380078637, "percentage": 64.9, "elapsed_time": "0:41:34", "remaining_time": "0:22:28", "throughput": 2656.83, "total_tokens": 6626552} {"current_steps": 24765, "total_steps": 38150, "loss": 0.3552, "lr": 1.6521544920174803e-05, "epoch": 6.491480996068152, "percentage": 64.91, "elapsed_time": "0:41:34", "remaining_time": "0:22:28", "throughput": 2656.86, "total_tokens": 6627768} {"current_steps": 24770, "total_steps": 38150, "loss": 0.2168, "lr": 1.6510786338349645e-05, "epoch": 6.492791612057667, "percentage": 64.93, "elapsed_time": "0:41:35", "remaining_time": "0:22:27", "throughput": 2656.97, "total_tokens": 6629288} {"current_steps": 24775, "total_steps": 38150, "loss": 0.3832, "lr": 1.6500029533302247e-05, "epoch": 6.494102228047182, "percentage": 64.94, "elapsed_time": "0:41:35", "remaining_time": "0:22:27", "throughput": 2656.93, "total_tokens": 6630296} {"current_steps": 24780, "total_steps": 38150, "loss": 0.3007, "lr": 1.648927450728397e-05, "epoch": 6.495412844036697, "percentage": 64.95, "elapsed_time": "0:41:35", "remaining_time": "0:22:26", "throughput": 2656.91, "total_tokens": 6631400} {"current_steps": 24785, "total_steps": 38150, "loss": 0.2326, "lr": 1.6478521262545837e-05, "epoch": 6.496723460026212, "percentage": 64.97, "elapsed_time": "0:41:36", "remaining_time": "0:22:26", "throughput": 2656.87, "total_tokens": 6632424} {"current_steps": 24790, "total_steps": 38150, "loss": 0.1606, "lr": 1.6467769801338478e-05, "epoch": 6.498034076015728, "percentage": 64.98, "elapsed_time": "0:41:36", "remaining_time": "0:22:25", "throughput": 2657.01, "total_tokens": 6634120} {"current_steps": 24795, "total_steps": 38150, "loss": 0.227, "lr": 1.645702012591216e-05, "epoch": 6.499344692005242, "percentage": 64.99, "elapsed_time": "0:41:37", "remaining_time": "0:22:25", "throughput": 2657.02, "total_tokens": 6635256} {"current_steps": 24800, "total_steps": 38150, "loss": 0.2133, "lr": 1.644627223851677e-05, "epoch": 6.500655307994758, "percentage": 65.01, "elapsed_time": "0:41:37", "remaining_time": "0:22:24", "throughput": 2657.04, "total_tokens": 6636552} {"current_steps": 24804, "total_steps": 38150, "eval_loss": 0.637935996055603, "epoch": 6.50170380078637, "percentage": 65.02, "elapsed_time": "0:41:54", "remaining_time": "0:22:33", "throughput": 2639.34, "total_tokens": 6637864} {"current_steps": 24805, "total_steps": 38150, "loss": 0.2731, "lr": 1.643552614140182e-05, "epoch": 6.501965923984272, "percentage": 65.02, "elapsed_time": "0:41:56", "remaining_time": "0:22:33", "throughput": 2637.78, "total_tokens": 6638008} {"current_steps": 24810, "total_steps": 38150, "loss": 0.2276, "lr": 1.6424781836816443e-05, "epoch": 6.503276539973788, "percentage": 65.03, "elapsed_time": "0:41:56", "remaining_time": "0:22:33", "throughput": 2637.82, "total_tokens": 6639304} {"current_steps": 24815, "total_steps": 38150, "loss": 0.2024, "lr": 1.641403932700941e-05, "epoch": 6.504587155963303, "percentage": 65.05, "elapsed_time": "0:41:57", "remaining_time": "0:22:32", "throughput": 2637.92, "total_tokens": 6640776} {"current_steps": 24820, "total_steps": 38150, "loss": 0.2193, "lr": 1.6403298614229117e-05, "epoch": 6.505897771952818, "percentage": 65.06, "elapsed_time": "0:41:57", "remaining_time": "0:22:32", "throughput": 2637.96, "total_tokens": 6642024} {"current_steps": 24825, "total_steps": 38150, "loss": 0.2761, "lr": 1.639255970072357e-05, "epoch": 6.507208387942333, "percentage": 65.07, "elapsed_time": "0:41:58", "remaining_time": "0:22:31", "throughput": 2637.98, "total_tokens": 6643288} {"current_steps": 24830, "total_steps": 38150, "loss": 0.2533, "lr": 1.6381822588740404e-05, "epoch": 6.508519003931848, "percentage": 65.09, "elapsed_time": "0:41:58", "remaining_time": "0:22:31", "throughput": 2637.92, "total_tokens": 6644232} {"current_steps": 24835, "total_steps": 38150, "loss": 0.162, "lr": 1.6371087280526888e-05, "epoch": 6.509829619921363, "percentage": 65.1, "elapsed_time": "0:41:59", "remaining_time": "0:22:30", "throughput": 2637.93, "total_tokens": 6645496} {"current_steps": 24840, "total_steps": 38150, "loss": 0.2406, "lr": 1.6360353778329883e-05, "epoch": 6.511140235910878, "percentage": 65.11, "elapsed_time": "0:41:59", "remaining_time": "0:22:30", "throughput": 2638.05, "total_tokens": 6647128} {"current_steps": 24845, "total_steps": 38150, "loss": 0.2655, "lr": 1.6349622084395903e-05, "epoch": 6.512450851900393, "percentage": 65.12, "elapsed_time": "0:42:00", "remaining_time": "0:22:29", "throughput": 2637.98, "total_tokens": 6648056} {"current_steps": 24850, "total_steps": 38150, "loss": 0.3267, "lr": 1.6338892200971078e-05, "epoch": 6.513761467889909, "percentage": 65.14, "elapsed_time": "0:42:00", "remaining_time": "0:22:29", "throughput": 2637.97, "total_tokens": 6649176} {"current_steps": 24855, "total_steps": 38150, "loss": 0.2351, "lr": 1.6328164130301157e-05, "epoch": 6.515072083879423, "percentage": 65.15, "elapsed_time": "0:42:01", "remaining_time": "0:22:28", "throughput": 2638.03, "total_tokens": 6650536} {"current_steps": 24860, "total_steps": 38150, "loss": 0.2694, "lr": 1.631743787463149e-05, "epoch": 6.516382699868938, "percentage": 65.16, "elapsed_time": "0:42:01", "remaining_time": "0:22:27", "throughput": 2638.13, "total_tokens": 6652072} {"current_steps": 24865, "total_steps": 38150, "loss": 0.1397, "lr": 1.630671343620708e-05, "epoch": 6.517693315858454, "percentage": 65.18, "elapsed_time": "0:42:01", "remaining_time": "0:22:27", "throughput": 2638.13, "total_tokens": 6653240} {"current_steps": 24870, "total_steps": 38150, "loss": 0.2653, "lr": 1.6295990817272516e-05, "epoch": 6.519003931847968, "percentage": 65.19, "elapsed_time": "0:42:02", "remaining_time": "0:22:26", "throughput": 2638.16, "total_tokens": 6654440} {"current_steps": 24875, "total_steps": 38150, "loss": 0.209, "lr": 1.6285270020072044e-05, "epoch": 6.520314547837484, "percentage": 65.2, "elapsed_time": "0:42:02", "remaining_time": "0:22:26", "throughput": 2638.18, "total_tokens": 6655608} {"current_steps": 24880, "total_steps": 38150, "loss": 0.1293, "lr": 1.6274551046849495e-05, "epoch": 6.521625163826998, "percentage": 65.22, "elapsed_time": "0:42:03", "remaining_time": "0:22:25", "throughput": 2638.17, "total_tokens": 6656712} {"current_steps": 24885, "total_steps": 38150, "loss": 0.2684, "lr": 1.6263833899848337e-05, "epoch": 6.522935779816514, "percentage": 65.23, "elapsed_time": "0:42:03", "remaining_time": "0:22:25", "throughput": 2638.42, "total_tokens": 6658936} {"current_steps": 24890, "total_steps": 38150, "loss": 0.3079, "lr": 1.625311858131165e-05, "epoch": 6.524246395806029, "percentage": 65.24, "elapsed_time": "0:42:04", "remaining_time": "0:22:24", "throughput": 2638.48, "total_tokens": 6660328} {"current_steps": 24895, "total_steps": 38150, "loss": 0.2818, "lr": 1.6242405093482133e-05, "epoch": 6.525557011795544, "percentage": 65.26, "elapsed_time": "0:42:04", "remaining_time": "0:22:24", "throughput": 2638.45, "total_tokens": 6661352} {"current_steps": 24900, "total_steps": 38150, "loss": 0.3324, "lr": 1.6231693438602097e-05, "epoch": 6.526867627785059, "percentage": 65.27, "elapsed_time": "0:42:05", "remaining_time": "0:22:23", "throughput": 2638.49, "total_tokens": 6662600} {"current_steps": 24905, "total_steps": 38150, "loss": 0.2879, "lr": 1.6220983618913472e-05, "epoch": 6.528178243774574, "percentage": 65.28, "elapsed_time": "0:42:05", "remaining_time": "0:22:23", "throughput": 2638.47, "total_tokens": 6663656} {"current_steps": 24910, "total_steps": 38150, "loss": 0.2283, "lr": 1.6210275636657805e-05, "epoch": 6.529488859764089, "percentage": 65.29, "elapsed_time": "0:42:06", "remaining_time": "0:22:22", "throughput": 2638.45, "total_tokens": 6664744} {"current_steps": 24915, "total_steps": 38150, "loss": 0.2481, "lr": 1.6199569494076265e-05, "epoch": 6.5307994757536045, "percentage": 65.31, "elapsed_time": "0:42:06", "remaining_time": "0:22:22", "throughput": 2638.51, "total_tokens": 6666104} {"current_steps": 24920, "total_steps": 38150, "loss": 0.2656, "lr": 1.618886519340962e-05, "epoch": 6.532110091743119, "percentage": 65.32, "elapsed_time": "0:42:06", "remaining_time": "0:22:21", "throughput": 2638.55, "total_tokens": 6667352} {"current_steps": 24925, "total_steps": 38150, "loss": 0.3319, "lr": 1.6178162736898264e-05, "epoch": 6.533420707732635, "percentage": 65.33, "elapsed_time": "0:42:07", "remaining_time": "0:22:21", "throughput": 2638.69, "total_tokens": 6669080} {"current_steps": 24930, "total_steps": 38150, "loss": 0.3535, "lr": 1.61674621267822e-05, "epoch": 6.534731323722149, "percentage": 65.35, "elapsed_time": "0:42:07", "remaining_time": "0:22:20", "throughput": 2638.81, "total_tokens": 6670712} {"current_steps": 24935, "total_steps": 38150, "loss": 0.2354, "lr": 1.6156763365301054e-05, "epoch": 6.536041939711664, "percentage": 65.36, "elapsed_time": "0:42:08", "remaining_time": "0:22:19", "throughput": 2638.85, "total_tokens": 6671944} {"current_steps": 24940, "total_steps": 38150, "loss": 0.2616, "lr": 1.614606645469406e-05, "epoch": 6.53735255570118, "percentage": 65.37, "elapsed_time": "0:42:08", "remaining_time": "0:22:19", "throughput": 2638.86, "total_tokens": 6673080} {"current_steps": 24945, "total_steps": 38150, "loss": 0.2947, "lr": 1.6135371397200057e-05, "epoch": 6.538663171690695, "percentage": 65.39, "elapsed_time": "0:42:09", "remaining_time": "0:22:18", "throughput": 2638.82, "total_tokens": 6674056} {"current_steps": 24950, "total_steps": 38150, "loss": 0.2196, "lr": 1.6124678195057507e-05, "epoch": 6.53997378768021, "percentage": 65.4, "elapsed_time": "0:42:09", "remaining_time": "0:22:18", "throughput": 2638.87, "total_tokens": 6675368} {"current_steps": 24955, "total_steps": 38150, "loss": 0.3879, "lr": 1.6113986850504475e-05, "epoch": 6.541284403669724, "percentage": 65.41, "elapsed_time": "0:42:10", "remaining_time": "0:22:17", "throughput": 2638.94, "total_tokens": 6676696} {"current_steps": 24960, "total_steps": 38150, "loss": 0.3112, "lr": 1.6103297365778636e-05, "epoch": 6.54259501965924, "percentage": 65.43, "elapsed_time": "0:42:10", "remaining_time": "0:22:17", "throughput": 2639.01, "total_tokens": 6678136} {"current_steps": 24965, "total_steps": 38150, "loss": 0.2855, "lr": 1.609260974311729e-05, "epoch": 6.543905635648755, "percentage": 65.44, "elapsed_time": "0:42:11", "remaining_time": "0:22:16", "throughput": 2639.11, "total_tokens": 6679656} {"current_steps": 24970, "total_steps": 38150, "loss": 0.2186, "lr": 1.6081923984757332e-05, "epoch": 6.54521625163827, "percentage": 65.45, "elapsed_time": "0:42:11", "remaining_time": "0:22:16", "throughput": 2639.14, "total_tokens": 6680856} {"current_steps": 24975, "total_steps": 38150, "loss": 0.2262, "lr": 1.607124009293528e-05, "epoch": 6.546526867627785, "percentage": 65.47, "elapsed_time": "0:42:11", "remaining_time": "0:22:15", "throughput": 2639.22, "total_tokens": 6682296} {"current_steps": 24980, "total_steps": 38150, "loss": 0.223, "lr": 1.6060558069887244e-05, "epoch": 6.5478374836173, "percentage": 65.48, "elapsed_time": "0:42:12", "remaining_time": "0:22:15", "throughput": 2639.29, "total_tokens": 6683624} {"current_steps": 24985, "total_steps": 38150, "loss": 0.282, "lr": 1.6049877917848948e-05, "epoch": 6.549148099606815, "percentage": 65.49, "elapsed_time": "0:42:12", "remaining_time": "0:22:14", "throughput": 2639.39, "total_tokens": 6685160} {"current_steps": 24990, "total_steps": 38150, "loss": 0.3244, "lr": 1.6039199639055755e-05, "epoch": 6.5504587155963305, "percentage": 65.5, "elapsed_time": "0:42:13", "remaining_time": "0:22:14", "throughput": 2639.71, "total_tokens": 6687512} {"current_steps": 24995, "total_steps": 38150, "loss": 0.3361, "lr": 1.602852323574259e-05, "epoch": 6.551769331585845, "percentage": 65.52, "elapsed_time": "0:42:13", "remaining_time": "0:22:13", "throughput": 2639.88, "total_tokens": 6689320} {"current_steps": 25000, "total_steps": 38150, "loss": 0.1413, "lr": 1.6017848710144006e-05, "epoch": 6.553079947575361, "percentage": 65.53, "elapsed_time": "0:42:14", "remaining_time": "0:22:13", "throughput": 2639.99, "total_tokens": 6690920} {"current_steps": 25005, "total_steps": 38150, "loss": 0.2531, "lr": 1.600717606449417e-05, "epoch": 6.554390563564875, "percentage": 65.54, "elapsed_time": "0:42:14", "remaining_time": "0:22:12", "throughput": 2640.01, "total_tokens": 6692088} {"current_steps": 25010, "total_steps": 38150, "loss": 0.2635, "lr": 1.5996505301026848e-05, "epoch": 6.555701179554391, "percentage": 65.56, "elapsed_time": "0:42:15", "remaining_time": "0:22:12", "throughput": 2640.04, "total_tokens": 6693288} {"current_steps": 25015, "total_steps": 38150, "loss": 0.2033, "lr": 1.598583642197541e-05, "epoch": 6.557011795543906, "percentage": 65.57, "elapsed_time": "0:42:15", "remaining_time": "0:22:11", "throughput": 2640.08, "total_tokens": 6694632} {"current_steps": 25020, "total_steps": 38150, "loss": 0.0767, "lr": 1.5975169429572828e-05, "epoch": 6.558322411533421, "percentage": 65.58, "elapsed_time": "0:42:16", "remaining_time": "0:22:10", "throughput": 2640.02, "total_tokens": 6695576} {"current_steps": 25025, "total_steps": 38150, "loss": 0.2238, "lr": 1.5964504326051693e-05, "epoch": 6.559633027522936, "percentage": 65.6, "elapsed_time": "0:42:16", "remaining_time": "0:22:10", "throughput": 2639.97, "total_tokens": 6696536} {"current_steps": 25030, "total_steps": 38150, "loss": 0.1756, "lr": 1.595384111364419e-05, "epoch": 6.56094364351245, "percentage": 65.61, "elapsed_time": "0:42:17", "remaining_time": "0:22:09", "throughput": 2640.05, "total_tokens": 6697960} {"current_steps": 25035, "total_steps": 38150, "loss": 0.2766, "lr": 1.594317979458212e-05, "epoch": 6.562254259501966, "percentage": 65.62, "elapsed_time": "0:42:17", "remaining_time": "0:22:09", "throughput": 2640.19, "total_tokens": 6699560} {"current_steps": 25040, "total_steps": 38150, "loss": 0.1605, "lr": 1.593252037109686e-05, "epoch": 6.5635648754914815, "percentage": 65.64, "elapsed_time": "0:42:17", "remaining_time": "0:22:08", "throughput": 2640.18, "total_tokens": 6700632} {"current_steps": 25045, "total_steps": 38150, "loss": 0.259, "lr": 1.5921862845419417e-05, "epoch": 6.564875491480996, "percentage": 65.65, "elapsed_time": "0:42:18", "remaining_time": "0:22:08", "throughput": 2640.3, "total_tokens": 6702312} {"current_steps": 25050, "total_steps": 38150, "loss": 0.2792, "lr": 1.5911207219780398e-05, "epoch": 6.566186107470511, "percentage": 65.66, "elapsed_time": "0:42:18", "remaining_time": "0:22:07", "throughput": 2640.4, "total_tokens": 6703816} {"current_steps": 25055, "total_steps": 38150, "loss": 0.193, "lr": 1.5900553496410004e-05, "epoch": 6.567496723460026, "percentage": 65.67, "elapsed_time": "0:42:19", "remaining_time": "0:22:07", "throughput": 2640.5, "total_tokens": 6705256} {"current_steps": 25060, "total_steps": 38150, "loss": 0.257, "lr": 1.5889901677538037e-05, "epoch": 6.568807339449541, "percentage": 65.69, "elapsed_time": "0:42:19", "remaining_time": "0:22:06", "throughput": 2640.5, "total_tokens": 6706408} {"current_steps": 25065, "total_steps": 38150, "loss": 0.293, "lr": 1.5879251765393914e-05, "epoch": 6.5701179554390565, "percentage": 65.7, "elapsed_time": "0:42:20", "remaining_time": "0:22:06", "throughput": 2640.48, "total_tokens": 6707448} {"current_steps": 25070, "total_steps": 38150, "loss": 0.2617, "lr": 1.5868603762206637e-05, "epoch": 6.571428571428571, "percentage": 65.71, "elapsed_time": "0:42:20", "remaining_time": "0:22:05", "throughput": 2640.48, "total_tokens": 6708648} {"current_steps": 25075, "total_steps": 38150, "loss": 0.2393, "lr": 1.5857957670204816e-05, "epoch": 6.572739187418087, "percentage": 65.73, "elapsed_time": "0:42:21", "remaining_time": "0:22:05", "throughput": 2640.52, "total_tokens": 6709928} {"current_steps": 25080, "total_steps": 38150, "loss": 0.2442, "lr": 1.5847313491616654e-05, "epoch": 6.574049803407601, "percentage": 65.74, "elapsed_time": "0:42:21", "remaining_time": "0:22:04", "throughput": 2640.68, "total_tokens": 6711816} {"current_steps": 25085, "total_steps": 38150, "loss": 0.2804, "lr": 1.5836671228669962e-05, "epoch": 6.575360419397117, "percentage": 65.75, "elapsed_time": "0:42:22", "remaining_time": "0:22:04", "throughput": 2640.72, "total_tokens": 6713128} {"current_steps": 25090, "total_steps": 38150, "loss": 0.1523, "lr": 1.582603088359216e-05, "epoch": 6.576671035386632, "percentage": 65.77, "elapsed_time": "0:42:22", "remaining_time": "0:22:03", "throughput": 2640.85, "total_tokens": 6714776} {"current_steps": 25095, "total_steps": 38150, "loss": 0.2949, "lr": 1.581539245861023e-05, "epoch": 6.577981651376147, "percentage": 65.78, "elapsed_time": "0:42:23", "remaining_time": "0:22:02", "throughput": 2640.77, "total_tokens": 6715672} {"current_steps": 25100, "total_steps": 38150, "loss": 0.236, "lr": 1.5804755955950785e-05, "epoch": 6.579292267365662, "percentage": 65.79, "elapsed_time": "0:42:23", "remaining_time": "0:22:02", "throughput": 2640.82, "total_tokens": 6717016} {"current_steps": 25105, "total_steps": 38150, "loss": 0.1588, "lr": 1.579412137784004e-05, "epoch": 6.580602883355177, "percentage": 65.81, "elapsed_time": "0:42:23", "remaining_time": "0:22:01", "throughput": 2640.81, "total_tokens": 6718104} {"current_steps": 25110, "total_steps": 38150, "loss": 0.1718, "lr": 1.578348872650378e-05, "epoch": 6.581913499344692, "percentage": 65.82, "elapsed_time": "0:42:24", "remaining_time": "0:22:01", "throughput": 2640.76, "total_tokens": 6719064} {"current_steps": 25115, "total_steps": 38150, "loss": 0.3696, "lr": 1.5772858004167407e-05, "epoch": 6.5832241153342075, "percentage": 65.83, "elapsed_time": "0:42:24", "remaining_time": "0:22:00", "throughput": 2640.8, "total_tokens": 6720376} {"current_steps": 25120, "total_steps": 38150, "loss": 0.2121, "lr": 1.5762229213055914e-05, "epoch": 6.584534731323722, "percentage": 65.85, "elapsed_time": "0:42:25", "remaining_time": "0:22:00", "throughput": 2640.87, "total_tokens": 6721784} {"current_steps": 25125, "total_steps": 38150, "loss": 0.2051, "lr": 1.5751602355393878e-05, "epoch": 6.585845347313237, "percentage": 65.86, "elapsed_time": "0:42:25", "remaining_time": "0:21:59", "throughput": 2640.94, "total_tokens": 6723192} {"current_steps": 25130, "total_steps": 38150, "loss": 0.1762, "lr": 1.5740977433405496e-05, "epoch": 6.587155963302752, "percentage": 65.87, "elapsed_time": "0:42:26", "remaining_time": "0:21:59", "throughput": 2640.94, "total_tokens": 6724392} {"current_steps": 25135, "total_steps": 38150, "loss": 0.2599, "lr": 1.5730354449314534e-05, "epoch": 6.588466579292267, "percentage": 65.88, "elapsed_time": "0:42:26", "remaining_time": "0:21:58", "throughput": 2641.0, "total_tokens": 6725672} {"current_steps": 25140, "total_steps": 38150, "loss": 0.2129, "lr": 1.5719733405344373e-05, "epoch": 6.5897771952817825, "percentage": 65.9, "elapsed_time": "0:42:27", "remaining_time": "0:21:58", "throughput": 2641.14, "total_tokens": 6727288} {"current_steps": 25145, "total_steps": 38150, "loss": 0.3603, "lr": 1.570911430371797e-05, "epoch": 6.591087811271297, "percentage": 65.91, "elapsed_time": "0:42:27", "remaining_time": "0:21:57", "throughput": 2641.25, "total_tokens": 6728744} {"current_steps": 25150, "total_steps": 38150, "loss": 0.3268, "lr": 1.5698497146657897e-05, "epoch": 6.592398427260813, "percentage": 65.92, "elapsed_time": "0:42:27", "remaining_time": "0:21:57", "throughput": 2641.31, "total_tokens": 6730040} {"current_steps": 25155, "total_steps": 38150, "loss": 0.3123, "lr": 1.5687881936386294e-05, "epoch": 6.593709043250327, "percentage": 65.94, "elapsed_time": "0:42:28", "remaining_time": "0:21:56", "throughput": 2641.42, "total_tokens": 6731592} {"current_steps": 25160, "total_steps": 38150, "loss": 0.3073, "lr": 1.5677268675124902e-05, "epoch": 6.595019659239843, "percentage": 65.95, "elapsed_time": "0:42:28", "remaining_time": "0:21:56", "throughput": 2641.52, "total_tokens": 6733064} {"current_steps": 25165, "total_steps": 38150, "loss": 0.1348, "lr": 1.5666657365095083e-05, "epoch": 6.5963302752293576, "percentage": 65.96, "elapsed_time": "0:42:29", "remaining_time": "0:21:55", "throughput": 2641.52, "total_tokens": 6734216} {"current_steps": 25170, "total_steps": 38150, "loss": 0.1406, "lr": 1.565604800851774e-05, "epoch": 6.597640891218873, "percentage": 65.98, "elapsed_time": "0:42:29", "remaining_time": "0:21:54", "throughput": 2641.49, "total_tokens": 6735224} {"current_steps": 25175, "total_steps": 38150, "loss": 0.2198, "lr": 1.5645440607613413e-05, "epoch": 6.598951507208388, "percentage": 65.99, "elapsed_time": "0:42:30", "remaining_time": "0:21:54", "throughput": 2641.57, "total_tokens": 6736728} {"current_steps": 25180, "total_steps": 38150, "loss": 0.2471, "lr": 1.56348351646022e-05, "epoch": 6.600262123197903, "percentage": 66.0, "elapsed_time": "0:42:30", "remaining_time": "0:21:53", "throughput": 2641.53, "total_tokens": 6737720} {"current_steps": 25185, "total_steps": 38150, "loss": 0.2715, "lr": 1.5624231681703812e-05, "epoch": 6.601572739187418, "percentage": 66.02, "elapsed_time": "0:42:31", "remaining_time": "0:21:53", "throughput": 2641.59, "total_tokens": 6739016} {"current_steps": 25190, "total_steps": 38150, "loss": 0.1881, "lr": 1.5613630161137523e-05, "epoch": 6.6028833551769335, "percentage": 66.03, "elapsed_time": "0:42:31", "remaining_time": "0:21:52", "throughput": 2641.62, "total_tokens": 6740328} {"current_steps": 25195, "total_steps": 38150, "loss": 0.1773, "lr": 1.5603030605122226e-05, "epoch": 6.604193971166448, "percentage": 66.04, "elapsed_time": "0:42:32", "remaining_time": "0:21:52", "throughput": 2641.6, "total_tokens": 6741384} {"current_steps": 25200, "total_steps": 38150, "loss": 0.3004, "lr": 1.5592433015876383e-05, "epoch": 6.605504587155964, "percentage": 66.06, "elapsed_time": "0:42:32", "remaining_time": "0:21:51", "throughput": 2641.65, "total_tokens": 6742744} {"current_steps": 25205, "total_steps": 38150, "loss": 0.4181, "lr": 1.558183739561806e-05, "epoch": 6.606815203145478, "percentage": 66.07, "elapsed_time": "0:42:33", "remaining_time": "0:21:51", "throughput": 2642.09, "total_tokens": 6746088} {"current_steps": 25210, "total_steps": 38150, "loss": 0.1986, "lr": 1.55712437465649e-05, "epoch": 6.608125819134994, "percentage": 66.08, "elapsed_time": "0:42:33", "remaining_time": "0:21:50", "throughput": 2642.23, "total_tokens": 6747784} {"current_steps": 25215, "total_steps": 38150, "loss": 0.4114, "lr": 1.5560652070934117e-05, "epoch": 6.6094364351245085, "percentage": 66.09, "elapsed_time": "0:42:34", "remaining_time": "0:21:50", "throughput": 2642.22, "total_tokens": 6748920} {"current_steps": 25220, "total_steps": 38150, "loss": 0.2538, "lr": 1.5550062370942556e-05, "epoch": 6.610747051114023, "percentage": 66.11, "elapsed_time": "0:42:34", "remaining_time": "0:21:49", "throughput": 2642.35, "total_tokens": 6750584} {"current_steps": 25225, "total_steps": 38150, "loss": 0.2177, "lr": 1.553947464880662e-05, "epoch": 6.612057667103539, "percentage": 66.12, "elapsed_time": "0:42:35", "remaining_time": "0:21:49", "throughput": 2642.47, "total_tokens": 6752184} {"current_steps": 25230, "total_steps": 38150, "loss": 0.4218, "lr": 1.5528888906742285e-05, "epoch": 6.613368283093053, "percentage": 66.13, "elapsed_time": "0:42:35", "remaining_time": "0:21:48", "throughput": 2642.5, "total_tokens": 6753480} {"current_steps": 25235, "total_steps": 38150, "loss": 0.2771, "lr": 1.5518305146965133e-05, "epoch": 6.614678899082569, "percentage": 66.15, "elapsed_time": "0:42:36", "remaining_time": "0:21:48", "throughput": 2642.61, "total_tokens": 6755032} {"current_steps": 25240, "total_steps": 38150, "loss": 0.15, "lr": 1.5507723371690336e-05, "epoch": 6.6159895150720835, "percentage": 66.16, "elapsed_time": "0:42:36", "remaining_time": "0:21:47", "throughput": 2642.75, "total_tokens": 6756680} {"current_steps": 25245, "total_steps": 38150, "loss": 0.2448, "lr": 1.5497143583132638e-05, "epoch": 6.617300131061599, "percentage": 66.17, "elapsed_time": "0:42:37", "remaining_time": "0:21:47", "throughput": 2642.75, "total_tokens": 6757896} {"current_steps": 25250, "total_steps": 38150, "loss": 0.319, "lr": 1.5486565783506367e-05, "epoch": 6.618610747051114, "percentage": 66.19, "elapsed_time": "0:42:37", "remaining_time": "0:21:46", "throughput": 2642.94, "total_tokens": 6759800} {"current_steps": 25255, "total_steps": 38150, "loss": 0.4445, "lr": 1.547598997502544e-05, "epoch": 6.619921363040629, "percentage": 66.2, "elapsed_time": "0:42:38", "remaining_time": "0:21:46", "throughput": 2643.0, "total_tokens": 6761096} {"current_steps": 25260, "total_steps": 38150, "loss": 0.2197, "lr": 1.546541615990335e-05, "epoch": 6.621231979030144, "percentage": 66.21, "elapsed_time": "0:42:38", "remaining_time": "0:21:45", "throughput": 2643.03, "total_tokens": 6762328} {"current_steps": 25265, "total_steps": 38150, "loss": 0.2157, "lr": 1.545484434035319e-05, "epoch": 6.6225425950196595, "percentage": 66.23, "elapsed_time": "0:42:38", "remaining_time": "0:21:45", "throughput": 2643.05, "total_tokens": 6763496} {"current_steps": 25270, "total_steps": 38150, "loss": 0.3056, "lr": 1.5444274518587617e-05, "epoch": 6.623853211009174, "percentage": 66.24, "elapsed_time": "0:42:39", "remaining_time": "0:21:44", "throughput": 2643.14, "total_tokens": 6764904} {"current_steps": 25275, "total_steps": 38150, "loss": 0.1993, "lr": 1.543370669681886e-05, "epoch": 6.62516382699869, "percentage": 66.25, "elapsed_time": "0:42:39", "remaining_time": "0:21:43", "throughput": 2643.19, "total_tokens": 6766168} {"current_steps": 25280, "total_steps": 38150, "loss": 0.2854, "lr": 1.5423140877258784e-05, "epoch": 6.626474442988204, "percentage": 66.26, "elapsed_time": "0:42:40", "remaining_time": "0:21:43", "throughput": 2643.18, "total_tokens": 6767272} {"current_steps": 25285, "total_steps": 38150, "loss": 0.3645, "lr": 1.5412577062118763e-05, "epoch": 6.62778505897772, "percentage": 66.28, "elapsed_time": "0:42:40", "remaining_time": "0:21:42", "throughput": 2643.21, "total_tokens": 6768456} {"current_steps": 25290, "total_steps": 38150, "loss": 0.238, "lr": 1.5402015253609796e-05, "epoch": 6.6290956749672345, "percentage": 66.29, "elapsed_time": "0:42:41", "remaining_time": "0:21:42", "throughput": 2643.27, "total_tokens": 6769800} {"current_steps": 25295, "total_steps": 38150, "loss": 0.1837, "lr": 1.539145545394246e-05, "epoch": 6.63040629095675, "percentage": 66.3, "elapsed_time": "0:42:41", "remaining_time": "0:21:41", "throughput": 2643.31, "total_tokens": 6771112} {"current_steps": 25300, "total_steps": 38150, "loss": 0.307, "lr": 1.538089766532689e-05, "epoch": 6.631716906946265, "percentage": 66.32, "elapsed_time": "0:42:42", "remaining_time": "0:21:41", "throughput": 2643.47, "total_tokens": 6772840} {"current_steps": 25305, "total_steps": 38150, "loss": 0.1975, "lr": 1.537034188997282e-05, "epoch": 6.63302752293578, "percentage": 66.33, "elapsed_time": "0:42:42", "remaining_time": "0:21:40", "throughput": 2643.46, "total_tokens": 6774008} {"current_steps": 25310, "total_steps": 38150, "loss": 0.3276, "lr": 1.5359788130089558e-05, "epoch": 6.634338138925295, "percentage": 66.34, "elapsed_time": "0:42:42", "remaining_time": "0:21:40", "throughput": 2643.52, "total_tokens": 6775336} {"current_steps": 25315, "total_steps": 38150, "loss": 0.2482, "lr": 1.5349236387885976e-05, "epoch": 6.6356487549148095, "percentage": 66.36, "elapsed_time": "0:42:43", "remaining_time": "0:21:39", "throughput": 2643.63, "total_tokens": 6776872} {"current_steps": 25320, "total_steps": 38150, "loss": 0.2453, "lr": 1.5338686665570546e-05, "epoch": 6.636959370904325, "percentage": 66.37, "elapsed_time": "0:42:43", "remaining_time": "0:21:39", "throughput": 2643.65, "total_tokens": 6778040} {"current_steps": 25325, "total_steps": 38150, "loss": 0.2636, "lr": 1.5328138965351307e-05, "epoch": 6.63826998689384, "percentage": 66.38, "elapsed_time": "0:42:44", "remaining_time": "0:21:38", "throughput": 2643.82, "total_tokens": 6779864} {"current_steps": 25330, "total_steps": 38150, "loss": 0.2961, "lr": 1.5317593289435855e-05, "epoch": 6.639580602883355, "percentage": 66.4, "elapsed_time": "0:42:44", "remaining_time": "0:21:38", "throughput": 2644.03, "total_tokens": 6781800} {"current_steps": 25335, "total_steps": 38150, "loss": 0.3089, "lr": 1.530704964003141e-05, "epoch": 6.64089121887287, "percentage": 66.41, "elapsed_time": "0:42:45", "remaining_time": "0:21:37", "throughput": 2644.1, "total_tokens": 6783208} {"current_steps": 25340, "total_steps": 38150, "loss": 0.2658, "lr": 1.529650801934473e-05, "epoch": 6.6422018348623855, "percentage": 66.42, "elapsed_time": "0:42:45", "remaining_time": "0:21:37", "throughput": 2644.17, "total_tokens": 6784664} {"current_steps": 25345, "total_steps": 38150, "loss": 0.2061, "lr": 1.5285968429582153e-05, "epoch": 6.6435124508519, "percentage": 66.44, "elapsed_time": "0:42:46", "remaining_time": "0:21:36", "throughput": 2644.26, "total_tokens": 6786056} {"current_steps": 25350, "total_steps": 38150, "loss": 0.3251, "lr": 1.52754308729496e-05, "epoch": 6.644823066841416, "percentage": 66.45, "elapsed_time": "0:42:46", "remaining_time": "0:21:36", "throughput": 2644.4, "total_tokens": 6787656} {"current_steps": 25355, "total_steps": 38150, "loss": 0.3597, "lr": 1.5264895351652555e-05, "epoch": 6.64613368283093, "percentage": 66.46, "elapsed_time": "0:42:47", "remaining_time": "0:21:35", "throughput": 2644.38, "total_tokens": 6788728} {"current_steps": 25360, "total_steps": 38150, "loss": 0.151, "lr": 1.52543618678961e-05, "epoch": 6.647444298820446, "percentage": 66.47, "elapsed_time": "0:42:47", "remaining_time": "0:21:34", "throughput": 2644.38, "total_tokens": 6789832} {"current_steps": 25365, "total_steps": 38150, "loss": 0.1814, "lr": 1.5243830423884867e-05, "epoch": 6.6487549148099605, "percentage": 66.49, "elapsed_time": "0:42:48", "remaining_time": "0:21:34", "throughput": 2644.49, "total_tokens": 6791368} {"current_steps": 25370, "total_steps": 38150, "loss": 0.3249, "lr": 1.5233301021823065e-05, "epoch": 6.650065530799476, "percentage": 66.5, "elapsed_time": "0:42:48", "remaining_time": "0:21:33", "throughput": 2644.54, "total_tokens": 6792648} {"current_steps": 25375, "total_steps": 38150, "loss": 0.1692, "lr": 1.5222773663914486e-05, "epoch": 6.651376146788991, "percentage": 66.51, "elapsed_time": "0:42:49", "remaining_time": "0:21:33", "throughput": 2644.64, "total_tokens": 6794120} {"current_steps": 25380, "total_steps": 38150, "loss": 0.3532, "lr": 1.5212248352362482e-05, "epoch": 6.652686762778506, "percentage": 66.53, "elapsed_time": "0:42:49", "remaining_time": "0:21:32", "throughput": 2644.64, "total_tokens": 6795240} {"current_steps": 25385, "total_steps": 38150, "loss": 0.1986, "lr": 1.5201725089369991e-05, "epoch": 6.653997378768021, "percentage": 66.54, "elapsed_time": "0:42:49", "remaining_time": "0:21:32", "throughput": 2644.7, "total_tokens": 6796632} {"current_steps": 25390, "total_steps": 38150, "loss": 0.1829, "lr": 1.5191203877139498e-05, "epoch": 6.655307994757536, "percentage": 66.55, "elapsed_time": "0:42:50", "remaining_time": "0:21:31", "throughput": 2644.8, "total_tokens": 6798120} {"current_steps": 25395, "total_steps": 38150, "loss": 0.3465, "lr": 1.5180684717873089e-05, "epoch": 6.656618610747051, "percentage": 66.57, "elapsed_time": "0:42:50", "remaining_time": "0:21:31", "throughput": 2644.94, "total_tokens": 6799784} {"current_steps": 25400, "total_steps": 38150, "loss": 0.2431, "lr": 1.5170167613772412e-05, "epoch": 6.657929226736567, "percentage": 66.58, "elapsed_time": "0:42:51", "remaining_time": "0:21:30", "throughput": 2644.96, "total_tokens": 6800952} {"current_steps": 25405, "total_steps": 38150, "loss": 0.3419, "lr": 1.5159652567038663e-05, "epoch": 6.659239842726081, "percentage": 66.59, "elapsed_time": "0:42:51", "remaining_time": "0:21:30", "throughput": 2645.07, "total_tokens": 6802504} {"current_steps": 25410, "total_steps": 38150, "loss": 0.312, "lr": 1.5149139579872629e-05, "epoch": 6.660550458715596, "percentage": 66.61, "elapsed_time": "0:42:52", "remaining_time": "0:21:29", "throughput": 2645.15, "total_tokens": 6803880} {"current_steps": 25415, "total_steps": 38150, "loss": 0.2962, "lr": 1.5138628654474656e-05, "epoch": 6.6618610747051115, "percentage": 66.62, "elapsed_time": "0:42:52", "remaining_time": "0:21:29", "throughput": 2645.2, "total_tokens": 6805176} {"current_steps": 25420, "total_steps": 38150, "loss": 0.2088, "lr": 1.5128119793044677e-05, "epoch": 6.663171690694626, "percentage": 66.63, "elapsed_time": "0:42:53", "remaining_time": "0:21:28", "throughput": 2645.23, "total_tokens": 6806456} {"current_steps": 25425, "total_steps": 38150, "loss": 0.2529, "lr": 1.511761299778216e-05, "epoch": 6.664482306684142, "percentage": 66.64, "elapsed_time": "0:42:53", "remaining_time": "0:21:28", "throughput": 2645.23, "total_tokens": 6807592} {"current_steps": 25430, "total_steps": 38150, "loss": 0.3242, "lr": 1.5107108270886166e-05, "epoch": 6.665792922673656, "percentage": 66.66, "elapsed_time": "0:42:54", "remaining_time": "0:21:27", "throughput": 2645.39, "total_tokens": 6809448} {"current_steps": 25435, "total_steps": 38150, "loss": 0.2938, "lr": 1.509660561455532e-05, "epoch": 6.667103538663172, "percentage": 66.67, "elapsed_time": "0:42:54", "remaining_time": "0:21:26", "throughput": 2645.38, "total_tokens": 6810520} {"current_steps": 25440, "total_steps": 38150, "loss": 0.2913, "lr": 1.5086105030987807e-05, "epoch": 6.6684141546526865, "percentage": 66.68, "elapsed_time": "0:42:54", "remaining_time": "0:21:26", "throughput": 2645.38, "total_tokens": 6811656} {"current_steps": 25445, "total_steps": 38150, "loss": 0.1949, "lr": 1.5075606522381375e-05, "epoch": 6.669724770642202, "percentage": 66.7, "elapsed_time": "0:42:55", "remaining_time": "0:21:25", "throughput": 2645.32, "total_tokens": 6812600} {"current_steps": 25450, "total_steps": 38150, "loss": 0.3124, "lr": 1.5065110090933354e-05, "epoch": 6.671035386631717, "percentage": 66.71, "elapsed_time": "0:42:55", "remaining_time": "0:21:25", "throughput": 2645.33, "total_tokens": 6813912} {"current_steps": 25455, "total_steps": 38150, "loss": 0.2779, "lr": 1.5054615738840627e-05, "epoch": 6.672346002621232, "percentage": 66.72, "elapsed_time": "0:42:56", "remaining_time": "0:21:24", "throughput": 2645.29, "total_tokens": 6814904} {"current_steps": 25460, "total_steps": 38150, "loss": 0.3012, "lr": 1.5044123468299648e-05, "epoch": 6.673656618610747, "percentage": 66.74, "elapsed_time": "0:42:56", "remaining_time": "0:21:24", "throughput": 2645.28, "total_tokens": 6815992} {"current_steps": 25465, "total_steps": 38150, "loss": 0.3217, "lr": 1.5033633281506416e-05, "epoch": 6.674967234600262, "percentage": 66.75, "elapsed_time": "0:42:57", "remaining_time": "0:21:23", "throughput": 2645.39, "total_tokens": 6817640} {"current_steps": 25470, "total_steps": 38150, "loss": 0.3114, "lr": 1.5023145180656517e-05, "epoch": 6.676277850589777, "percentage": 66.76, "elapsed_time": "0:42:57", "remaining_time": "0:21:23", "throughput": 2645.51, "total_tokens": 6819288} {"current_steps": 25475, "total_steps": 38150, "loss": 0.245, "lr": 1.5012659167945097e-05, "epoch": 6.677588466579293, "percentage": 66.78, "elapsed_time": "0:42:58", "remaining_time": "0:21:22", "throughput": 2645.51, "total_tokens": 6820440} {"current_steps": 25480, "total_steps": 38150, "loss": 0.1898, "lr": 1.5002175245566857e-05, "epoch": 6.678899082568807, "percentage": 66.79, "elapsed_time": "0:42:58", "remaining_time": "0:21:22", "throughput": 2645.61, "total_tokens": 6822104} {"current_steps": 25485, "total_steps": 38150, "loss": 0.368, "lr": 1.4991693415716062e-05, "epoch": 6.680209698558322, "percentage": 66.8, "elapsed_time": "0:42:59", "remaining_time": "0:21:21", "throughput": 2645.61, "total_tokens": 6823208} {"current_steps": 25490, "total_steps": 38150, "loss": 0.2721, "lr": 1.498121368058654e-05, "epoch": 6.6815203145478375, "percentage": 66.82, "elapsed_time": "0:42:59", "remaining_time": "0:21:21", "throughput": 2645.73, "total_tokens": 6824872} {"current_steps": 25495, "total_steps": 38150, "loss": 0.222, "lr": 1.4970736042371685e-05, "epoch": 6.682830930537353, "percentage": 66.83, "elapsed_time": "0:43:00", "remaining_time": "0:21:20", "throughput": 2645.74, "total_tokens": 6826040} {"current_steps": 25500, "total_steps": 38150, "loss": 0.2761, "lr": 1.4960260503264445e-05, "epoch": 6.684141546526868, "percentage": 66.84, "elapsed_time": "0:43:00", "remaining_time": "0:21:20", "throughput": 2645.82, "total_tokens": 6827400} {"current_steps": 25505, "total_steps": 38150, "loss": 0.1884, "lr": 1.494978706545733e-05, "epoch": 6.685452162516382, "percentage": 66.85, "elapsed_time": "0:43:00", "remaining_time": "0:21:19", "throughput": 2645.89, "total_tokens": 6828760} {"current_steps": 25510, "total_steps": 38150, "loss": 0.1932, "lr": 1.4939315731142423e-05, "epoch": 6.686762778505898, "percentage": 66.87, "elapsed_time": "0:43:01", "remaining_time": "0:21:19", "throughput": 2645.98, "total_tokens": 6830296} {"current_steps": 25515, "total_steps": 38150, "loss": 0.3092, "lr": 1.4928846502511353e-05, "epoch": 6.6880733944954125, "percentage": 66.88, "elapsed_time": "0:43:01", "remaining_time": "0:21:18", "throughput": 2646.17, "total_tokens": 6832152} {"current_steps": 25520, "total_steps": 38150, "loss": 0.2365, "lr": 1.4918379381755303e-05, "epoch": 6.689384010484928, "percentage": 66.89, "elapsed_time": "0:43:02", "remaining_time": "0:21:18", "throughput": 2646.17, "total_tokens": 6833288} {"current_steps": 25525, "total_steps": 38150, "loss": 0.11, "lr": 1.4907914371065032e-05, "epoch": 6.690694626474443, "percentage": 66.91, "elapsed_time": "0:43:02", "remaining_time": "0:21:17", "throughput": 2646.27, "total_tokens": 6834792} {"current_steps": 25530, "total_steps": 38150, "loss": 0.3807, "lr": 1.4897451472630844e-05, "epoch": 6.692005242463958, "percentage": 66.92, "elapsed_time": "0:43:03", "remaining_time": "0:21:16", "throughput": 2646.37, "total_tokens": 6836360} {"current_steps": 25535, "total_steps": 38150, "loss": 0.1987, "lr": 1.4886990688642605e-05, "epoch": 6.693315858453473, "percentage": 66.93, "elapsed_time": "0:43:03", "remaining_time": "0:21:16", "throughput": 2646.34, "total_tokens": 6837448} {"current_steps": 25540, "total_steps": 38150, "loss": 0.3264, "lr": 1.487653202128975e-05, "epoch": 6.694626474442988, "percentage": 66.95, "elapsed_time": "0:43:04", "remaining_time": "0:21:15", "throughput": 2646.36, "total_tokens": 6838632} {"current_steps": 25545, "total_steps": 38150, "loss": 0.2492, "lr": 1.4866075472761243e-05, "epoch": 6.695937090432503, "percentage": 66.96, "elapsed_time": "0:43:04", "remaining_time": "0:21:15", "throughput": 2646.35, "total_tokens": 6839720} {"current_steps": 25550, "total_steps": 38150, "loss": 0.2556, "lr": 1.485562104524563e-05, "epoch": 6.697247706422019, "percentage": 66.97, "elapsed_time": "0:43:05", "remaining_time": "0:21:14", "throughput": 2646.35, "total_tokens": 6840856} {"current_steps": 25555, "total_steps": 38150, "loss": 0.2303, "lr": 1.4845168740931004e-05, "epoch": 6.698558322411533, "percentage": 66.99, "elapsed_time": "0:43:05", "remaining_time": "0:21:14", "throughput": 2646.38, "total_tokens": 6842088} {"current_steps": 25560, "total_steps": 38150, "loss": 0.155, "lr": 1.4834718562005007e-05, "epoch": 6.699868938401049, "percentage": 67.0, "elapsed_time": "0:43:05", "remaining_time": "0:21:13", "throughput": 2646.47, "total_tokens": 6843528} {"current_steps": 25565, "total_steps": 38150, "loss": 0.229, "lr": 1.4824270510654859e-05, "epoch": 6.7011795543905635, "percentage": 67.01, "elapsed_time": "0:43:06", "remaining_time": "0:21:13", "throughput": 2646.5, "total_tokens": 6844776} {"current_steps": 25570, "total_steps": 38150, "loss": 0.1508, "lr": 1.4813824589067309e-05, "epoch": 6.702490170380079, "percentage": 67.02, "elapsed_time": "0:43:06", "remaining_time": "0:21:12", "throughput": 2646.56, "total_tokens": 6846216} {"current_steps": 25575, "total_steps": 38150, "loss": 0.2156, "lr": 1.4803380799428679e-05, "epoch": 6.703800786369594, "percentage": 67.04, "elapsed_time": "0:43:07", "remaining_time": "0:21:12", "throughput": 2646.53, "total_tokens": 6847224} {"current_steps": 25580, "total_steps": 38150, "loss": 0.2884, "lr": 1.4792939143924822e-05, "epoch": 6.705111402359108, "percentage": 67.05, "elapsed_time": "0:43:07", "remaining_time": "0:21:11", "throughput": 2646.58, "total_tokens": 6848536} {"current_steps": 25585, "total_steps": 38150, "loss": 0.3374, "lr": 1.478249962474117e-05, "epoch": 6.706422018348624, "percentage": 67.06, "elapsed_time": "0:43:08", "remaining_time": "0:21:11", "throughput": 2646.58, "total_tokens": 6849672} {"current_steps": 25590, "total_steps": 38150, "loss": 0.2673, "lr": 1.4772062244062687e-05, "epoch": 6.707732634338139, "percentage": 67.08, "elapsed_time": "0:43:08", "remaining_time": "0:21:10", "throughput": 2646.59, "total_tokens": 6850824} {"current_steps": 25595, "total_steps": 38150, "loss": 0.2804, "lr": 1.4761627004073905e-05, "epoch": 6.709043250327654, "percentage": 67.09, "elapsed_time": "0:43:08", "remaining_time": "0:21:09", "throughput": 2646.62, "total_tokens": 6852072} {"current_steps": 25600, "total_steps": 38150, "loss": 0.2672, "lr": 1.4751193906958907e-05, "epoch": 6.710353866317169, "percentage": 67.1, "elapsed_time": "0:43:09", "remaining_time": "0:21:09", "throughput": 2646.63, "total_tokens": 6853240} {"current_steps": 25605, "total_steps": 38150, "loss": 0.2083, "lr": 1.474076295490131e-05, "epoch": 6.711664482306684, "percentage": 67.12, "elapsed_time": "0:43:09", "remaining_time": "0:21:08", "throughput": 2646.76, "total_tokens": 6854840} {"current_steps": 25610, "total_steps": 38150, "loss": 0.1712, "lr": 1.4730334150084302e-05, "epoch": 6.712975098296199, "percentage": 67.13, "elapsed_time": "0:43:10", "remaining_time": "0:21:08", "throughput": 2646.71, "total_tokens": 6855848} {"current_steps": 25615, "total_steps": 38150, "loss": 0.2375, "lr": 1.4719907494690604e-05, "epoch": 6.714285714285714, "percentage": 67.14, "elapsed_time": "0:43:10", "remaining_time": "0:21:07", "throughput": 2646.81, "total_tokens": 6857320} {"current_steps": 25620, "total_steps": 38150, "loss": 0.1912, "lr": 1.470948299090251e-05, "epoch": 6.715596330275229, "percentage": 67.16, "elapsed_time": "0:43:11", "remaining_time": "0:21:07", "throughput": 2646.84, "total_tokens": 6858568} {"current_steps": 25625, "total_steps": 38150, "loss": 0.1149, "lr": 1.4699060640901845e-05, "epoch": 6.716906946264745, "percentage": 67.17, "elapsed_time": "0:43:11", "remaining_time": "0:21:06", "throughput": 2646.91, "total_tokens": 6859912} {"current_steps": 25630, "total_steps": 38150, "loss": 0.1465, "lr": 1.4688640446869988e-05, "epoch": 6.718217562254259, "percentage": 67.18, "elapsed_time": "0:43:12", "remaining_time": "0:21:06", "throughput": 2646.81, "total_tokens": 6860760} {"current_steps": 25635, "total_steps": 38150, "loss": 0.2182, "lr": 1.467822241098788e-05, "epoch": 6.719528178243775, "percentage": 67.2, "elapsed_time": "0:43:12", "remaining_time": "0:21:05", "throughput": 2646.82, "total_tokens": 6861928} {"current_steps": 25640, "total_steps": 38150, "loss": 0.142, "lr": 1.4667806535435974e-05, "epoch": 6.7208387942332894, "percentage": 67.21, "elapsed_time": "0:43:13", "remaining_time": "0:21:05", "throughput": 2647.04, "total_tokens": 6864136} {"current_steps": 25645, "total_steps": 38150, "loss": 0.1916, "lr": 1.4657392822394312e-05, "epoch": 6.722149410222805, "percentage": 67.22, "elapsed_time": "0:43:13", "remaining_time": "0:21:04", "throughput": 2647.1, "total_tokens": 6865480} {"current_steps": 25650, "total_steps": 38150, "loss": 0.2111, "lr": 1.464698127404246e-05, "epoch": 6.72346002621232, "percentage": 67.23, "elapsed_time": "0:43:14", "remaining_time": "0:21:04", "throughput": 2647.16, "total_tokens": 6866888} {"current_steps": 25655, "total_steps": 38150, "loss": 0.3076, "lr": 1.4636571892559547e-05, "epoch": 6.724770642201835, "percentage": 67.25, "elapsed_time": "0:43:14", "remaining_time": "0:21:03", "throughput": 2647.22, "total_tokens": 6868248} {"current_steps": 25660, "total_steps": 38150, "loss": 0.2203, "lr": 1.4626164680124221e-05, "epoch": 6.72608125819135, "percentage": 67.26, "elapsed_time": "0:43:14", "remaining_time": "0:21:03", "throughput": 2647.21, "total_tokens": 6869352} {"current_steps": 25665, "total_steps": 38150, "loss": 0.2508, "lr": 1.4615759638914705e-05, "epoch": 6.727391874180865, "percentage": 67.27, "elapsed_time": "0:43:15", "remaining_time": "0:21:02", "throughput": 2647.19, "total_tokens": 6870440} {"current_steps": 25670, "total_steps": 38150, "loss": 0.3034, "lr": 1.4605356771108753e-05, "epoch": 6.72870249017038, "percentage": 67.29, "elapsed_time": "0:43:15", "remaining_time": "0:21:02", "throughput": 2647.23, "total_tokens": 6871704} {"current_steps": 25675, "total_steps": 38150, "loss": 0.2152, "lr": 1.4594956078883665e-05, "epoch": 6.730013106159895, "percentage": 67.3, "elapsed_time": "0:43:16", "remaining_time": "0:21:01", "throughput": 2647.33, "total_tokens": 6873208} {"current_steps": 25680, "total_steps": 38150, "loss": 0.2613, "lr": 1.4584557564416296e-05, "epoch": 6.73132372214941, "percentage": 67.31, "elapsed_time": "0:43:16", "remaining_time": "0:21:00", "throughput": 2647.42, "total_tokens": 6874616} {"current_steps": 25685, "total_steps": 38150, "loss": 0.2078, "lr": 1.457416122988303e-05, "epoch": 6.732634338138926, "percentage": 67.33, "elapsed_time": "0:43:17", "remaining_time": "0:21:00", "throughput": 2647.4, "total_tokens": 6875672} {"current_steps": 25690, "total_steps": 38150, "loss": 0.2112, "lr": 1.4563767077459805e-05, "epoch": 6.73394495412844, "percentage": 67.34, "elapsed_time": "0:43:17", "remaining_time": "0:20:59", "throughput": 2647.47, "total_tokens": 6877064} {"current_steps": 25695, "total_steps": 38150, "loss": 0.2737, "lr": 1.4553375109322098e-05, "epoch": 6.735255570117955, "percentage": 67.35, "elapsed_time": "0:43:18", "remaining_time": "0:20:59", "throughput": 2647.51, "total_tokens": 6878328} {"current_steps": 25700, "total_steps": 38150, "loss": 0.2189, "lr": 1.4542985327644931e-05, "epoch": 6.736566186107471, "percentage": 67.37, "elapsed_time": "0:43:18", "remaining_time": "0:20:58", "throughput": 2647.54, "total_tokens": 6879528} {"current_steps": 25705, "total_steps": 38150, "loss": 0.303, "lr": 1.4532597734602877e-05, "epoch": 6.737876802096985, "percentage": 67.38, "elapsed_time": "0:43:18", "remaining_time": "0:20:58", "throughput": 2647.6, "total_tokens": 6880920} {"current_steps": 25710, "total_steps": 38150, "loss": 0.2301, "lr": 1.4522212332370019e-05, "epoch": 6.739187418086501, "percentage": 67.39, "elapsed_time": "0:43:19", "remaining_time": "0:20:57", "throughput": 2647.66, "total_tokens": 6882344} {"current_steps": 25715, "total_steps": 38150, "loss": 0.4123, "lr": 1.4511829123120018e-05, "epoch": 6.740498034076015, "percentage": 67.4, "elapsed_time": "0:43:19", "remaining_time": "0:20:57", "throughput": 2647.71, "total_tokens": 6883624} {"current_steps": 25720, "total_steps": 38150, "loss": 0.2803, "lr": 1.4501448109026055e-05, "epoch": 6.741808650065531, "percentage": 67.42, "elapsed_time": "0:43:20", "remaining_time": "0:20:56", "throughput": 2647.88, "total_tokens": 6885432} {"current_steps": 25725, "total_steps": 38150, "loss": 0.1951, "lr": 1.4491069292260868e-05, "epoch": 6.743119266055046, "percentage": 67.43, "elapsed_time": "0:43:20", "remaining_time": "0:20:56", "throughput": 2648.09, "total_tokens": 6887480} {"current_steps": 25730, "total_steps": 38150, "loss": 0.2426, "lr": 1.448069267499671e-05, "epoch": 6.744429882044561, "percentage": 67.44, "elapsed_time": "0:43:21", "remaining_time": "0:20:55", "throughput": 2648.13, "total_tokens": 6888728} {"current_steps": 25735, "total_steps": 38150, "loss": 0.5907, "lr": 1.4470318259405407e-05, "epoch": 6.745740498034076, "percentage": 67.46, "elapsed_time": "0:43:21", "remaining_time": "0:20:55", "throughput": 2648.13, "total_tokens": 6889848} {"current_steps": 25740, "total_steps": 38150, "loss": 0.1577, "lr": 1.4459946047658306e-05, "epoch": 6.747051114023591, "percentage": 67.47, "elapsed_time": "0:43:22", "remaining_time": "0:20:54", "throughput": 2648.14, "total_tokens": 6891016} {"current_steps": 25745, "total_steps": 38150, "loss": 0.127, "lr": 1.444957604192628e-05, "epoch": 6.748361730013106, "percentage": 67.48, "elapsed_time": "0:43:22", "remaining_time": "0:20:54", "throughput": 2648.25, "total_tokens": 6892472} {"current_steps": 25750, "total_steps": 38150, "loss": 0.2941, "lr": 1.4439208244379757e-05, "epoch": 6.749672346002622, "percentage": 67.5, "elapsed_time": "0:43:23", "remaining_time": "0:20:53", "throughput": 2648.35, "total_tokens": 6893912} {"current_steps": 25755, "total_steps": 38150, "loss": 0.2574, "lr": 1.4428842657188701e-05, "epoch": 6.750982961992136, "percentage": 67.51, "elapsed_time": "0:43:23", "remaining_time": "0:20:52", "throughput": 2648.32, "total_tokens": 6894920} {"current_steps": 25760, "total_steps": 38150, "loss": 0.2566, "lr": 1.441847928252261e-05, "epoch": 6.752293577981652, "percentage": 67.52, "elapsed_time": "0:43:23", "remaining_time": "0:20:52", "throughput": 2648.41, "total_tokens": 6896344} {"current_steps": 25765, "total_steps": 38150, "loss": 0.3483, "lr": 1.4408118122550524e-05, "epoch": 6.753604193971166, "percentage": 67.54, "elapsed_time": "0:43:24", "remaining_time": "0:20:51", "throughput": 2648.52, "total_tokens": 6898072} {"current_steps": 25770, "total_steps": 38150, "loss": 0.442, "lr": 1.4397759179441012e-05, "epoch": 6.754914809960681, "percentage": 67.55, "elapsed_time": "0:43:24", "remaining_time": "0:20:51", "throughput": 2648.55, "total_tokens": 6899304} {"current_steps": 25775, "total_steps": 38150, "loss": 0.165, "lr": 1.4387402455362181e-05, "epoch": 6.756225425950197, "percentage": 67.56, "elapsed_time": "0:43:25", "remaining_time": "0:20:50", "throughput": 2648.71, "total_tokens": 6901000} {"current_steps": 25780, "total_steps": 38150, "loss": 0.2755, "lr": 1.4377047952481685e-05, "epoch": 6.757536041939712, "percentage": 67.58, "elapsed_time": "0:43:25", "remaining_time": "0:20:50", "throughput": 2648.72, "total_tokens": 6902184} {"current_steps": 25785, "total_steps": 38150, "loss": 0.2029, "lr": 1.4366695672966705e-05, "epoch": 6.758846657929227, "percentage": 67.59, "elapsed_time": "0:43:26", "remaining_time": "0:20:49", "throughput": 2648.75, "total_tokens": 6903480} {"current_steps": 25790, "total_steps": 38150, "loss": 0.239, "lr": 1.4356345618983927e-05, "epoch": 6.760157273918741, "percentage": 67.6, "elapsed_time": "0:43:26", "remaining_time": "0:20:49", "throughput": 2648.73, "total_tokens": 6904536} {"current_steps": 25795, "total_steps": 38150, "loss": 0.1752, "lr": 1.434599779269963e-05, "epoch": 6.761467889908257, "percentage": 67.61, "elapsed_time": "0:43:27", "remaining_time": "0:20:48", "throughput": 2648.77, "total_tokens": 6905768} {"current_steps": 25800, "total_steps": 38150, "loss": 0.15, "lr": 1.4335652196279587e-05, "epoch": 6.762778505897772, "percentage": 67.63, "elapsed_time": "0:43:27", "remaining_time": "0:20:48", "throughput": 2648.81, "total_tokens": 6907096} {"current_steps": 25805, "total_steps": 38150, "loss": 0.2548, "lr": 1.4325308831889115e-05, "epoch": 6.764089121887287, "percentage": 67.64, "elapsed_time": "0:43:28", "remaining_time": "0:20:47", "throughput": 2648.85, "total_tokens": 6908344} {"current_steps": 25810, "total_steps": 38150, "loss": 0.224, "lr": 1.4314967701693055e-05, "epoch": 6.765399737876802, "percentage": 67.65, "elapsed_time": "0:43:28", "remaining_time": "0:20:47", "throughput": 2648.86, "total_tokens": 6909592} {"current_steps": 25815, "total_steps": 38150, "loss": 0.1939, "lr": 1.4304628807855797e-05, "epoch": 6.766710353866317, "percentage": 67.67, "elapsed_time": "0:43:28", "remaining_time": "0:20:46", "throughput": 2648.81, "total_tokens": 6910552} {"current_steps": 25820, "total_steps": 38150, "loss": 0.255, "lr": 1.4294292152541258e-05, "epoch": 6.768020969855832, "percentage": 67.68, "elapsed_time": "0:43:29", "remaining_time": "0:20:46", "throughput": 2648.85, "total_tokens": 6911880} {"current_steps": 25825, "total_steps": 38150, "loss": 0.2539, "lr": 1.4283957737912862e-05, "epoch": 6.7693315858453476, "percentage": 67.69, "elapsed_time": "0:43:29", "remaining_time": "0:20:45", "throughput": 2648.9, "total_tokens": 6913176} {"current_steps": 25830, "total_steps": 38150, "loss": 0.3494, "lr": 1.4273625566133596e-05, "epoch": 6.770642201834862, "percentage": 67.71, "elapsed_time": "0:43:30", "remaining_time": "0:20:45", "throughput": 2648.94, "total_tokens": 6914424} {"current_steps": 25835, "total_steps": 38150, "loss": 0.2599, "lr": 1.426329563936597e-05, "epoch": 6.771952817824378, "percentage": 67.72, "elapsed_time": "0:43:30", "remaining_time": "0:20:44", "throughput": 2649.02, "total_tokens": 6915896} {"current_steps": 25840, "total_steps": 38150, "loss": 0.2254, "lr": 1.4252967959772013e-05, "epoch": 6.773263433813892, "percentage": 67.73, "elapsed_time": "0:43:31", "remaining_time": "0:20:43", "throughput": 2649.19, "total_tokens": 6917672} {"current_steps": 25845, "total_steps": 38150, "loss": 0.1519, "lr": 1.4242642529513278e-05, "epoch": 6.774574049803408, "percentage": 67.75, "elapsed_time": "0:43:31", "remaining_time": "0:20:43", "throughput": 2649.24, "total_tokens": 6918968} {"current_steps": 25850, "total_steps": 38150, "loss": 0.2545, "lr": 1.4232319350750888e-05, "epoch": 6.775884665792923, "percentage": 67.76, "elapsed_time": "0:43:32", "remaining_time": "0:20:42", "throughput": 2649.36, "total_tokens": 6920536} {"current_steps": 25855, "total_steps": 38150, "loss": 0.2209, "lr": 1.422199842564545e-05, "epoch": 6.777195281782438, "percentage": 67.77, "elapsed_time": "0:43:32", "remaining_time": "0:20:42", "throughput": 2649.46, "total_tokens": 6922056} {"current_steps": 25860, "total_steps": 38150, "loss": 0.2738, "lr": 1.4211679756357132e-05, "epoch": 6.778505897771953, "percentage": 67.79, "elapsed_time": "0:43:33", "remaining_time": "0:20:41", "throughput": 2649.43, "total_tokens": 6923080} {"current_steps": 25865, "total_steps": 38150, "loss": 0.2314, "lr": 1.4201363345045588e-05, "epoch": 6.779816513761467, "percentage": 67.8, "elapsed_time": "0:43:33", "remaining_time": "0:20:41", "throughput": 2649.57, "total_tokens": 6924776} {"current_steps": 25870, "total_steps": 38150, "loss": 0.2396, "lr": 1.4191049193870037e-05, "epoch": 6.781127129750983, "percentage": 67.81, "elapsed_time": "0:43:33", "remaining_time": "0:20:40", "throughput": 2649.66, "total_tokens": 6926216} {"current_steps": 25875, "total_steps": 38150, "loss": 0.2452, "lr": 1.4180737304989216e-05, "epoch": 6.7824377457404985, "percentage": 67.82, "elapsed_time": "0:43:34", "remaining_time": "0:20:40", "throughput": 2649.7, "total_tokens": 6927432} {"current_steps": 25880, "total_steps": 38150, "loss": 0.2215, "lr": 1.4170427680561382e-05, "epoch": 6.783748361730013, "percentage": 67.84, "elapsed_time": "0:43:34", "remaining_time": "0:20:39", "throughput": 2649.81, "total_tokens": 6929064} {"current_steps": 25885, "total_steps": 38150, "loss": 0.2344, "lr": 1.4160120322744322e-05, "epoch": 6.785058977719528, "percentage": 67.85, "elapsed_time": "0:43:35", "remaining_time": "0:20:39", "throughput": 2649.89, "total_tokens": 6930584} {"current_steps": 25890, "total_steps": 38150, "loss": 0.3393, "lr": 1.4149815233695346e-05, "epoch": 6.786369593709043, "percentage": 67.86, "elapsed_time": "0:43:35", "remaining_time": "0:20:38", "throughput": 2650.01, "total_tokens": 6932312} {"current_steps": 25895, "total_steps": 38150, "loss": 0.3432, "lr": 1.4139512415571298e-05, "epoch": 6.787680209698558, "percentage": 67.88, "elapsed_time": "0:43:36", "remaining_time": "0:20:38", "throughput": 2650.17, "total_tokens": 6934152} {"current_steps": 25900, "total_steps": 38150, "loss": 0.207, "lr": 1.4129211870528534e-05, "epoch": 6.7889908256880735, "percentage": 67.89, "elapsed_time": "0:43:36", "remaining_time": "0:20:37", "throughput": 2650.21, "total_tokens": 6935400} {"current_steps": 25905, "total_steps": 38150, "loss": 0.1564, "lr": 1.411891360072294e-05, "epoch": 6.790301441677588, "percentage": 67.9, "elapsed_time": "0:43:37", "remaining_time": "0:20:37", "throughput": 2650.18, "total_tokens": 6936424} {"current_steps": 25910, "total_steps": 38150, "loss": 0.1957, "lr": 1.4108617608309932e-05, "epoch": 6.791612057667104, "percentage": 67.92, "elapsed_time": "0:43:37", "remaining_time": "0:20:36", "throughput": 2650.21, "total_tokens": 6937624} {"current_steps": 25915, "total_steps": 38150, "loss": 0.2361, "lr": 1.4098323895444437e-05, "epoch": 6.792922673656618, "percentage": 67.93, "elapsed_time": "0:43:38", "remaining_time": "0:20:36", "throughput": 2650.27, "total_tokens": 6939032} {"current_steps": 25920, "total_steps": 38150, "loss": 0.352, "lr": 1.4088032464280914e-05, "epoch": 6.794233289646134, "percentage": 67.94, "elapsed_time": "0:43:38", "remaining_time": "0:20:35", "throughput": 2650.31, "total_tokens": 6940296} {"current_steps": 25925, "total_steps": 38150, "loss": 0.2502, "lr": 1.4077743316973346e-05, "epoch": 6.795543905635649, "percentage": 67.96, "elapsed_time": "0:43:39", "remaining_time": "0:20:35", "throughput": 2650.5, "total_tokens": 6942200} {"current_steps": 25930, "total_steps": 38150, "loss": 0.2461, "lr": 1.4067456455675226e-05, "epoch": 6.796854521625164, "percentage": 67.97, "elapsed_time": "0:43:39", "remaining_time": "0:20:34", "throughput": 2650.75, "total_tokens": 6944472} {"current_steps": 25935, "total_steps": 38150, "loss": 0.2642, "lr": 1.4057171882539583e-05, "epoch": 6.798165137614679, "percentage": 67.98, "elapsed_time": "0:43:40", "remaining_time": "0:20:34", "throughput": 2650.83, "total_tokens": 6945944} {"current_steps": 25940, "total_steps": 38150, "loss": 0.1961, "lr": 1.4046889599718962e-05, "epoch": 6.799475753604194, "percentage": 67.99, "elapsed_time": "0:43:40", "remaining_time": "0:20:33", "throughput": 2650.84, "total_tokens": 6947096} {"current_steps": 25945, "total_steps": 38150, "loss": 0.2583, "lr": 1.4036609609365414e-05, "epoch": 6.800786369593709, "percentage": 68.01, "elapsed_time": "0:43:41", "remaining_time": "0:20:33", "throughput": 2650.85, "total_tokens": 6948360} {"current_steps": 25950, "total_steps": 38150, "loss": 0.2488, "lr": 1.4026331913630536e-05, "epoch": 6.8020969855832245, "percentage": 68.02, "elapsed_time": "0:43:41", "remaining_time": "0:20:32", "throughput": 2650.88, "total_tokens": 6949576} {"current_steps": 25955, "total_steps": 38150, "loss": 0.1504, "lr": 1.401605651466542e-05, "epoch": 6.803407601572739, "percentage": 68.03, "elapsed_time": "0:43:42", "remaining_time": "0:20:31", "throughput": 2650.92, "total_tokens": 6950840} {"current_steps": 25960, "total_steps": 38150, "loss": 0.1805, "lr": 1.4005783414620694e-05, "epoch": 6.804718217562254, "percentage": 68.05, "elapsed_time": "0:43:42", "remaining_time": "0:20:31", "throughput": 2650.99, "total_tokens": 6952296} {"current_steps": 25965, "total_steps": 38150, "loss": 0.3162, "lr": 1.3995512615646509e-05, "epoch": 6.806028833551769, "percentage": 68.06, "elapsed_time": "0:43:42", "remaining_time": "0:20:30", "throughput": 2651.0, "total_tokens": 6953512} {"current_steps": 25970, "total_steps": 38150, "loss": 0.247, "lr": 1.3985244119892518e-05, "epoch": 6.807339449541285, "percentage": 68.07, "elapsed_time": "0:43:43", "remaining_time": "0:20:30", "throughput": 2651.03, "total_tokens": 6954744} {"current_steps": 25975, "total_steps": 38150, "loss": 0.1788, "lr": 1.3974977929507913e-05, "epoch": 6.8086500655307995, "percentage": 68.09, "elapsed_time": "0:43:43", "remaining_time": "0:20:29", "throughput": 2651.13, "total_tokens": 6956280} {"current_steps": 25980, "total_steps": 38150, "loss": 0.1871, "lr": 1.3964714046641366e-05, "epoch": 6.809960681520314, "percentage": 68.1, "elapsed_time": "0:43:44", "remaining_time": "0:20:29", "throughput": 2651.1, "total_tokens": 6957304} {"current_steps": 25985, "total_steps": 38150, "loss": 0.2493, "lr": 1.3954452473441104e-05, "epoch": 6.81127129750983, "percentage": 68.11, "elapsed_time": "0:43:44", "remaining_time": "0:20:28", "throughput": 2651.04, "total_tokens": 6958296} {"current_steps": 25990, "total_steps": 38150, "loss": 0.2981, "lr": 1.3944193212054851e-05, "epoch": 6.812581913499344, "percentage": 68.13, "elapsed_time": "0:43:45", "remaining_time": "0:20:28", "throughput": 2651.04, "total_tokens": 6959400} {"current_steps": 25995, "total_steps": 38150, "loss": 0.211, "lr": 1.393393626462986e-05, "epoch": 6.81389252948886, "percentage": 68.14, "elapsed_time": "0:43:45", "remaining_time": "0:20:27", "throughput": 2651.09, "total_tokens": 6960904} {"current_steps": 26000, "total_steps": 38150, "loss": 0.1558, "lr": 1.3923681633312885e-05, "epoch": 6.815203145478375, "percentage": 68.15, "elapsed_time": "0:43:46", "remaining_time": "0:20:27", "throughput": 2651.13, "total_tokens": 6962120} {"current_steps": 26005, "total_steps": 38150, "loss": 0.1931, "lr": 1.3913429320250203e-05, "epoch": 6.81651376146789, "percentage": 68.17, "elapsed_time": "0:43:46", "remaining_time": "0:20:26", "throughput": 2651.1, "total_tokens": 6963160} {"current_steps": 26010, "total_steps": 38150, "loss": 0.2885, "lr": 1.3903179327587612e-05, "epoch": 6.817824377457405, "percentage": 68.18, "elapsed_time": "0:43:46", "remaining_time": "0:20:26", "throughput": 2651.2, "total_tokens": 6964696} {"current_steps": 26015, "total_steps": 38150, "loss": 0.1899, "lr": 1.3892931657470415e-05, "epoch": 6.81913499344692, "percentage": 68.19, "elapsed_time": "0:43:47", "remaining_time": "0:20:25", "throughput": 2651.26, "total_tokens": 6966152} {"current_steps": 26020, "total_steps": 38150, "loss": 0.317, "lr": 1.3882686312043428e-05, "epoch": 6.820445609436435, "percentage": 68.2, "elapsed_time": "0:43:47", "remaining_time": "0:20:25", "throughput": 2651.28, "total_tokens": 6967320} {"current_steps": 26025, "total_steps": 38150, "loss": 0.261, "lr": 1.3872443293450987e-05, "epoch": 6.8217562254259505, "percentage": 68.22, "elapsed_time": "0:43:48", "remaining_time": "0:20:24", "throughput": 2651.28, "total_tokens": 6968440} {"current_steps": 26030, "total_steps": 38150, "loss": 0.2756, "lr": 1.3862202603836938e-05, "epoch": 6.823066841415465, "percentage": 68.23, "elapsed_time": "0:43:48", "remaining_time": "0:20:24", "throughput": 2651.33, "total_tokens": 6969800} {"current_steps": 26035, "total_steps": 38150, "loss": 0.2207, "lr": 1.385196424534464e-05, "epoch": 6.824377457404981, "percentage": 68.24, "elapsed_time": "0:43:49", "remaining_time": "0:20:23", "throughput": 2651.5, "total_tokens": 6971752} {"current_steps": 26040, "total_steps": 38150, "loss": 0.159, "lr": 1.3841728220116961e-05, "epoch": 6.825688073394495, "percentage": 68.26, "elapsed_time": "0:43:49", "remaining_time": "0:20:23", "throughput": 2651.51, "total_tokens": 6972968} {"current_steps": 26045, "total_steps": 38150, "loss": 0.1474, "lr": 1.3831494530296291e-05, "epoch": 6.826998689384011, "percentage": 68.27, "elapsed_time": "0:43:50", "remaining_time": "0:20:22", "throughput": 2651.66, "total_tokens": 6974664} {"current_steps": 26050, "total_steps": 38150, "loss": 0.2071, "lr": 1.3821263178024512e-05, "epoch": 6.8283093053735255, "percentage": 68.28, "elapsed_time": "0:43:50", "remaining_time": "0:20:21", "throughput": 2651.76, "total_tokens": 6976152} {"current_steps": 26055, "total_steps": 38150, "loss": 0.2499, "lr": 1.3811034165443038e-05, "epoch": 6.82961992136304, "percentage": 68.3, "elapsed_time": "0:43:51", "remaining_time": "0:20:21", "throughput": 2651.79, "total_tokens": 6977400} {"current_steps": 26060, "total_steps": 38150, "loss": 0.3321, "lr": 1.3800807494692785e-05, "epoch": 6.830930537352556, "percentage": 68.31, "elapsed_time": "0:43:51", "remaining_time": "0:20:20", "throughput": 2651.87, "total_tokens": 6978808} {"current_steps": 26065, "total_steps": 38150, "loss": 0.2299, "lr": 1.3790583167914168e-05, "epoch": 6.832241153342071, "percentage": 68.32, "elapsed_time": "0:43:52", "remaining_time": "0:20:20", "throughput": 2652.01, "total_tokens": 6980424} {"current_steps": 26070, "total_steps": 38150, "loss": 0.1886, "lr": 1.3780361187247125e-05, "epoch": 6.833551769331586, "percentage": 68.34, "elapsed_time": "0:43:52", "remaining_time": "0:20:19", "throughput": 2652.07, "total_tokens": 6981736} {"current_steps": 26075, "total_steps": 38150, "loss": 0.37, "lr": 1.377014155483109e-05, "epoch": 6.834862385321101, "percentage": 68.35, "elapsed_time": "0:43:53", "remaining_time": "0:20:19", "throughput": 2652.13, "total_tokens": 6983112} {"current_steps": 26080, "total_steps": 38150, "loss": 0.3075, "lr": 1.375992427280503e-05, "epoch": 6.836173001310616, "percentage": 68.36, "elapsed_time": "0:43:53", "remaining_time": "0:20:18", "throughput": 2652.14, "total_tokens": 6984376} {"current_steps": 26085, "total_steps": 38150, "loss": 0.2843, "lr": 1.3749709343307401e-05, "epoch": 6.837483617300131, "percentage": 68.37, "elapsed_time": "0:43:53", "remaining_time": "0:20:18", "throughput": 2652.15, "total_tokens": 6985576} {"current_steps": 26090, "total_steps": 38150, "loss": 0.2081, "lr": 1.3739496768476168e-05, "epoch": 6.838794233289646, "percentage": 68.39, "elapsed_time": "0:43:54", "remaining_time": "0:20:17", "throughput": 2652.19, "total_tokens": 6986888} {"current_steps": 26095, "total_steps": 38150, "loss": 0.3336, "lr": 1.3729286550448814e-05, "epoch": 6.840104849279161, "percentage": 68.4, "elapsed_time": "0:43:54", "remaining_time": "0:20:17", "throughput": 2652.34, "total_tokens": 6988648} {"current_steps": 26100, "total_steps": 38150, "loss": 0.2324, "lr": 1.3719078691362302e-05, "epoch": 6.8414154652686765, "percentage": 68.41, "elapsed_time": "0:43:55", "remaining_time": "0:20:16", "throughput": 2652.45, "total_tokens": 6990264} {"current_steps": 26105, "total_steps": 38150, "loss": 0.2177, "lr": 1.3708873193353125e-05, "epoch": 6.842726081258191, "percentage": 68.43, "elapsed_time": "0:43:55", "remaining_time": "0:20:16", "throughput": 2652.4, "total_tokens": 6991256} {"current_steps": 26110, "total_steps": 38150, "loss": 0.2325, "lr": 1.3698670058557281e-05, "epoch": 6.844036697247707, "percentage": 68.44, "elapsed_time": "0:43:56", "remaining_time": "0:20:15", "throughput": 2652.39, "total_tokens": 6992360} {"current_steps": 26115, "total_steps": 38150, "loss": 0.4432, "lr": 1.3688469289110268e-05, "epoch": 6.845347313237221, "percentage": 68.45, "elapsed_time": "0:43:56", "remaining_time": "0:20:15", "throughput": 2652.57, "total_tokens": 6994360} {"current_steps": 26120, "total_steps": 38150, "loss": 0.2254, "lr": 1.3678270887147085e-05, "epoch": 6.846657929226737, "percentage": 68.47, "elapsed_time": "0:43:57", "remaining_time": "0:20:14", "throughput": 2652.56, "total_tokens": 6995464} {"current_steps": 26125, "total_steps": 38150, "loss": 0.2464, "lr": 1.3668074854802243e-05, "epoch": 6.8479685452162515, "percentage": 68.48, "elapsed_time": "0:43:57", "remaining_time": "0:20:14", "throughput": 2652.62, "total_tokens": 6996872} {"current_steps": 26130, "total_steps": 38150, "loss": 0.4621, "lr": 1.3657881194209754e-05, "epoch": 6.849279161205767, "percentage": 68.49, "elapsed_time": "0:43:58", "remaining_time": "0:20:13", "throughput": 2652.68, "total_tokens": 6998248} {"current_steps": 26135, "total_steps": 38150, "loss": 0.2147, "lr": 1.3647689907503136e-05, "epoch": 6.850589777195282, "percentage": 68.51, "elapsed_time": "0:43:58", "remaining_time": "0:20:13", "throughput": 2652.67, "total_tokens": 6999352} {"current_steps": 26140, "total_steps": 38150, "loss": 0.2626, "lr": 1.3637500996815402e-05, "epoch": 6.851900393184797, "percentage": 68.52, "elapsed_time": "0:43:59", "remaining_time": "0:20:12", "throughput": 2652.76, "total_tokens": 7000760} {"current_steps": 26145, "total_steps": 38150, "loss": 0.2265, "lr": 1.3627314464279078e-05, "epoch": 6.853211009174312, "percentage": 68.53, "elapsed_time": "0:43:59", "remaining_time": "0:20:11", "throughput": 2652.84, "total_tokens": 7002200} {"current_steps": 26150, "total_steps": 38150, "loss": 0.3363, "lr": 1.3617130312026188e-05, "epoch": 6.854521625163827, "percentage": 68.55, "elapsed_time": "0:44:00", "remaining_time": "0:20:11", "throughput": 2653.03, "total_tokens": 7004136} {"current_steps": 26155, "total_steps": 38150, "loss": 0.235, "lr": 1.3606948542188252e-05, "epoch": 6.855832241153342, "percentage": 68.56, "elapsed_time": "0:44:00", "remaining_time": "0:20:10", "throughput": 2653.0, "total_tokens": 7005288} {"current_steps": 26160, "total_steps": 38150, "loss": 0.2687, "lr": 1.3596769156896303e-05, "epoch": 6.857142857142857, "percentage": 68.57, "elapsed_time": "0:44:00", "remaining_time": "0:20:10", "throughput": 2652.96, "total_tokens": 7006264} {"current_steps": 26165, "total_steps": 38150, "loss": 0.2006, "lr": 1.3586592158280864e-05, "epoch": 6.858453473132372, "percentage": 68.58, "elapsed_time": "0:44:01", "remaining_time": "0:20:09", "throughput": 2653.0, "total_tokens": 7007608} {"current_steps": 26170, "total_steps": 38150, "loss": 0.247, "lr": 1.3576417548471967e-05, "epoch": 6.859764089121887, "percentage": 68.6, "elapsed_time": "0:44:01", "remaining_time": "0:20:09", "throughput": 2653.11, "total_tokens": 7009224} {"current_steps": 26175, "total_steps": 38150, "loss": 0.2725, "lr": 1.3566245329599148e-05, "epoch": 6.8610747051114025, "percentage": 68.61, "elapsed_time": "0:44:02", "remaining_time": "0:20:08", "throughput": 2653.2, "total_tokens": 7010728} {"current_steps": 26180, "total_steps": 38150, "loss": 0.2318, "lr": 1.3556075503791416e-05, "epoch": 6.862385321100917, "percentage": 68.62, "elapsed_time": "0:44:02", "remaining_time": "0:20:08", "throughput": 2653.15, "total_tokens": 7011752} {"current_steps": 26185, "total_steps": 38150, "loss": 0.4051, "lr": 1.3545908073177308e-05, "epoch": 6.863695937090433, "percentage": 68.64, "elapsed_time": "0:44:03", "remaining_time": "0:20:07", "throughput": 2653.2, "total_tokens": 7013016} {"current_steps": 26190, "total_steps": 38150, "loss": 0.2199, "lr": 1.3535743039884841e-05, "epoch": 6.865006553079947, "percentage": 68.65, "elapsed_time": "0:44:03", "remaining_time": "0:20:07", "throughput": 2653.23, "total_tokens": 7014360} {"current_steps": 26195, "total_steps": 38150, "loss": 0.3655, "lr": 1.3525580406041552e-05, "epoch": 6.866317169069463, "percentage": 68.66, "elapsed_time": "0:44:04", "remaining_time": "0:20:06", "throughput": 2653.16, "total_tokens": 7015304} {"current_steps": 26200, "total_steps": 38150, "loss": 0.4175, "lr": 1.3515420173774463e-05, "epoch": 6.8676277850589775, "percentage": 68.68, "elapsed_time": "0:44:04", "remaining_time": "0:20:06", "throughput": 2653.34, "total_tokens": 7017096} {"current_steps": 26205, "total_steps": 38150, "loss": 0.834, "lr": 1.3505262345210084e-05, "epoch": 6.868938401048493, "percentage": 68.69, "elapsed_time": "0:44:05", "remaining_time": "0:20:05", "throughput": 2653.35, "total_tokens": 7018248} {"current_steps": 26210, "total_steps": 38150, "loss": 0.3103, "lr": 1.3495106922474444e-05, "epoch": 6.870249017038008, "percentage": 68.7, "elapsed_time": "0:44:05", "remaining_time": "0:20:05", "throughput": 2653.46, "total_tokens": 7019960} {"current_steps": 26215, "total_steps": 38150, "loss": 0.3183, "lr": 1.3484953907693038e-05, "epoch": 6.871559633027523, "percentage": 68.72, "elapsed_time": "0:44:06", "remaining_time": "0:20:04", "throughput": 2653.44, "total_tokens": 7021016} {"current_steps": 26220, "total_steps": 38150, "loss": 0.213, "lr": 1.3474803302990885e-05, "epoch": 6.872870249017038, "percentage": 68.73, "elapsed_time": "0:44:06", "remaining_time": "0:20:04", "throughput": 2653.52, "total_tokens": 7022520} {"current_steps": 26225, "total_steps": 38150, "loss": 0.2527, "lr": 1.3464655110492484e-05, "epoch": 6.8741808650065535, "percentage": 68.74, "elapsed_time": "0:44:06", "remaining_time": "0:20:03", "throughput": 2653.62, "total_tokens": 7024056} {"current_steps": 26230, "total_steps": 38150, "loss": 0.1991, "lr": 1.3454509332321834e-05, "epoch": 6.875491480996068, "percentage": 68.75, "elapsed_time": "0:44:07", "remaining_time": "0:20:03", "throughput": 2653.65, "total_tokens": 7025256} {"current_steps": 26235, "total_steps": 38150, "loss": 0.1787, "lr": 1.3444365970602436e-05, "epoch": 6.876802096985584, "percentage": 68.77, "elapsed_time": "0:44:07", "remaining_time": "0:20:02", "throughput": 2653.66, "total_tokens": 7026424} {"current_steps": 26240, "total_steps": 38150, "loss": 0.1644, "lr": 1.3434225027457274e-05, "epoch": 6.878112712975098, "percentage": 68.78, "elapsed_time": "0:44:08", "remaining_time": "0:20:02", "throughput": 2653.71, "total_tokens": 7027704} {"current_steps": 26245, "total_steps": 38150, "loss": 0.1824, "lr": 1.3424086505008827e-05, "epoch": 6.879423328964613, "percentage": 68.79, "elapsed_time": "0:44:08", "remaining_time": "0:20:01", "throughput": 2653.81, "total_tokens": 7029288} {"current_steps": 26250, "total_steps": 38150, "loss": 0.2845, "lr": 1.3413950405379075e-05, "epoch": 6.8807339449541285, "percentage": 68.81, "elapsed_time": "0:44:09", "remaining_time": "0:20:00", "throughput": 2653.89, "total_tokens": 7030648} {"current_steps": 26255, "total_steps": 38150, "loss": 0.2047, "lr": 1.3403816730689483e-05, "epoch": 6.882044560943643, "percentage": 68.82, "elapsed_time": "0:44:09", "remaining_time": "0:20:00", "throughput": 2653.93, "total_tokens": 7031992} {"current_steps": 26260, "total_steps": 38150, "loss": 0.1939, "lr": 1.3393685483061014e-05, "epoch": 6.883355176933159, "percentage": 68.83, "elapsed_time": "0:44:10", "remaining_time": "0:19:59", "throughput": 2653.93, "total_tokens": 7033144} {"current_steps": 26265, "total_steps": 38150, "loss": 0.3043, "lr": 1.3383556664614117e-05, "epoch": 6.884665792922673, "percentage": 68.85, "elapsed_time": "0:44:10", "remaining_time": "0:19:59", "throughput": 2654.07, "total_tokens": 7034824} {"current_steps": 26270, "total_steps": 38150, "loss": 0.2419, "lr": 1.337343027746874e-05, "epoch": 6.885976408912189, "percentage": 68.86, "elapsed_time": "0:44:11", "remaining_time": "0:19:58", "throughput": 2654.09, "total_tokens": 7036008} {"current_steps": 26275, "total_steps": 38150, "loss": 0.2521, "lr": 1.3363306323744315e-05, "epoch": 6.8872870249017035, "percentage": 68.87, "elapsed_time": "0:44:11", "remaining_time": "0:19:58", "throughput": 2654.21, "total_tokens": 7037624} {"current_steps": 26280, "total_steps": 38150, "loss": 0.3852, "lr": 1.335318480555977e-05, "epoch": 6.888597640891219, "percentage": 68.89, "elapsed_time": "0:44:11", "remaining_time": "0:19:57", "throughput": 2654.3, "total_tokens": 7039096} {"current_steps": 26285, "total_steps": 38150, "loss": 0.3295, "lr": 1.3343065725033522e-05, "epoch": 6.889908256880734, "percentage": 68.9, "elapsed_time": "0:44:12", "remaining_time": "0:19:57", "throughput": 2654.39, "total_tokens": 7040664} {"current_steps": 26290, "total_steps": 38150, "loss": 0.4118, "lr": 1.3332949084283478e-05, "epoch": 6.891218872870249, "percentage": 68.91, "elapsed_time": "0:44:12", "remaining_time": "0:19:56", "throughput": 2654.47, "total_tokens": 7042136} {"current_steps": 26295, "total_steps": 38150, "loss": 0.2723, "lr": 1.3322834885427038e-05, "epoch": 6.892529488859764, "percentage": 68.93, "elapsed_time": "0:44:13", "remaining_time": "0:19:56", "throughput": 2654.51, "total_tokens": 7043464} {"current_steps": 26300, "total_steps": 38150, "loss": 0.2431, "lr": 1.3312723130581073e-05, "epoch": 6.8938401048492794, "percentage": 68.94, "elapsed_time": "0:44:13", "remaining_time": "0:19:55", "throughput": 2654.5, "total_tokens": 7044568} {"current_steps": 26305, "total_steps": 38150, "loss": 0.1482, "lr": 1.3302613821861951e-05, "epoch": 6.895150720838794, "percentage": 68.95, "elapsed_time": "0:44:14", "remaining_time": "0:19:55", "throughput": 2654.54, "total_tokens": 7045896} {"current_steps": 26310, "total_steps": 38150, "loss": 0.2229, "lr": 1.3292506961385553e-05, "epoch": 6.89646133682831, "percentage": 68.96, "elapsed_time": "0:44:14", "remaining_time": "0:19:54", "throughput": 2654.59, "total_tokens": 7047288} {"current_steps": 26315, "total_steps": 38150, "loss": 0.3264, "lr": 1.3282402551267223e-05, "epoch": 6.897771952817824, "percentage": 68.98, "elapsed_time": "0:44:15", "remaining_time": "0:19:54", "throughput": 2654.6, "total_tokens": 7048472} {"current_steps": 26320, "total_steps": 38150, "loss": 0.2255, "lr": 1.3272300593621789e-05, "epoch": 6.89908256880734, "percentage": 68.99, "elapsed_time": "0:44:15", "remaining_time": "0:19:53", "throughput": 2654.67, "total_tokens": 7049832} {"current_steps": 26325, "total_steps": 38150, "loss": 0.3154, "lr": 1.3262201090563581e-05, "epoch": 6.9003931847968545, "percentage": 69.0, "elapsed_time": "0:44:16", "remaining_time": "0:19:53", "throughput": 2654.74, "total_tokens": 7051176} {"current_steps": 26330, "total_steps": 38150, "loss": 0.2527, "lr": 1.325210404420641e-05, "epoch": 6.90170380078637, "percentage": 69.02, "elapsed_time": "0:44:16", "remaining_time": "0:19:52", "throughput": 2654.9, "total_tokens": 7052888} {"current_steps": 26335, "total_steps": 38150, "loss": 0.1819, "lr": 1.324200945666355e-05, "epoch": 6.903014416775885, "percentage": 69.03, "elapsed_time": "0:44:16", "remaining_time": "0:19:52", "throughput": 2654.89, "total_tokens": 7053960} {"current_steps": 26340, "total_steps": 38150, "loss": 0.3428, "lr": 1.3231917330047802e-05, "epoch": 6.904325032765399, "percentage": 69.04, "elapsed_time": "0:44:17", "remaining_time": "0:19:51", "throughput": 2654.91, "total_tokens": 7055160} {"current_steps": 26345, "total_steps": 38150, "loss": 0.2158, "lr": 1.322182766647142e-05, "epoch": 6.905635648754915, "percentage": 69.06, "elapsed_time": "0:44:17", "remaining_time": "0:19:50", "throughput": 2654.92, "total_tokens": 7056344} {"current_steps": 26350, "total_steps": 38150, "loss": 0.2627, "lr": 1.3211740468046158e-05, "epoch": 6.9069462647444295, "percentage": 69.07, "elapsed_time": "0:44:18", "remaining_time": "0:19:50", "throughput": 2654.88, "total_tokens": 7057368} {"current_steps": 26355, "total_steps": 38150, "loss": 0.2628, "lr": 1.3201655736883244e-05, "epoch": 6.908256880733945, "percentage": 69.08, "elapsed_time": "0:44:18", "remaining_time": "0:19:49", "throughput": 2654.92, "total_tokens": 7058696} {"current_steps": 26360, "total_steps": 38150, "loss": 0.1913, "lr": 1.31915734750934e-05, "epoch": 6.90956749672346, "percentage": 69.1, "elapsed_time": "0:44:19", "remaining_time": "0:19:49", "throughput": 2655.02, "total_tokens": 7060216} {"current_steps": 26365, "total_steps": 38150, "loss": 0.3625, "lr": 1.3181493684786825e-05, "epoch": 6.910878112712975, "percentage": 69.11, "elapsed_time": "0:44:19", "remaining_time": "0:19:48", "throughput": 2655.2, "total_tokens": 7062168} {"current_steps": 26370, "total_steps": 38150, "loss": 0.2373, "lr": 1.31714163680732e-05, "epoch": 6.91218872870249, "percentage": 69.12, "elapsed_time": "0:44:20", "remaining_time": "0:19:48", "throughput": 2655.23, "total_tokens": 7063416} {"current_steps": 26375, "total_steps": 38150, "loss": 0.1936, "lr": 1.316134152706169e-05, "epoch": 6.913499344692005, "percentage": 69.13, "elapsed_time": "0:44:20", "remaining_time": "0:19:47", "throughput": 2655.29, "total_tokens": 7064728} {"current_steps": 26380, "total_steps": 38150, "loss": 0.4085, "lr": 1.3151269163860947e-05, "epoch": 6.91480996068152, "percentage": 69.15, "elapsed_time": "0:44:21", "remaining_time": "0:19:47", "throughput": 2655.61, "total_tokens": 7067624} {"current_steps": 26385, "total_steps": 38150, "loss": 0.5664, "lr": 1.3141199280579092e-05, "epoch": 6.916120576671036, "percentage": 69.16, "elapsed_time": "0:44:21", "remaining_time": "0:19:46", "throughput": 2655.6, "total_tokens": 7068760} {"current_steps": 26390, "total_steps": 38150, "loss": 0.2582, "lr": 1.3131131879323736e-05, "epoch": 6.91743119266055, "percentage": 69.17, "elapsed_time": "0:44:22", "remaining_time": "0:19:46", "throughput": 2655.7, "total_tokens": 7070328} {"current_steps": 26395, "total_steps": 38150, "loss": 0.1364, "lr": 1.3121066962201971e-05, "epoch": 6.918741808650066, "percentage": 69.19, "elapsed_time": "0:44:22", "remaining_time": "0:19:45", "throughput": 2655.78, "total_tokens": 7071832} {"current_steps": 26400, "total_steps": 38150, "loss": 0.1842, "lr": 1.3111004531320364e-05, "epoch": 6.9200524246395805, "percentage": 69.2, "elapsed_time": "0:44:23", "remaining_time": "0:19:45", "throughput": 2655.78, "total_tokens": 7072952} {"current_steps": 26405, "total_steps": 38150, "loss": 0.2755, "lr": 1.3100944588784969e-05, "epoch": 6.921363040629096, "percentage": 69.21, "elapsed_time": "0:44:23", "remaining_time": "0:19:44", "throughput": 2655.87, "total_tokens": 7074488} {"current_steps": 26410, "total_steps": 38150, "loss": 0.0885, "lr": 1.3090887136701319e-05, "epoch": 6.922673656618611, "percentage": 69.23, "elapsed_time": "0:44:24", "remaining_time": "0:19:44", "throughput": 2656.09, "total_tokens": 7077080} {"current_steps": 26415, "total_steps": 38150, "loss": 0.1999, "lr": 1.3080832177174406e-05, "epoch": 6.923984272608125, "percentage": 69.24, "elapsed_time": "0:44:24", "remaining_time": "0:19:43", "throughput": 2656.22, "total_tokens": 7078616} {"current_steps": 26420, "total_steps": 38150, "loss": 0.3089, "lr": 1.3070779712308711e-05, "epoch": 6.925294888597641, "percentage": 69.25, "elapsed_time": "0:44:25", "remaining_time": "0:19:43", "throughput": 2656.33, "total_tokens": 7080120} {"current_steps": 26425, "total_steps": 38150, "loss": 0.3221, "lr": 1.3060729744208222e-05, "epoch": 6.926605504587156, "percentage": 69.27, "elapsed_time": "0:44:25", "remaining_time": "0:19:42", "throughput": 2656.46, "total_tokens": 7081784} {"current_steps": 26430, "total_steps": 38150, "loss": 0.1858, "lr": 1.3050682274976369e-05, "epoch": 6.927916120576671, "percentage": 69.28, "elapsed_time": "0:44:26", "remaining_time": "0:19:42", "throughput": 2656.54, "total_tokens": 7083208} {"current_steps": 26435, "total_steps": 38150, "loss": 0.2216, "lr": 1.304063730671607e-05, "epoch": 6.929226736566186, "percentage": 69.29, "elapsed_time": "0:44:26", "remaining_time": "0:19:41", "throughput": 2656.57, "total_tokens": 7084456} {"current_steps": 26440, "total_steps": 38150, "loss": 0.2964, "lr": 1.3030594841529714e-05, "epoch": 6.930537352555701, "percentage": 69.31, "elapsed_time": "0:44:27", "remaining_time": "0:19:41", "throughput": 2656.65, "total_tokens": 7085800} {"current_steps": 26445, "total_steps": 38150, "loss": 0.1826, "lr": 1.3020554881519187e-05, "epoch": 6.931847968545216, "percentage": 69.32, "elapsed_time": "0:44:27", "remaining_time": "0:19:40", "throughput": 2656.73, "total_tokens": 7087144} {"current_steps": 26450, "total_steps": 38150, "loss": 0.2094, "lr": 1.3010517428785818e-05, "epoch": 6.933158584534731, "percentage": 69.33, "elapsed_time": "0:44:28", "remaining_time": "0:19:40", "throughput": 2656.81, "total_tokens": 7088632} {"current_steps": 26455, "total_steps": 38150, "loss": 0.1839, "lr": 1.3000482485430433e-05, "epoch": 6.934469200524246, "percentage": 69.34, "elapsed_time": "0:44:28", "remaining_time": "0:19:39", "throughput": 2656.83, "total_tokens": 7089800} {"current_steps": 26460, "total_steps": 38150, "loss": 0.2516, "lr": 1.299045005355333e-05, "epoch": 6.935779816513762, "percentage": 69.36, "elapsed_time": "0:44:28", "remaining_time": "0:19:39", "throughput": 2656.85, "total_tokens": 7091016} {"current_steps": 26465, "total_steps": 38150, "loss": 0.3422, "lr": 1.2980420135254279e-05, "epoch": 6.937090432503276, "percentage": 69.37, "elapsed_time": "0:44:29", "remaining_time": "0:19:38", "throughput": 2656.88, "total_tokens": 7092264} {"current_steps": 26470, "total_steps": 38150, "loss": 0.2915, "lr": 1.2970392732632527e-05, "epoch": 6.938401048492792, "percentage": 69.38, "elapsed_time": "0:44:29", "remaining_time": "0:19:38", "throughput": 2656.86, "total_tokens": 7093320} {"current_steps": 26475, "total_steps": 38150, "loss": 0.2025, "lr": 1.2960367847786781e-05, "epoch": 6.9397116644823065, "percentage": 69.4, "elapsed_time": "0:44:30", "remaining_time": "0:19:37", "throughput": 2656.92, "total_tokens": 7094712} {"current_steps": 26480, "total_steps": 38150, "loss": 0.231, "lr": 1.295034548281526e-05, "epoch": 6.941022280471822, "percentage": 69.41, "elapsed_time": "0:44:30", "remaining_time": "0:19:37", "throughput": 2656.93, "total_tokens": 7095880} {"current_steps": 26485, "total_steps": 38150, "loss": 0.2552, "lr": 1.2940325639815599e-05, "epoch": 6.942332896461337, "percentage": 69.42, "elapsed_time": "0:44:31", "remaining_time": "0:19:36", "throughput": 2657.02, "total_tokens": 7097288} {"current_steps": 26490, "total_steps": 38150, "loss": 0.1993, "lr": 1.2930308320884946e-05, "epoch": 6.943643512450852, "percentage": 69.44, "elapsed_time": "0:44:31", "remaining_time": "0:19:35", "throughput": 2657.01, "total_tokens": 7098424} {"current_steps": 26495, "total_steps": 38150, "loss": 0.1286, "lr": 1.2920293528119903e-05, "epoch": 6.944954128440367, "percentage": 69.45, "elapsed_time": "0:44:32", "remaining_time": "0:19:35", "throughput": 2657.02, "total_tokens": 7099608} {"current_steps": 26500, "total_steps": 38150, "loss": 0.4254, "lr": 1.2910281263616559e-05, "epoch": 6.946264744429882, "percentage": 69.46, "elapsed_time": "0:44:32", "remaining_time": "0:19:34", "throughput": 2657.15, "total_tokens": 7101208} {"current_steps": 26505, "total_steps": 38150, "loss": 0.2543, "lr": 1.2900271529470451e-05, "epoch": 6.947575360419397, "percentage": 69.48, "elapsed_time": "0:44:32", "remaining_time": "0:19:34", "throughput": 2657.21, "total_tokens": 7102616} {"current_steps": 26510, "total_steps": 38150, "loss": 0.2202, "lr": 1.2890264327776608e-05, "epoch": 6.948885976408912, "percentage": 69.49, "elapsed_time": "0:44:33", "remaining_time": "0:19:33", "throughput": 2657.2, "total_tokens": 7103720} {"current_steps": 26515, "total_steps": 38150, "loss": 0.2824, "lr": 1.2880259660629516e-05, "epoch": 6.950196592398427, "percentage": 69.5, "elapsed_time": "0:44:33", "remaining_time": "0:19:33", "throughput": 2657.21, "total_tokens": 7104888} {"current_steps": 26520, "total_steps": 38150, "loss": 0.2054, "lr": 1.2870257530123136e-05, "epoch": 6.951507208387943, "percentage": 69.52, "elapsed_time": "0:44:34", "remaining_time": "0:19:32", "throughput": 2657.24, "total_tokens": 7106088} {"current_steps": 26525, "total_steps": 38150, "loss": 0.4687, "lr": 1.2860257938350895e-05, "epoch": 6.952817824377457, "percentage": 69.53, "elapsed_time": "0:44:34", "remaining_time": "0:19:32", "throughput": 2657.25, "total_tokens": 7107320} {"current_steps": 26530, "total_steps": 38150, "loss": 0.3916, "lr": 1.2850260887405702e-05, "epoch": 6.954128440366972, "percentage": 69.54, "elapsed_time": "0:44:35", "remaining_time": "0:19:31", "throughput": 2657.35, "total_tokens": 7109000} {"current_steps": 26535, "total_steps": 38150, "loss": 0.1656, "lr": 1.2840266379379896e-05, "epoch": 6.955439056356488, "percentage": 69.55, "elapsed_time": "0:44:35", "remaining_time": "0:19:31", "throughput": 2657.44, "total_tokens": 7110504} {"current_steps": 26540, "total_steps": 38150, "loss": 0.303, "lr": 1.2830274416365334e-05, "epoch": 6.956749672346002, "percentage": 69.57, "elapsed_time": "0:44:36", "remaining_time": "0:19:30", "throughput": 2657.51, "total_tokens": 7111912} {"current_steps": 26545, "total_steps": 38150, "loss": 0.2662, "lr": 1.2820285000453309e-05, "epoch": 6.958060288335518, "percentage": 69.58, "elapsed_time": "0:44:36", "remaining_time": "0:19:30", "throughput": 2657.81, "total_tokens": 7114440} {"current_steps": 26550, "total_steps": 38150, "loss": 0.1455, "lr": 1.281029813373459e-05, "epoch": 6.9593709043250325, "percentage": 69.59, "elapsed_time": "0:44:37", "remaining_time": "0:19:29", "throughput": 2657.9, "total_tokens": 7115928} {"current_steps": 26555, "total_steps": 38150, "loss": 0.368, "lr": 1.2800313818299403e-05, "epoch": 6.960681520314548, "percentage": 69.61, "elapsed_time": "0:44:37", "remaining_time": "0:19:29", "throughput": 2657.91, "total_tokens": 7117144} {"current_steps": 26560, "total_steps": 38150, "loss": 0.4449, "lr": 1.2790332056237458e-05, "epoch": 6.961992136304063, "percentage": 69.62, "elapsed_time": "0:44:38", "remaining_time": "0:19:28", "throughput": 2657.97, "total_tokens": 7118552} {"current_steps": 26565, "total_steps": 38150, "loss": 0.2255, "lr": 1.2780352849637928e-05, "epoch": 6.963302752293578, "percentage": 69.63, "elapsed_time": "0:44:38", "remaining_time": "0:19:28", "throughput": 2657.96, "total_tokens": 7119640} {"current_steps": 26570, "total_steps": 38150, "loss": 0.2999, "lr": 1.2770376200589423e-05, "epoch": 6.964613368283093, "percentage": 69.65, "elapsed_time": "0:44:39", "remaining_time": "0:19:27", "throughput": 2658.07, "total_tokens": 7121192} {"current_steps": 26575, "total_steps": 38150, "loss": 0.4421, "lr": 1.2760402111180048e-05, "epoch": 6.965923984272608, "percentage": 69.66, "elapsed_time": "0:44:39", "remaining_time": "0:19:27", "throughput": 2658.08, "total_tokens": 7122360} {"current_steps": 26580, "total_steps": 38150, "loss": 0.3872, "lr": 1.2750430583497363e-05, "epoch": 6.967234600262123, "percentage": 69.67, "elapsed_time": "0:44:40", "remaining_time": "0:19:26", "throughput": 2658.19, "total_tokens": 7124104} {"current_steps": 26585, "total_steps": 38150, "loss": 0.2346, "lr": 1.2740461619628392e-05, "epoch": 6.968545216251639, "percentage": 69.69, "elapsed_time": "0:44:40", "remaining_time": "0:19:26", "throughput": 2658.27, "total_tokens": 7125496} {"current_steps": 26590, "total_steps": 38150, "loss": 0.3429, "lr": 1.2730495221659607e-05, "epoch": 6.969855832241153, "percentage": 69.7, "elapsed_time": "0:44:40", "remaining_time": "0:19:25", "throughput": 2658.32, "total_tokens": 7126792} {"current_steps": 26595, "total_steps": 38150, "loss": 0.289, "lr": 1.2720531391676987e-05, "epoch": 6.971166448230669, "percentage": 69.71, "elapsed_time": "0:44:41", "remaining_time": "0:19:25", "throughput": 2658.43, "total_tokens": 7128536} {"current_steps": 26600, "total_steps": 38150, "loss": 0.214, "lr": 1.2710570131765937e-05, "epoch": 6.972477064220183, "percentage": 69.72, "elapsed_time": "0:44:41", "remaining_time": "0:19:24", "throughput": 2658.51, "total_tokens": 7129896} {"current_steps": 26605, "total_steps": 38150, "loss": 0.2826, "lr": 1.2700611444011312e-05, "epoch": 6.973787680209698, "percentage": 69.74, "elapsed_time": "0:44:42", "remaining_time": "0:19:23", "throughput": 2658.52, "total_tokens": 7131080} {"current_steps": 26610, "total_steps": 38150, "loss": 0.201, "lr": 1.2690655330497464e-05, "epoch": 6.975098296199214, "percentage": 69.75, "elapsed_time": "0:44:42", "remaining_time": "0:19:23", "throughput": 2658.61, "total_tokens": 7132504} {"current_steps": 26615, "total_steps": 38150, "loss": 0.1505, "lr": 1.2680701793308187e-05, "epoch": 6.976408912188729, "percentage": 69.76, "elapsed_time": "0:44:43", "remaining_time": "0:19:22", "throughput": 2658.61, "total_tokens": 7133720} {"current_steps": 26620, "total_steps": 38150, "loss": 0.2833, "lr": 1.2670750834526735e-05, "epoch": 6.977719528178244, "percentage": 69.78, "elapsed_time": "0:44:43", "remaining_time": "0:19:22", "throughput": 2658.7, "total_tokens": 7135176} {"current_steps": 26625, "total_steps": 38150, "loss": 0.3211, "lr": 1.266080245623583e-05, "epoch": 6.9790301441677585, "percentage": 69.79, "elapsed_time": "0:44:44", "remaining_time": "0:19:21", "throughput": 2658.77, "total_tokens": 7136648} {"current_steps": 26630, "total_steps": 38150, "loss": 0.4187, "lr": 1.2650856660517652e-05, "epoch": 6.980340760157274, "percentage": 69.8, "elapsed_time": "0:44:44", "remaining_time": "0:19:21", "throughput": 2658.72, "total_tokens": 7137640} {"current_steps": 26635, "total_steps": 38150, "loss": 0.2817, "lr": 1.2640913449453837e-05, "epoch": 6.981651376146789, "percentage": 69.82, "elapsed_time": "0:44:45", "remaining_time": "0:19:20", "throughput": 2658.73, "total_tokens": 7138824} {"current_steps": 26640, "total_steps": 38150, "loss": 0.3284, "lr": 1.2630972825125482e-05, "epoch": 6.982961992136304, "percentage": 69.83, "elapsed_time": "0:44:45", "remaining_time": "0:19:20", "throughput": 2658.87, "total_tokens": 7140376} {"current_steps": 26645, "total_steps": 38150, "loss": 0.4298, "lr": 1.2621034789613151e-05, "epoch": 6.984272608125819, "percentage": 69.84, "elapsed_time": "0:44:45", "remaining_time": "0:19:19", "throughput": 2658.97, "total_tokens": 7141896} {"current_steps": 26650, "total_steps": 38150, "loss": 0.2714, "lr": 1.2611099344996832e-05, "epoch": 6.985583224115334, "percentage": 69.86, "elapsed_time": "0:44:46", "remaining_time": "0:19:19", "throughput": 2659.08, "total_tokens": 7143432} {"current_steps": 26655, "total_steps": 38150, "loss": 0.2664, "lr": 1.2601166493356023e-05, "epoch": 6.986893840104849, "percentage": 69.87, "elapsed_time": "0:44:46", "remaining_time": "0:19:18", "throughput": 2659.06, "total_tokens": 7144520} {"current_steps": 26660, "total_steps": 38150, "loss": 0.2432, "lr": 1.2591236236769643e-05, "epoch": 6.988204456094365, "percentage": 69.88, "elapsed_time": "0:44:47", "remaining_time": "0:19:18", "throughput": 2659.12, "total_tokens": 7145816} {"current_steps": 26665, "total_steps": 38150, "loss": 0.2753, "lr": 1.2581308577316079e-05, "epoch": 6.989515072083879, "percentage": 69.9, "elapsed_time": "0:44:47", "remaining_time": "0:19:17", "throughput": 2659.18, "total_tokens": 7147192} {"current_steps": 26670, "total_steps": 38150, "loss": 0.2579, "lr": 1.2571383517073172e-05, "epoch": 6.990825688073395, "percentage": 69.91, "elapsed_time": "0:44:48", "remaining_time": "0:19:17", "throughput": 2659.23, "total_tokens": 7148488} {"current_steps": 26675, "total_steps": 38150, "loss": 0.3096, "lr": 1.2561461058118219e-05, "epoch": 6.992136304062909, "percentage": 69.92, "elapsed_time": "0:44:48", "remaining_time": "0:19:16", "throughput": 2659.11, "total_tokens": 7149256} {"current_steps": 26680, "total_steps": 38150, "loss": 0.2099, "lr": 1.2551541202527984e-05, "epoch": 6.993446920052425, "percentage": 69.93, "elapsed_time": "0:44:49", "remaining_time": "0:19:16", "throughput": 2659.27, "total_tokens": 7151000} {"current_steps": 26685, "total_steps": 38150, "loss": 0.2366, "lr": 1.2541623952378657e-05, "epoch": 6.99475753604194, "percentage": 69.95, "elapsed_time": "0:44:49", "remaining_time": "0:19:15", "throughput": 2659.23, "total_tokens": 7152008} {"current_steps": 26690, "total_steps": 38150, "loss": 0.197, "lr": 1.2531709309745907e-05, "epoch": 6.996068152031455, "percentage": 69.96, "elapsed_time": "0:44:49", "remaining_time": "0:19:14", "throughput": 2659.28, "total_tokens": 7153320} {"current_steps": 26695, "total_steps": 38150, "loss": 0.4201, "lr": 1.2521797276704858e-05, "epoch": 6.99737876802097, "percentage": 69.97, "elapsed_time": "0:44:50", "remaining_time": "0:19:14", "throughput": 2659.27, "total_tokens": 7154424} {"current_steps": 26700, "total_steps": 38150, "loss": 0.3076, "lr": 1.251188785533008e-05, "epoch": 6.9986893840104845, "percentage": 69.99, "elapsed_time": "0:44:50", "remaining_time": "0:19:13", "throughput": 2659.46, "total_tokens": 7156472} {"current_steps": 26705, "total_steps": 38150, "loss": 0.2119, "lr": 1.2501981047695583e-05, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:44:51", "remaining_time": "0:19:13", "throughput": 2659.33, "total_tokens": 7157624} {"current_steps": 26710, "total_steps": 38150, "loss": 0.1318, "lr": 1.2492076855874868e-05, "epoch": 7.001310615989515, "percentage": 70.01, "elapsed_time": "0:44:52", "remaining_time": "0:19:13", "throughput": 2659.14, "total_tokens": 7158776} {"current_steps": 26712, "total_steps": 38150, "eval_loss": 0.657537043094635, "epoch": 7.001834862385321, "percentage": 70.02, "elapsed_time": "0:45:09", "remaining_time": "0:19:20", "throughput": 2642.68, "total_tokens": 7159688} {"current_steps": 26715, "total_steps": 38150, "loss": 0.1587, "lr": 1.2482175281940855e-05, "epoch": 7.00262123197903, "percentage": 70.03, "elapsed_time": "0:45:11", "remaining_time": "0:19:20", "throughput": 2641.11, "total_tokens": 7160488} {"current_steps": 26720, "total_steps": 38150, "loss": 0.2289, "lr": 1.2472276327965938e-05, "epoch": 7.003931847968545, "percentage": 70.04, "elapsed_time": "0:45:11", "remaining_time": "0:19:19", "throughput": 2641.27, "total_tokens": 7162232} {"current_steps": 26725, "total_steps": 38150, "loss": 0.2971, "lr": 1.2462379996021928e-05, "epoch": 7.00524246395806, "percentage": 70.05, "elapsed_time": "0:45:12", "remaining_time": "0:19:19", "throughput": 2641.46, "total_tokens": 7164264} {"current_steps": 26730, "total_steps": 38150, "loss": 0.1329, "lr": 1.2452486288180124e-05, "epoch": 7.006553079947575, "percentage": 70.07, "elapsed_time": "0:45:12", "remaining_time": "0:19:18", "throughput": 2641.54, "total_tokens": 7165720} {"current_steps": 26735, "total_steps": 38150, "loss": 0.2393, "lr": 1.2442595206511257e-05, "epoch": 7.007863695937091, "percentage": 70.08, "elapsed_time": "0:45:13", "remaining_time": "0:19:18", "throughput": 2641.6, "total_tokens": 7167048} {"current_steps": 26740, "total_steps": 38150, "loss": 0.2148, "lr": 1.2432706753085516e-05, "epoch": 7.009174311926605, "percentage": 70.09, "elapsed_time": "0:45:13", "remaining_time": "0:19:17", "throughput": 2641.82, "total_tokens": 7169224} {"current_steps": 26745, "total_steps": 38150, "loss": 0.1695, "lr": 1.2422820929972537e-05, "epoch": 7.010484927916121, "percentage": 70.1, "elapsed_time": "0:45:14", "remaining_time": "0:19:17", "throughput": 2641.84, "total_tokens": 7170472} {"current_steps": 26750, "total_steps": 38150, "loss": 0.1649, "lr": 1.2412937739241407e-05, "epoch": 7.011795543905635, "percentage": 70.12, "elapsed_time": "0:45:14", "remaining_time": "0:19:16", "throughput": 2641.78, "total_tokens": 7171416} {"current_steps": 26755, "total_steps": 38150, "loss": 0.1154, "lr": 1.2403057182960655e-05, "epoch": 7.013106159895151, "percentage": 70.13, "elapsed_time": "0:45:15", "remaining_time": "0:19:16", "throughput": 2641.86, "total_tokens": 7172856} {"current_steps": 26760, "total_steps": 38150, "loss": 0.1817, "lr": 1.2393179263198273e-05, "epoch": 7.014416775884666, "percentage": 70.14, "elapsed_time": "0:45:15", "remaining_time": "0:19:15", "throughput": 2641.9, "total_tokens": 7174200} {"current_steps": 26765, "total_steps": 38150, "loss": 0.1996, "lr": 1.2383303982021688e-05, "epoch": 7.015727391874181, "percentage": 70.16, "elapsed_time": "0:45:15", "remaining_time": "0:19:15", "throughput": 2641.91, "total_tokens": 7175384} {"current_steps": 26770, "total_steps": 38150, "loss": 0.1808, "lr": 1.237343134149778e-05, "epoch": 7.017038007863696, "percentage": 70.17, "elapsed_time": "0:45:16", "remaining_time": "0:19:14", "throughput": 2641.98, "total_tokens": 7176824} {"current_steps": 26775, "total_steps": 38150, "loss": 0.2574, "lr": 1.2363561343692873e-05, "epoch": 7.018348623853211, "percentage": 70.18, "elapsed_time": "0:45:16", "remaining_time": "0:19:14", "throughput": 2642.0, "total_tokens": 7178040} {"current_steps": 26780, "total_steps": 38150, "loss": 0.1585, "lr": 1.2353693990672743e-05, "epoch": 7.019659239842726, "percentage": 70.2, "elapsed_time": "0:45:17", "remaining_time": "0:19:13", "throughput": 2642.02, "total_tokens": 7179224} {"current_steps": 26785, "total_steps": 38150, "loss": 0.2016, "lr": 1.2343829284502612e-05, "epoch": 7.0209698558322415, "percentage": 70.21, "elapsed_time": "0:45:17", "remaining_time": "0:19:13", "throughput": 2642.0, "total_tokens": 7180280} {"current_steps": 26790, "total_steps": 38150, "loss": 0.1226, "lr": 1.2333967227247143e-05, "epoch": 7.022280471821756, "percentage": 70.22, "elapsed_time": "0:45:18", "remaining_time": "0:19:12", "throughput": 2642.06, "total_tokens": 7181624} {"current_steps": 26795, "total_steps": 38150, "loss": 0.3562, "lr": 1.2324107820970445e-05, "epoch": 7.023591087811272, "percentage": 70.24, "elapsed_time": "0:45:18", "remaining_time": "0:19:12", "throughput": 2642.09, "total_tokens": 7182872} {"current_steps": 26800, "total_steps": 38150, "loss": 0.1563, "lr": 1.231425106773609e-05, "epoch": 7.024901703800786, "percentage": 70.25, "elapsed_time": "0:45:19", "remaining_time": "0:19:11", "throughput": 2642.13, "total_tokens": 7184120} {"current_steps": 26805, "total_steps": 38150, "loss": 0.1518, "lr": 1.2304396969607057e-05, "epoch": 7.026212319790301, "percentage": 70.26, "elapsed_time": "0:45:19", "remaining_time": "0:19:10", "throughput": 2642.05, "total_tokens": 7185000} {"current_steps": 26810, "total_steps": 38150, "loss": 0.1833, "lr": 1.2294545528645804e-05, "epoch": 7.027522935779817, "percentage": 70.28, "elapsed_time": "0:45:19", "remaining_time": "0:19:10", "throughput": 2642.11, "total_tokens": 7186456} {"current_steps": 26815, "total_steps": 38150, "loss": 0.2847, "lr": 1.2284696746914216e-05, "epoch": 7.028833551769331, "percentage": 70.29, "elapsed_time": "0:45:20", "remaining_time": "0:19:09", "throughput": 2642.08, "total_tokens": 7187496} {"current_steps": 26820, "total_steps": 38150, "loss": 0.1424, "lr": 1.227485062647362e-05, "epoch": 7.030144167758847, "percentage": 70.3, "elapsed_time": "0:45:20", "remaining_time": "0:19:09", "throughput": 2642.21, "total_tokens": 7189144} {"current_steps": 26825, "total_steps": 38150, "loss": 0.0875, "lr": 1.226500716938481e-05, "epoch": 7.031454783748361, "percentage": 70.31, "elapsed_time": "0:45:21", "remaining_time": "0:19:08", "throughput": 2642.2, "total_tokens": 7190248} {"current_steps": 26830, "total_steps": 38150, "loss": 0.1323, "lr": 1.2255166377707995e-05, "epoch": 7.032765399737877, "percentage": 70.33, "elapsed_time": "0:45:21", "remaining_time": "0:19:08", "throughput": 2642.3, "total_tokens": 7191768} {"current_steps": 26835, "total_steps": 38150, "loss": 0.2087, "lr": 1.2245328253502844e-05, "epoch": 7.034076015727392, "percentage": 70.34, "elapsed_time": "0:45:22", "remaining_time": "0:19:07", "throughput": 2642.39, "total_tokens": 7193272} {"current_steps": 26840, "total_steps": 38150, "loss": 0.2001, "lr": 1.2235492798828444e-05, "epoch": 7.035386631716907, "percentage": 70.35, "elapsed_time": "0:45:22", "remaining_time": "0:19:07", "throughput": 2642.48, "total_tokens": 7194792} {"current_steps": 26845, "total_steps": 38150, "loss": 0.249, "lr": 1.2225660015743343e-05, "epoch": 7.036697247706422, "percentage": 70.37, "elapsed_time": "0:45:23", "remaining_time": "0:19:06", "throughput": 2642.5, "total_tokens": 7195992} {"current_steps": 26850, "total_steps": 38150, "loss": 0.2134, "lr": 1.2215829906305531e-05, "epoch": 7.038007863695937, "percentage": 70.38, "elapsed_time": "0:45:23", "remaining_time": "0:19:06", "throughput": 2642.61, "total_tokens": 7197544} {"current_steps": 26855, "total_steps": 38150, "loss": 0.2505, "lr": 1.2206002472572428e-05, "epoch": 7.039318479685452, "percentage": 70.39, "elapsed_time": "0:45:24", "remaining_time": "0:19:05", "throughput": 2642.66, "total_tokens": 7198904} {"current_steps": 26860, "total_steps": 38150, "loss": 0.1681, "lr": 1.2196177716600904e-05, "epoch": 7.0406290956749675, "percentage": 70.41, "elapsed_time": "0:45:24", "remaining_time": "0:19:05", "throughput": 2642.71, "total_tokens": 7200200} {"current_steps": 26865, "total_steps": 38150, "loss": 0.2, "lr": 1.2186355640447259e-05, "epoch": 7.041939711664482, "percentage": 70.42, "elapsed_time": "0:45:25", "remaining_time": "0:19:04", "throughput": 2642.76, "total_tokens": 7201576} {"current_steps": 26870, "total_steps": 38150, "loss": 0.1063, "lr": 1.2176536246167235e-05, "epoch": 7.043250327653998, "percentage": 70.43, "elapsed_time": "0:45:25", "remaining_time": "0:19:04", "throughput": 2642.89, "total_tokens": 7203272} {"current_steps": 26875, "total_steps": 38150, "loss": 0.1306, "lr": 1.2166719535816024e-05, "epoch": 7.044560943643512, "percentage": 70.45, "elapsed_time": "0:45:25", "remaining_time": "0:19:03", "throughput": 2642.93, "total_tokens": 7204504} {"current_steps": 26880, "total_steps": 38150, "loss": 0.0983, "lr": 1.2156905511448235e-05, "epoch": 7.045871559633028, "percentage": 70.46, "elapsed_time": "0:45:26", "remaining_time": "0:19:03", "throughput": 2642.9, "total_tokens": 7205544} {"current_steps": 26885, "total_steps": 38150, "loss": 0.3037, "lr": 1.2147094175117932e-05, "epoch": 7.047182175622543, "percentage": 70.47, "elapsed_time": "0:45:26", "remaining_time": "0:19:02", "throughput": 2642.93, "total_tokens": 7206760} {"current_steps": 26890, "total_steps": 38150, "loss": 0.2542, "lr": 1.2137285528878611e-05, "epoch": 7.048492791612058, "percentage": 70.48, "elapsed_time": "0:45:27", "remaining_time": "0:19:02", "throughput": 2643.02, "total_tokens": 7208264} {"current_steps": 26895, "total_steps": 38150, "loss": 0.2864, "lr": 1.2127479574783205e-05, "epoch": 7.049803407601573, "percentage": 70.5, "elapsed_time": "0:45:27", "remaining_time": "0:19:01", "throughput": 2643.34, "total_tokens": 7210936} {"current_steps": 26900, "total_steps": 38150, "loss": 0.1635, "lr": 1.211767631488408e-05, "epoch": 7.051114023591087, "percentage": 70.51, "elapsed_time": "0:45:28", "remaining_time": "0:19:01", "throughput": 2643.35, "total_tokens": 7212200} {"current_steps": 26905, "total_steps": 38150, "loss": 0.2286, "lr": 1.2107875751233045e-05, "epoch": 7.052424639580603, "percentage": 70.52, "elapsed_time": "0:45:28", "remaining_time": "0:19:00", "throughput": 2643.33, "total_tokens": 7213272} {"current_steps": 26910, "total_steps": 38150, "loss": 0.1359, "lr": 1.2098077885881336e-05, "epoch": 7.053735255570118, "percentage": 70.54, "elapsed_time": "0:45:29", "remaining_time": "0:18:59", "throughput": 2643.36, "total_tokens": 7214472} {"current_steps": 26915, "total_steps": 38150, "loss": 0.2132, "lr": 1.2088282720879646e-05, "epoch": 7.055045871559633, "percentage": 70.55, "elapsed_time": "0:45:29", "remaining_time": "0:18:59", "throughput": 2643.36, "total_tokens": 7215608} {"current_steps": 26920, "total_steps": 38150, "loss": 0.2241, "lr": 1.2078490258278061e-05, "epoch": 7.056356487549148, "percentage": 70.56, "elapsed_time": "0:45:30", "remaining_time": "0:18:58", "throughput": 2643.41, "total_tokens": 7216952} {"current_steps": 26925, "total_steps": 38150, "loss": 0.1988, "lr": 1.206870050012614e-05, "epoch": 7.057667103538663, "percentage": 70.58, "elapsed_time": "0:45:30", "remaining_time": "0:18:58", "throughput": 2643.58, "total_tokens": 7218824} {"current_steps": 26930, "total_steps": 38150, "loss": 0.1666, "lr": 1.205891344847286e-05, "epoch": 7.058977719528178, "percentage": 70.59, "elapsed_time": "0:45:31", "remaining_time": "0:18:57", "throughput": 2643.62, "total_tokens": 7220136} {"current_steps": 26935, "total_steps": 38150, "loss": 0.2273, "lr": 1.2049129105366625e-05, "epoch": 7.0602883355176935, "percentage": 70.6, "elapsed_time": "0:45:31", "remaining_time": "0:18:57", "throughput": 2643.58, "total_tokens": 7221112} {"current_steps": 26940, "total_steps": 38150, "loss": 0.1948, "lr": 1.20393474728553e-05, "epoch": 7.061598951507208, "percentage": 70.62, "elapsed_time": "0:45:32", "remaining_time": "0:18:56", "throughput": 2643.7, "total_tokens": 7222696} {"current_steps": 26945, "total_steps": 38150, "loss": 0.1658, "lr": 1.2029568552986156e-05, "epoch": 7.062909567496724, "percentage": 70.63, "elapsed_time": "0:45:32", "remaining_time": "0:18:56", "throughput": 2643.73, "total_tokens": 7223928} {"current_steps": 26950, "total_steps": 38150, "loss": 0.1991, "lr": 1.2019792347805902e-05, "epoch": 7.064220183486238, "percentage": 70.64, "elapsed_time": "0:45:32", "remaining_time": "0:18:55", "throughput": 2643.76, "total_tokens": 7225160} {"current_steps": 26955, "total_steps": 38150, "loss": 0.2895, "lr": 1.2010018859360691e-05, "epoch": 7.065530799475754, "percentage": 70.66, "elapsed_time": "0:45:33", "remaining_time": "0:18:55", "throughput": 2643.86, "total_tokens": 7226728} {"current_steps": 26960, "total_steps": 38150, "loss": 0.1613, "lr": 1.2000248089696078e-05, "epoch": 7.066841415465269, "percentage": 70.67, "elapsed_time": "0:45:33", "remaining_time": "0:18:54", "throughput": 2643.89, "total_tokens": 7227944} {"current_steps": 26965, "total_steps": 38150, "loss": 0.1851, "lr": 1.1990480040857076e-05, "epoch": 7.068152031454784, "percentage": 70.68, "elapsed_time": "0:45:34", "remaining_time": "0:18:54", "throughput": 2643.93, "total_tokens": 7229208} {"current_steps": 26970, "total_steps": 38150, "loss": 0.1207, "lr": 1.1980714714888127e-05, "epoch": 7.069462647444299, "percentage": 70.69, "elapsed_time": "0:45:34", "remaining_time": "0:18:53", "throughput": 2643.99, "total_tokens": 7230616} {"current_steps": 26975, "total_steps": 38150, "loss": 0.2517, "lr": 1.197095211383309e-05, "epoch": 7.070773263433814, "percentage": 70.71, "elapsed_time": "0:45:35", "remaining_time": "0:18:53", "throughput": 2644.03, "total_tokens": 7231896} {"current_steps": 26980, "total_steps": 38150, "loss": 0.3097, "lr": 1.1961192239735264e-05, "epoch": 7.072083879423329, "percentage": 70.72, "elapsed_time": "0:45:35", "remaining_time": "0:18:52", "throughput": 2644.16, "total_tokens": 7233496} {"current_steps": 26985, "total_steps": 38150, "loss": 0.1559, "lr": 1.1951435094637373e-05, "epoch": 7.073394495412844, "percentage": 70.73, "elapsed_time": "0:45:36", "remaining_time": "0:18:52", "throughput": 2644.24, "total_tokens": 7234936} {"current_steps": 26990, "total_steps": 38150, "loss": 0.1997, "lr": 1.194168068058157e-05, "epoch": 7.074705111402359, "percentage": 70.75, "elapsed_time": "0:45:36", "remaining_time": "0:18:51", "throughput": 2644.29, "total_tokens": 7236200} {"current_steps": 26995, "total_steps": 38150, "loss": 0.1308, "lr": 1.1931928999609438e-05, "epoch": 7.076015727391874, "percentage": 70.76, "elapsed_time": "0:45:37", "remaining_time": "0:18:50", "throughput": 2644.37, "total_tokens": 7237672} {"current_steps": 27000, "total_steps": 38150, "loss": 0.1822, "lr": 1.1922180053761985e-05, "epoch": 7.077326343381389, "percentage": 70.77, "elapsed_time": "0:45:37", "remaining_time": "0:18:50", "throughput": 2644.43, "total_tokens": 7238952} {"current_steps": 27005, "total_steps": 38150, "loss": 0.3459, "lr": 1.1912433845079652e-05, "epoch": 7.078636959370904, "percentage": 70.79, "elapsed_time": "0:45:37", "remaining_time": "0:18:49", "throughput": 2644.49, "total_tokens": 7240296} {"current_steps": 27010, "total_steps": 38150, "loss": 0.2009, "lr": 1.19026903756023e-05, "epoch": 7.0799475753604195, "percentage": 70.8, "elapsed_time": "0:45:38", "remaining_time": "0:18:49", "throughput": 2644.49, "total_tokens": 7241448} {"current_steps": 27015, "total_steps": 38150, "loss": 0.1906, "lr": 1.1892949647369223e-05, "epoch": 7.081258191349934, "percentage": 70.81, "elapsed_time": "0:45:38", "remaining_time": "0:18:48", "throughput": 2644.57, "total_tokens": 7242920} {"current_steps": 27020, "total_steps": 38150, "loss": 0.1397, "lr": 1.1883211662419137e-05, "epoch": 7.08256880733945, "percentage": 70.83, "elapsed_time": "0:45:39", "remaining_time": "0:18:48", "throughput": 2644.69, "total_tokens": 7244488} {"current_steps": 27025, "total_steps": 38150, "loss": 0.2193, "lr": 1.1873476422790187e-05, "epoch": 7.083879423328964, "percentage": 70.84, "elapsed_time": "0:45:39", "remaining_time": "0:18:47", "throughput": 2644.77, "total_tokens": 7245928} {"current_steps": 27030, "total_steps": 38150, "loss": 0.269, "lr": 1.1863743930519939e-05, "epoch": 7.08519003931848, "percentage": 70.85, "elapsed_time": "0:45:40", "remaining_time": "0:18:47", "throughput": 2644.82, "total_tokens": 7247208} {"current_steps": 27035, "total_steps": 38150, "loss": 0.2256, "lr": 1.1854014187645398e-05, "epoch": 7.086500655307995, "percentage": 70.87, "elapsed_time": "0:45:40", "remaining_time": "0:18:46", "throughput": 2644.83, "total_tokens": 7248360} {"current_steps": 27040, "total_steps": 38150, "loss": 0.152, "lr": 1.1844287196202967e-05, "epoch": 7.08781127129751, "percentage": 70.88, "elapsed_time": "0:45:41", "remaining_time": "0:18:46", "throughput": 2644.9, "total_tokens": 7249800} {"current_steps": 27045, "total_steps": 38150, "loss": 0.1834, "lr": 1.183456295822849e-05, "epoch": 7.089121887287025, "percentage": 70.89, "elapsed_time": "0:45:41", "remaining_time": "0:18:45", "throughput": 2645.03, "total_tokens": 7251448} {"current_steps": 27050, "total_steps": 38150, "loss": 0.3464, "lr": 1.1824841475757232e-05, "epoch": 7.09043250327654, "percentage": 70.9, "elapsed_time": "0:45:41", "remaining_time": "0:18:45", "throughput": 2645.08, "total_tokens": 7252712} {"current_steps": 27055, "total_steps": 38150, "loss": 0.285, "lr": 1.1815122750823896e-05, "epoch": 7.091743119266055, "percentage": 70.92, "elapsed_time": "0:45:42", "remaining_time": "0:18:44", "throughput": 2645.3, "total_tokens": 7254968} {"current_steps": 27060, "total_steps": 38150, "loss": 0.1473, "lr": 1.1805406785462587e-05, "epoch": 7.0930537352555705, "percentage": 70.93, "elapsed_time": "0:45:43", "remaining_time": "0:18:44", "throughput": 2645.34, "total_tokens": 7256312} {"current_steps": 27065, "total_steps": 38150, "loss": 0.1764, "lr": 1.1795693581706838e-05, "epoch": 7.094364351245085, "percentage": 70.94, "elapsed_time": "0:45:43", "remaining_time": "0:18:43", "throughput": 2645.36, "total_tokens": 7257528} {"current_steps": 27070, "total_steps": 38150, "loss": 0.1618, "lr": 1.1785983141589618e-05, "epoch": 7.095674967234601, "percentage": 70.96, "elapsed_time": "0:45:43", "remaining_time": "0:18:43", "throughput": 2645.41, "total_tokens": 7258808} {"current_steps": 27075, "total_steps": 38150, "loss": 0.2039, "lr": 1.1776275467143283e-05, "epoch": 7.096985583224115, "percentage": 70.97, "elapsed_time": "0:45:44", "remaining_time": "0:18:42", "throughput": 2645.47, "total_tokens": 7260200} {"current_steps": 27080, "total_steps": 38150, "loss": 0.1725, "lr": 1.1766570560399647e-05, "epoch": 7.09829619921363, "percentage": 70.98, "elapsed_time": "0:45:44", "remaining_time": "0:18:42", "throughput": 2645.46, "total_tokens": 7261320} {"current_steps": 27085, "total_steps": 38150, "loss": 0.2187, "lr": 1.1756868423389925e-05, "epoch": 7.0996068152031455, "percentage": 71.0, "elapsed_time": "0:45:45", "remaining_time": "0:18:41", "throughput": 2645.49, "total_tokens": 7262696} {"current_steps": 27090, "total_steps": 38150, "loss": 0.2456, "lr": 1.1747169058144761e-05, "epoch": 7.10091743119266, "percentage": 71.01, "elapsed_time": "0:45:45", "remaining_time": "0:18:40", "throughput": 2645.53, "total_tokens": 7263944} {"current_steps": 27095, "total_steps": 38150, "loss": 0.2765, "lr": 1.1737472466694213e-05, "epoch": 7.102228047182176, "percentage": 71.02, "elapsed_time": "0:45:46", "remaining_time": "0:18:40", "throughput": 2645.54, "total_tokens": 7265112} {"current_steps": 27100, "total_steps": 38150, "loss": 0.13, "lr": 1.1727778651067761e-05, "epoch": 7.10353866317169, "percentage": 71.04, "elapsed_time": "0:45:46", "remaining_time": "0:18:39", "throughput": 2645.57, "total_tokens": 7266424} {"current_steps": 27105, "total_steps": 38150, "loss": 0.2217, "lr": 1.1718087613294307e-05, "epoch": 7.104849279161206, "percentage": 71.05, "elapsed_time": "0:45:47", "remaining_time": "0:18:39", "throughput": 2645.66, "total_tokens": 7267848} {"current_steps": 27110, "total_steps": 38150, "loss": 0.1891, "lr": 1.1708399355402163e-05, "epoch": 7.1061598951507206, "percentage": 71.06, "elapsed_time": "0:45:47", "remaining_time": "0:18:38", "throughput": 2645.79, "total_tokens": 7269416} {"current_steps": 27115, "total_steps": 38150, "loss": 0.2248, "lr": 1.1698713879419072e-05, "epoch": 7.107470511140236, "percentage": 71.07, "elapsed_time": "0:45:48", "remaining_time": "0:18:38", "throughput": 2645.92, "total_tokens": 7271032} {"current_steps": 27120, "total_steps": 38150, "loss": 0.2056, "lr": 1.168903118737218e-05, "epoch": 7.108781127129751, "percentage": 71.09, "elapsed_time": "0:45:48", "remaining_time": "0:18:37", "throughput": 2645.95, "total_tokens": 7272216} {"current_steps": 27125, "total_steps": 38150, "loss": 0.2296, "lr": 1.1679351281288062e-05, "epoch": 7.110091743119266, "percentage": 71.1, "elapsed_time": "0:45:48", "remaining_time": "0:18:37", "throughput": 2646.06, "total_tokens": 7273688} {"current_steps": 27130, "total_steps": 38150, "loss": 0.3088, "lr": 1.1669674163192703e-05, "epoch": 7.111402359108781, "percentage": 71.11, "elapsed_time": "0:45:49", "remaining_time": "0:18:36", "throughput": 2646.06, "total_tokens": 7274808} {"current_steps": 27135, "total_steps": 38150, "loss": 0.2584, "lr": 1.165999983511151e-05, "epoch": 7.1127129750982965, "percentage": 71.13, "elapsed_time": "0:45:49", "remaining_time": "0:18:36", "throughput": 2646.21, "total_tokens": 7276664} {"current_steps": 27140, "total_steps": 38150, "loss": 0.1587, "lr": 1.1650328299069301e-05, "epoch": 7.114023591087811, "percentage": 71.14, "elapsed_time": "0:45:50", "remaining_time": "0:18:35", "throughput": 2646.24, "total_tokens": 7277912} {"current_steps": 27145, "total_steps": 38150, "loss": 0.1902, "lr": 1.1640659557090313e-05, "epoch": 7.115334207077327, "percentage": 71.15, "elapsed_time": "0:45:50", "remaining_time": "0:18:35", "throughput": 2646.21, "total_tokens": 7278920} {"current_steps": 27150, "total_steps": 38150, "loss": 0.2516, "lr": 1.1630993611198207e-05, "epoch": 7.116644823066841, "percentage": 71.17, "elapsed_time": "0:45:51", "remaining_time": "0:18:34", "throughput": 2646.26, "total_tokens": 7280184} {"current_steps": 27155, "total_steps": 38150, "loss": 0.2499, "lr": 1.1621330463416027e-05, "epoch": 7.117955439056357, "percentage": 71.18, "elapsed_time": "0:45:51", "remaining_time": "0:18:34", "throughput": 2646.37, "total_tokens": 7281736} {"current_steps": 27160, "total_steps": 38150, "loss": 0.1696, "lr": 1.1611670115766265e-05, "epoch": 7.1192660550458715, "percentage": 71.19, "elapsed_time": "0:45:52", "remaining_time": "0:18:33", "throughput": 2646.43, "total_tokens": 7283112} {"current_steps": 27165, "total_steps": 38150, "loss": 0.1217, "lr": 1.1602012570270806e-05, "epoch": 7.120576671035387, "percentage": 71.21, "elapsed_time": "0:45:52", "remaining_time": "0:18:33", "throughput": 2646.41, "total_tokens": 7284136} {"current_steps": 27170, "total_steps": 38150, "loss": 0.309, "lr": 1.1592357828950976e-05, "epoch": 7.121887287024902, "percentage": 71.22, "elapsed_time": "0:45:52", "remaining_time": "0:18:32", "throughput": 2646.48, "total_tokens": 7285576} {"current_steps": 27175, "total_steps": 38150, "loss": 0.1087, "lr": 1.1582705893827483e-05, "epoch": 7.123197903014416, "percentage": 71.23, "elapsed_time": "0:45:53", "remaining_time": "0:18:31", "throughput": 2646.5, "total_tokens": 7286856} {"current_steps": 27180, "total_steps": 38150, "loss": 0.1441, "lr": 1.1573056766920465e-05, "epoch": 7.124508519003932, "percentage": 71.25, "elapsed_time": "0:45:53", "remaining_time": "0:18:31", "throughput": 2646.55, "total_tokens": 7288168} {"current_steps": 27185, "total_steps": 38150, "loss": 0.1315, "lr": 1.1563410450249468e-05, "epoch": 7.1258191349934465, "percentage": 71.26, "elapsed_time": "0:45:54", "remaining_time": "0:18:30", "throughput": 2646.6, "total_tokens": 7289448} {"current_steps": 27190, "total_steps": 38150, "loss": 0.2045, "lr": 1.1553766945833452e-05, "epoch": 7.127129750982962, "percentage": 71.27, "elapsed_time": "0:45:54", "remaining_time": "0:18:30", "throughput": 2646.63, "total_tokens": 7290744} {"current_steps": 27195, "total_steps": 38150, "loss": 0.1627, "lr": 1.1544126255690774e-05, "epoch": 7.128440366972477, "percentage": 71.28, "elapsed_time": "0:45:55", "remaining_time": "0:18:29", "throughput": 2646.74, "total_tokens": 7292296} {"current_steps": 27200, "total_steps": 38150, "loss": 0.1334, "lr": 1.153448838183922e-05, "epoch": 7.129750982961992, "percentage": 71.3, "elapsed_time": "0:45:55", "remaining_time": "0:18:29", "throughput": 2646.72, "total_tokens": 7293336} {"current_steps": 27205, "total_steps": 38150, "loss": 0.1313, "lr": 1.1524853326295982e-05, "epoch": 7.131061598951507, "percentage": 71.31, "elapsed_time": "0:45:56", "remaining_time": "0:18:28", "throughput": 2646.69, "total_tokens": 7294392} {"current_steps": 27210, "total_steps": 38150, "loss": 0.1533, "lr": 1.151522109107766e-05, "epoch": 7.1323722149410225, "percentage": 71.32, "elapsed_time": "0:45:56", "remaining_time": "0:18:28", "throughput": 2646.76, "total_tokens": 7295816} {"current_steps": 27215, "total_steps": 38150, "loss": 0.3287, "lr": 1.150559167820026e-05, "epoch": 7.133682830930537, "percentage": 71.34, "elapsed_time": "0:45:56", "remaining_time": "0:18:27", "throughput": 2646.85, "total_tokens": 7297320} {"current_steps": 27220, "total_steps": 38150, "loss": 0.165, "lr": 1.14959650896792e-05, "epoch": 7.134993446920053, "percentage": 71.35, "elapsed_time": "0:45:57", "remaining_time": "0:18:27", "throughput": 2646.84, "total_tokens": 7298440} {"current_steps": 27225, "total_steps": 38150, "loss": 0.1604, "lr": 1.1486341327529332e-05, "epoch": 7.136304062909567, "percentage": 71.36, "elapsed_time": "0:45:57", "remaining_time": "0:18:26", "throughput": 2646.96, "total_tokens": 7300104} {"current_steps": 27230, "total_steps": 38150, "loss": 0.1601, "lr": 1.1476720393764864e-05, "epoch": 7.137614678899083, "percentage": 71.38, "elapsed_time": "0:45:58", "remaining_time": "0:18:26", "throughput": 2646.95, "total_tokens": 7301224} {"current_steps": 27235, "total_steps": 38150, "loss": 0.1689, "lr": 1.146710229039945e-05, "epoch": 7.1389252948885975, "percentage": 71.39, "elapsed_time": "0:45:58", "remaining_time": "0:18:25", "throughput": 2647.01, "total_tokens": 7302616} {"current_steps": 27240, "total_steps": 38150, "loss": 0.2531, "lr": 1.1457487019446145e-05, "epoch": 7.140235910878113, "percentage": 71.4, "elapsed_time": "0:45:59", "remaining_time": "0:18:25", "throughput": 2647.02, "total_tokens": 7303752} {"current_steps": 27245, "total_steps": 38150, "loss": 0.1603, "lr": 1.1447874582917407e-05, "epoch": 7.141546526867628, "percentage": 71.42, "elapsed_time": "0:45:59", "remaining_time": "0:18:24", "throughput": 2647.05, "total_tokens": 7304968} {"current_steps": 27250, "total_steps": 38150, "loss": 0.1795, "lr": 1.1438264982825104e-05, "epoch": 7.142857142857143, "percentage": 71.43, "elapsed_time": "0:46:00", "remaining_time": "0:18:24", "throughput": 2647.09, "total_tokens": 7306248} {"current_steps": 27255, "total_steps": 38150, "loss": 0.1637, "lr": 1.1428658221180506e-05, "epoch": 7.144167758846658, "percentage": 71.44, "elapsed_time": "0:46:00", "remaining_time": "0:18:23", "throughput": 2647.26, "total_tokens": 7308120} {"current_steps": 27260, "total_steps": 38150, "loss": 0.1886, "lr": 1.1419054299994292e-05, "epoch": 7.145478374836173, "percentage": 71.45, "elapsed_time": "0:46:01", "remaining_time": "0:18:23", "throughput": 2647.22, "total_tokens": 7309144} {"current_steps": 27265, "total_steps": 38150, "loss": 0.2679, "lr": 1.1409453221276545e-05, "epoch": 7.146788990825688, "percentage": 71.47, "elapsed_time": "0:46:01", "remaining_time": "0:18:22", "throughput": 2647.3, "total_tokens": 7310632} {"current_steps": 27270, "total_steps": 38150, "loss": 0.191, "lr": 1.1399854987036768e-05, "epoch": 7.148099606815203, "percentage": 71.48, "elapsed_time": "0:46:01", "remaining_time": "0:18:21", "throughput": 2647.33, "total_tokens": 7311848} {"current_steps": 27275, "total_steps": 38150, "loss": 0.2328, "lr": 1.1390259599283835e-05, "epoch": 7.149410222804718, "percentage": 71.49, "elapsed_time": "0:46:02", "remaining_time": "0:18:21", "throughput": 2647.35, "total_tokens": 7313048} {"current_steps": 27280, "total_steps": 38150, "loss": 0.2022, "lr": 1.1380667060026041e-05, "epoch": 7.150720838794233, "percentage": 71.51, "elapsed_time": "0:46:02", "remaining_time": "0:18:20", "throughput": 2647.29, "total_tokens": 7313992} {"current_steps": 27285, "total_steps": 38150, "loss": 0.1891, "lr": 1.1371077371271108e-05, "epoch": 7.1520314547837485, "percentage": 71.52, "elapsed_time": "0:46:03", "remaining_time": "0:18:20", "throughput": 2647.36, "total_tokens": 7315464} {"current_steps": 27290, "total_steps": 38150, "loss": 0.24, "lr": 1.136149053502613e-05, "epoch": 7.153342070773263, "percentage": 71.53, "elapsed_time": "0:46:03", "remaining_time": "0:18:19", "throughput": 2647.41, "total_tokens": 7316840} {"current_steps": 27295, "total_steps": 38150, "loss": 0.2042, "lr": 1.1351906553297622e-05, "epoch": 7.154652686762779, "percentage": 71.55, "elapsed_time": "0:46:04", "remaining_time": "0:18:19", "throughput": 2647.46, "total_tokens": 7318232} {"current_steps": 27300, "total_steps": 38150, "loss": 0.1329, "lr": 1.1342325428091488e-05, "epoch": 7.155963302752293, "percentage": 71.56, "elapsed_time": "0:46:04", "remaining_time": "0:18:18", "throughput": 2647.45, "total_tokens": 7319320} {"current_steps": 27305, "total_steps": 38150, "loss": 0.1377, "lr": 1.1332747161413054e-05, "epoch": 7.157273918741809, "percentage": 71.57, "elapsed_time": "0:46:05", "remaining_time": "0:18:18", "throughput": 2647.5, "total_tokens": 7320600} {"current_steps": 27310, "total_steps": 38150, "loss": 0.1657, "lr": 1.1323171755267015e-05, "epoch": 7.1585845347313235, "percentage": 71.59, "elapsed_time": "0:46:05", "remaining_time": "0:18:17", "throughput": 2647.6, "total_tokens": 7322072} {"current_steps": 27315, "total_steps": 38150, "loss": 0.175, "lr": 1.1313599211657494e-05, "epoch": 7.159895150720839, "percentage": 71.6, "elapsed_time": "0:46:05", "remaining_time": "0:18:17", "throughput": 2647.55, "total_tokens": 7323032} {"current_steps": 27320, "total_steps": 38150, "loss": 0.23, "lr": 1.130402953258801e-05, "epoch": 7.161205766710354, "percentage": 71.61, "elapsed_time": "0:46:06", "remaining_time": "0:18:16", "throughput": 2647.62, "total_tokens": 7324472} {"current_steps": 27325, "total_steps": 38150, "loss": 0.3354, "lr": 1.129446272006148e-05, "epoch": 7.162516382699869, "percentage": 71.63, "elapsed_time": "0:46:06", "remaining_time": "0:18:16", "throughput": 2647.66, "total_tokens": 7325704} {"current_steps": 27330, "total_steps": 38150, "loss": 0.2089, "lr": 1.1284898776080222e-05, "epoch": 7.163826998689384, "percentage": 71.64, "elapsed_time": "0:46:07", "remaining_time": "0:18:15", "throughput": 2647.79, "total_tokens": 7327368} {"current_steps": 27335, "total_steps": 38150, "loss": 0.2753, "lr": 1.127533770264594e-05, "epoch": 7.165137614678899, "percentage": 71.65, "elapsed_time": "0:46:07", "remaining_time": "0:18:15", "throughput": 2647.83, "total_tokens": 7328664} {"current_steps": 27340, "total_steps": 38150, "loss": 0.2379, "lr": 1.1265779501759786e-05, "epoch": 7.166448230668414, "percentage": 71.66, "elapsed_time": "0:46:08", "remaining_time": "0:18:14", "throughput": 2647.87, "total_tokens": 7329912} {"current_steps": 27345, "total_steps": 38150, "loss": 0.2183, "lr": 1.125622417542224e-05, "epoch": 7.16775884665793, "percentage": 71.68, "elapsed_time": "0:46:08", "remaining_time": "0:18:13", "throughput": 2647.93, "total_tokens": 7331208} {"current_steps": 27350, "total_steps": 38150, "loss": 0.1394, "lr": 1.1246671725633227e-05, "epoch": 7.169069462647444, "percentage": 71.69, "elapsed_time": "0:46:09", "remaining_time": "0:18:13", "throughput": 2647.89, "total_tokens": 7332216} {"current_steps": 27355, "total_steps": 38150, "loss": 0.0815, "lr": 1.1237122154392058e-05, "epoch": 7.17038007863696, "percentage": 71.7, "elapsed_time": "0:46:09", "remaining_time": "0:18:12", "throughput": 2647.98, "total_tokens": 7333784} {"current_steps": 27360, "total_steps": 38150, "loss": 0.2731, "lr": 1.122757546369744e-05, "epoch": 7.1716906946264745, "percentage": 71.72, "elapsed_time": "0:46:10", "remaining_time": "0:18:12", "throughput": 2648.1, "total_tokens": 7335304} {"current_steps": 27365, "total_steps": 38150, "loss": 0.1741, "lr": 1.1218031655547482e-05, "epoch": 7.173001310615989, "percentage": 71.73, "elapsed_time": "0:46:10", "remaining_time": "0:18:11", "throughput": 2648.15, "total_tokens": 7336680} {"current_steps": 27370, "total_steps": 38150, "loss": 0.2598, "lr": 1.1208490731939683e-05, "epoch": 7.174311926605505, "percentage": 71.74, "elapsed_time": "0:46:10", "remaining_time": "0:18:11", "throughput": 2648.23, "total_tokens": 7338088} {"current_steps": 27375, "total_steps": 38150, "loss": 0.2378, "lr": 1.1198952694870945e-05, "epoch": 7.175622542595019, "percentage": 71.76, "elapsed_time": "0:46:11", "remaining_time": "0:18:10", "throughput": 2648.29, "total_tokens": 7339384} {"current_steps": 27380, "total_steps": 38150, "loss": 0.296, "lr": 1.1189417546337564e-05, "epoch": 7.176933158584535, "percentage": 71.77, "elapsed_time": "0:46:11", "remaining_time": "0:18:10", "throughput": 2648.3, "total_tokens": 7340648} {"current_steps": 27385, "total_steps": 38150, "loss": 0.1499, "lr": 1.1179885288335235e-05, "epoch": 7.1782437745740495, "percentage": 71.78, "elapsed_time": "0:46:12", "remaining_time": "0:18:09", "throughput": 2648.33, "total_tokens": 7341912} {"current_steps": 27390, "total_steps": 38150, "loss": 0.2171, "lr": 1.1170355922859024e-05, "epoch": 7.179554390563565, "percentage": 71.8, "elapsed_time": "0:46:12", "remaining_time": "0:18:09", "throughput": 2648.39, "total_tokens": 7343272} {"current_steps": 27395, "total_steps": 38150, "loss": 0.2155, "lr": 1.1160829451903418e-05, "epoch": 7.18086500655308, "percentage": 71.81, "elapsed_time": "0:46:13", "remaining_time": "0:18:08", "throughput": 2648.48, "total_tokens": 7344696} {"current_steps": 27400, "total_steps": 38150, "loss": 0.2028, "lr": 1.1151305877462304e-05, "epoch": 7.182175622542595, "percentage": 71.82, "elapsed_time": "0:46:13", "remaining_time": "0:18:08", "throughput": 2648.54, "total_tokens": 7346008} {"current_steps": 27405, "total_steps": 38150, "loss": 0.1748, "lr": 1.1141785201528936e-05, "epoch": 7.18348623853211, "percentage": 71.83, "elapsed_time": "0:46:14", "remaining_time": "0:18:07", "throughput": 2648.63, "total_tokens": 7347512} {"current_steps": 27410, "total_steps": 38150, "loss": 0.1957, "lr": 1.1132267426095985e-05, "epoch": 7.184796854521625, "percentage": 71.85, "elapsed_time": "0:46:14", "remaining_time": "0:18:07", "throughput": 2648.71, "total_tokens": 7348936} {"current_steps": 27415, "total_steps": 38150, "loss": 0.1258, "lr": 1.11227525531555e-05, "epoch": 7.18610747051114, "percentage": 71.86, "elapsed_time": "0:46:14", "remaining_time": "0:18:06", "throughput": 2648.75, "total_tokens": 7350184} {"current_steps": 27420, "total_steps": 38150, "loss": 0.1542, "lr": 1.1113240584698927e-05, "epoch": 7.187418086500656, "percentage": 71.87, "elapsed_time": "0:46:15", "remaining_time": "0:18:06", "throughput": 2648.79, "total_tokens": 7351432} {"current_steps": 27425, "total_steps": 38150, "loss": 0.1408, "lr": 1.1103731522717115e-05, "epoch": 7.18872870249017, "percentage": 71.89, "elapsed_time": "0:46:15", "remaining_time": "0:18:05", "throughput": 2648.77, "total_tokens": 7352504} {"current_steps": 27430, "total_steps": 38150, "loss": 0.1875, "lr": 1.1094225369200272e-05, "epoch": 7.190039318479686, "percentage": 71.9, "elapsed_time": "0:46:16", "remaining_time": "0:18:05", "throughput": 2648.86, "total_tokens": 7354024} {"current_steps": 27435, "total_steps": 38150, "loss": 0.2945, "lr": 1.1084722126138037e-05, "epoch": 7.1913499344692005, "percentage": 71.91, "elapsed_time": "0:46:16", "remaining_time": "0:18:04", "throughput": 2648.89, "total_tokens": 7355336} {"current_steps": 27440, "total_steps": 38150, "loss": 0.2579, "lr": 1.1075221795519413e-05, "epoch": 7.192660550458716, "percentage": 71.93, "elapsed_time": "0:46:17", "remaining_time": "0:18:03", "throughput": 2648.95, "total_tokens": 7356696} {"current_steps": 27445, "total_steps": 38150, "loss": 0.1969, "lr": 1.106572437933281e-05, "epoch": 7.193971166448231, "percentage": 71.94, "elapsed_time": "0:46:17", "remaining_time": "0:18:03", "throughput": 2649.07, "total_tokens": 7358312} {"current_steps": 27450, "total_steps": 38150, "loss": 0.1944, "lr": 1.1056229879566004e-05, "epoch": 7.195281782437746, "percentage": 71.95, "elapsed_time": "0:46:18", "remaining_time": "0:18:02", "throughput": 2649.09, "total_tokens": 7359512} {"current_steps": 27455, "total_steps": 38150, "loss": 0.2503, "lr": 1.1046738298206205e-05, "epoch": 7.196592398427261, "percentage": 71.97, "elapsed_time": "0:46:18", "remaining_time": "0:18:02", "throughput": 2649.14, "total_tokens": 7360808} {"current_steps": 27460, "total_steps": 38150, "loss": 0.2688, "lr": 1.103724963723998e-05, "epoch": 7.1979030144167755, "percentage": 71.98, "elapsed_time": "0:46:19", "remaining_time": "0:18:01", "throughput": 2649.21, "total_tokens": 7362408} {"current_steps": 27465, "total_steps": 38150, "loss": 0.1972, "lr": 1.1027763898653268e-05, "epoch": 7.199213630406291, "percentage": 71.99, "elapsed_time": "0:46:19", "remaining_time": "0:18:01", "throughput": 2649.34, "total_tokens": 7364184} {"current_steps": 27470, "total_steps": 38150, "loss": 0.1447, "lr": 1.1018281084431432e-05, "epoch": 7.200524246395806, "percentage": 72.01, "elapsed_time": "0:46:20", "remaining_time": "0:18:00", "throughput": 2649.31, "total_tokens": 7365208} {"current_steps": 27475, "total_steps": 38150, "loss": 0.1481, "lr": 1.1008801196559204e-05, "epoch": 7.201834862385321, "percentage": 72.02, "elapsed_time": "0:46:20", "remaining_time": "0:18:00", "throughput": 2649.28, "total_tokens": 7366264} {"current_steps": 27480, "total_steps": 38150, "loss": 0.2973, "lr": 1.0999324237020714e-05, "epoch": 7.203145478374836, "percentage": 72.03, "elapsed_time": "0:46:21", "remaining_time": "0:17:59", "throughput": 2649.47, "total_tokens": 7368328} {"current_steps": 27485, "total_steps": 38150, "loss": 0.2165, "lr": 1.0989850207799469e-05, "epoch": 7.204456094364351, "percentage": 72.04, "elapsed_time": "0:46:21", "remaining_time": "0:17:59", "throughput": 2649.65, "total_tokens": 7370296} {"current_steps": 27490, "total_steps": 38150, "loss": 0.2562, "lr": 1.0980379110878366e-05, "epoch": 7.205766710353866, "percentage": 72.06, "elapsed_time": "0:46:22", "remaining_time": "0:17:58", "throughput": 2649.58, "total_tokens": 7371176} {"current_steps": 27495, "total_steps": 38150, "loss": 0.2192, "lr": 1.0970910948239694e-05, "epoch": 7.207077326343382, "percentage": 72.07, "elapsed_time": "0:46:22", "remaining_time": "0:17:58", "throughput": 2649.58, "total_tokens": 7372312} {"current_steps": 27500, "total_steps": 38150, "loss": 0.2158, "lr": 1.0961445721865116e-05, "epoch": 7.208387942332896, "percentage": 72.08, "elapsed_time": "0:46:22", "remaining_time": "0:17:57", "throughput": 2649.61, "total_tokens": 7373544} {"current_steps": 27505, "total_steps": 38150, "loss": 0.1245, "lr": 1.0951983433735704e-05, "epoch": 7.209698558322412, "percentage": 72.1, "elapsed_time": "0:46:23", "remaining_time": "0:17:57", "throughput": 2649.67, "total_tokens": 7374888} {"current_steps": 27510, "total_steps": 38150, "loss": 0.2076, "lr": 1.0942524085831868e-05, "epoch": 7.2110091743119265, "percentage": 72.11, "elapsed_time": "0:46:23", "remaining_time": "0:17:56", "throughput": 2649.77, "total_tokens": 7376504} {"current_steps": 27515, "total_steps": 38150, "loss": 0.1208, "lr": 1.0933067680133457e-05, "epoch": 7.212319790301442, "percentage": 72.12, "elapsed_time": "0:46:24", "remaining_time": "0:17:56", "throughput": 2649.8, "total_tokens": 7377752} {"current_steps": 27520, "total_steps": 38150, "loss": 0.0839, "lr": 1.092361421861968e-05, "epoch": 7.213630406290957, "percentage": 72.14, "elapsed_time": "0:46:24", "remaining_time": "0:17:55", "throughput": 2649.82, "total_tokens": 7378952} {"current_steps": 27525, "total_steps": 38150, "loss": 0.1615, "lr": 1.091416370326912e-05, "epoch": 7.214941022280472, "percentage": 72.15, "elapsed_time": "0:46:25", "remaining_time": "0:17:55", "throughput": 2649.93, "total_tokens": 7380520} {"current_steps": 27530, "total_steps": 38150, "loss": 0.2517, "lr": 1.090471613605976e-05, "epoch": 7.216251638269987, "percentage": 72.16, "elapsed_time": "0:46:25", "remaining_time": "0:17:54", "throughput": 2650.03, "total_tokens": 7382008} {"current_steps": 27535, "total_steps": 38150, "loss": 0.1053, "lr": 1.0895271518968962e-05, "epoch": 7.217562254259502, "percentage": 72.18, "elapsed_time": "0:46:26", "remaining_time": "0:17:54", "throughput": 2650.11, "total_tokens": 7383592} {"current_steps": 27540, "total_steps": 38150, "loss": 0.1452, "lr": 1.0885829853973467e-05, "epoch": 7.218872870249017, "percentage": 72.19, "elapsed_time": "0:46:26", "remaining_time": "0:17:53", "throughput": 2650.12, "total_tokens": 7384728} {"current_steps": 27545, "total_steps": 38150, "loss": 0.2641, "lr": 1.087639114304939e-05, "epoch": 7.220183486238533, "percentage": 72.2, "elapsed_time": "0:46:26", "remaining_time": "0:17:53", "throughput": 2650.13, "total_tokens": 7385880} {"current_steps": 27550, "total_steps": 38150, "loss": 0.1869, "lr": 1.0866955388172245e-05, "epoch": 7.221494102228047, "percentage": 72.21, "elapsed_time": "0:46:27", "remaining_time": "0:17:52", "throughput": 2650.13, "total_tokens": 7387000} {"current_steps": 27555, "total_steps": 38150, "loss": 0.1027, "lr": 1.0857522591316915e-05, "epoch": 7.222804718217562, "percentage": 72.23, "elapsed_time": "0:46:27", "remaining_time": "0:17:51", "throughput": 2650.22, "total_tokens": 7388520} {"current_steps": 27560, "total_steps": 38150, "loss": 0.1551, "lr": 1.084809275445767e-05, "epoch": 7.224115334207077, "percentage": 72.24, "elapsed_time": "0:46:28", "remaining_time": "0:17:51", "throughput": 2650.25, "total_tokens": 7389832} {"current_steps": 27565, "total_steps": 38150, "loss": 0.2918, "lr": 1.083866587956815e-05, "epoch": 7.225425950196592, "percentage": 72.25, "elapsed_time": "0:46:28", "remaining_time": "0:17:50", "throughput": 2650.17, "total_tokens": 7390712} {"current_steps": 27570, "total_steps": 38150, "loss": 0.2457, "lr": 1.0829241968621401e-05, "epoch": 7.226736566186108, "percentage": 72.27, "elapsed_time": "0:46:29", "remaining_time": "0:17:50", "throughput": 2650.28, "total_tokens": 7392344} {"current_steps": 27575, "total_steps": 38150, "loss": 0.1967, "lr": 1.0819821023589832e-05, "epoch": 7.228047182175622, "percentage": 72.28, "elapsed_time": "0:46:29", "remaining_time": "0:17:49", "throughput": 2650.34, "total_tokens": 7393736} {"current_steps": 27580, "total_steps": 38150, "loss": 0.1861, "lr": 1.0810403046445214e-05, "epoch": 7.229357798165138, "percentage": 72.29, "elapsed_time": "0:46:30", "remaining_time": "0:17:49", "throughput": 2650.43, "total_tokens": 7395256} {"current_steps": 27585, "total_steps": 38150, "loss": 0.0758, "lr": 1.0800988039158719e-05, "epoch": 7.2306684141546524, "percentage": 72.31, "elapsed_time": "0:46:30", "remaining_time": "0:17:48", "throughput": 2650.5, "total_tokens": 7396712} {"current_steps": 27590, "total_steps": 38150, "loss": 0.1967, "lr": 1.0791576003700895e-05, "epoch": 7.231979030144168, "percentage": 72.32, "elapsed_time": "0:46:31", "remaining_time": "0:17:48", "throughput": 2650.49, "total_tokens": 7397832} {"current_steps": 27595, "total_steps": 38150, "loss": 0.1306, "lr": 1.0782166942041663e-05, "epoch": 7.233289646133683, "percentage": 72.33, "elapsed_time": "0:46:31", "remaining_time": "0:17:47", "throughput": 2650.47, "total_tokens": 7398904} {"current_steps": 27600, "total_steps": 38150, "loss": 0.2022, "lr": 1.0772760856150322e-05, "epoch": 7.234600262123198, "percentage": 72.35, "elapsed_time": "0:46:31", "remaining_time": "0:17:47", "throughput": 2650.43, "total_tokens": 7399896} {"current_steps": 27605, "total_steps": 38150, "loss": 0.2159, "lr": 1.0763357747995551e-05, "epoch": 7.235910878112713, "percentage": 72.36, "elapsed_time": "0:46:32", "remaining_time": "0:17:46", "throughput": 2650.43, "total_tokens": 7401128} {"current_steps": 27610, "total_steps": 38150, "loss": 0.3994, "lr": 1.0753957619545405e-05, "epoch": 7.237221494102228, "percentage": 72.37, "elapsed_time": "0:46:32", "remaining_time": "0:17:46", "throughput": 2650.53, "total_tokens": 7402632} {"current_steps": 27615, "total_steps": 38150, "loss": 0.165, "lr": 1.0744560472767315e-05, "epoch": 7.238532110091743, "percentage": 72.39, "elapsed_time": "0:46:33", "remaining_time": "0:17:45", "throughput": 2650.57, "total_tokens": 7403960} {"current_steps": 27620, "total_steps": 38150, "loss": 0.1357, "lr": 1.0735166309628083e-05, "epoch": 7.239842726081259, "percentage": 72.4, "elapsed_time": "0:46:33", "remaining_time": "0:17:45", "throughput": 2650.56, "total_tokens": 7405064} {"current_steps": 27625, "total_steps": 38150, "loss": 0.2458, "lr": 1.0725775132093899e-05, "epoch": 7.241153342070773, "percentage": 72.41, "elapsed_time": "0:46:34", "remaining_time": "0:17:44", "throughput": 2650.63, "total_tokens": 7406504} {"current_steps": 27630, "total_steps": 38150, "loss": 0.1627, "lr": 1.0716386942130313e-05, "epoch": 7.242463958060289, "percentage": 72.42, "elapsed_time": "0:46:34", "remaining_time": "0:17:44", "throughput": 2650.71, "total_tokens": 7407928} {"current_steps": 27635, "total_steps": 38150, "loss": 0.2083, "lr": 1.0707001741702261e-05, "epoch": 7.243774574049803, "percentage": 72.44, "elapsed_time": "0:46:35", "remaining_time": "0:17:43", "throughput": 2650.8, "total_tokens": 7409432} {"current_steps": 27640, "total_steps": 38150, "loss": 0.2418, "lr": 1.0697619532774047e-05, "epoch": 7.245085190039318, "percentage": 72.45, "elapsed_time": "0:46:35", "remaining_time": "0:17:43", "throughput": 2650.81, "total_tokens": 7410600} {"current_steps": 27645, "total_steps": 38150, "loss": 0.2335, "lr": 1.0688240317309355e-05, "epoch": 7.246395806028834, "percentage": 72.46, "elapsed_time": "0:46:36", "remaining_time": "0:17:42", "throughput": 2650.82, "total_tokens": 7411736} {"current_steps": 27650, "total_steps": 38150, "loss": 0.3001, "lr": 1.0678864097271234e-05, "epoch": 7.247706422018348, "percentage": 72.48, "elapsed_time": "0:46:36", "remaining_time": "0:17:41", "throughput": 2650.95, "total_tokens": 7413304} {"current_steps": 27655, "total_steps": 38150, "loss": 0.1159, "lr": 1.0669490874622112e-05, "epoch": 7.249017038007864, "percentage": 72.49, "elapsed_time": "0:46:36", "remaining_time": "0:17:41", "throughput": 2651.01, "total_tokens": 7414744} {"current_steps": 27660, "total_steps": 38150, "loss": 0.1686, "lr": 1.0660120651323799e-05, "epoch": 7.250327653997378, "percentage": 72.5, "elapsed_time": "0:46:37", "remaining_time": "0:17:40", "throughput": 2650.96, "total_tokens": 7415720} {"current_steps": 27665, "total_steps": 38150, "loss": 0.241, "lr": 1.0650753429337446e-05, "epoch": 7.251638269986894, "percentage": 72.52, "elapsed_time": "0:46:37", "remaining_time": "0:17:40", "throughput": 2651.04, "total_tokens": 7417160} {"current_steps": 27670, "total_steps": 38150, "loss": 0.1937, "lr": 1.0641389210623607e-05, "epoch": 7.252948885976409, "percentage": 72.53, "elapsed_time": "0:46:38", "remaining_time": "0:17:39", "throughput": 2651.12, "total_tokens": 7418696} {"current_steps": 27675, "total_steps": 38150, "loss": 0.1605, "lr": 1.0632027997142196e-05, "epoch": 7.254259501965924, "percentage": 72.54, "elapsed_time": "0:46:38", "remaining_time": "0:17:39", "throughput": 2651.22, "total_tokens": 7420264} {"current_steps": 27680, "total_steps": 38150, "loss": 0.2174, "lr": 1.062266979085249e-05, "epoch": 7.255570117955439, "percentage": 72.56, "elapsed_time": "0:46:39", "remaining_time": "0:17:38", "throughput": 2651.15, "total_tokens": 7421160} {"current_steps": 27685, "total_steps": 38150, "loss": 0.1205, "lr": 1.0613314593713164e-05, "epoch": 7.256880733944954, "percentage": 72.57, "elapsed_time": "0:46:39", "remaining_time": "0:17:38", "throughput": 2651.15, "total_tokens": 7422360} {"current_steps": 27690, "total_steps": 38150, "loss": 0.3324, "lr": 1.0603962407682236e-05, "epoch": 7.258191349934469, "percentage": 72.58, "elapsed_time": "0:46:40", "remaining_time": "0:17:37", "throughput": 2651.22, "total_tokens": 7423720} {"current_steps": 27695, "total_steps": 38150, "loss": 0.1885, "lr": 1.059461323471711e-05, "epoch": 7.259501965923985, "percentage": 72.6, "elapsed_time": "0:46:40", "remaining_time": "0:17:37", "throughput": 2651.34, "total_tokens": 7425336} {"current_steps": 27700, "total_steps": 38150, "loss": 0.3251, "lr": 1.0585267076774536e-05, "epoch": 7.260812581913499, "percentage": 72.61, "elapsed_time": "0:46:41", "remaining_time": "0:17:36", "throughput": 2651.37, "total_tokens": 7426616} {"current_steps": 27705, "total_steps": 38150, "loss": 0.1984, "lr": 1.0575923935810656e-05, "epoch": 7.262123197903015, "percentage": 72.62, "elapsed_time": "0:46:41", "remaining_time": "0:17:36", "throughput": 2651.48, "total_tokens": 7428424} {"current_steps": 27710, "total_steps": 38150, "loss": 0.4406, "lr": 1.056658381378097e-05, "epoch": 7.263433813892529, "percentage": 72.63, "elapsed_time": "0:46:42", "remaining_time": "0:17:35", "throughput": 2651.52, "total_tokens": 7429672} {"current_steps": 27715, "total_steps": 38150, "loss": 0.1278, "lr": 1.0557246712640356e-05, "epoch": 7.264744429882045, "percentage": 72.65, "elapsed_time": "0:46:42", "remaining_time": "0:17:35", "throughput": 2651.46, "total_tokens": 7430616} {"current_steps": 27720, "total_steps": 38150, "loss": 0.2152, "lr": 1.054791263434305e-05, "epoch": 7.26605504587156, "percentage": 72.66, "elapsed_time": "0:46:42", "remaining_time": "0:17:34", "throughput": 2651.55, "total_tokens": 7432104} {"current_steps": 27725, "total_steps": 38150, "loss": 0.1885, "lr": 1.0538581580842655e-05, "epoch": 7.267365661861074, "percentage": 72.67, "elapsed_time": "0:46:43", "remaining_time": "0:17:34", "throughput": 2651.52, "total_tokens": 7433144} {"current_steps": 27730, "total_steps": 38150, "loss": 0.3291, "lr": 1.052925355409215e-05, "epoch": 7.26867627785059, "percentage": 72.69, "elapsed_time": "0:46:43", "remaining_time": "0:17:33", "throughput": 2651.59, "total_tokens": 7434664} {"current_steps": 27735, "total_steps": 38150, "loss": 0.2386, "lr": 1.0519928556043873e-05, "epoch": 7.269986893840104, "percentage": 72.7, "elapsed_time": "0:46:44", "remaining_time": "0:17:33", "throughput": 2651.54, "total_tokens": 7435624} {"current_steps": 27740, "total_steps": 38150, "loss": 0.2357, "lr": 1.0510606588649526e-05, "epoch": 7.27129750982962, "percentage": 72.71, "elapsed_time": "0:46:44", "remaining_time": "0:17:32", "throughput": 2651.56, "total_tokens": 7436840} {"current_steps": 27745, "total_steps": 38150, "loss": 0.3871, "lr": 1.0501287653860189e-05, "epoch": 7.272608125819135, "percentage": 72.73, "elapsed_time": "0:46:45", "remaining_time": "0:17:32", "throughput": 2651.61, "total_tokens": 7438232} {"current_steps": 27750, "total_steps": 38150, "loss": 0.2947, "lr": 1.0491971753626292e-05, "epoch": 7.27391874180865, "percentage": 72.74, "elapsed_time": "0:46:45", "remaining_time": "0:17:31", "throughput": 2652.03, "total_tokens": 7441576} {"current_steps": 27755, "total_steps": 38150, "loss": 0.2391, "lr": 1.048265888989764e-05, "epoch": 7.275229357798165, "percentage": 72.75, "elapsed_time": "0:46:46", "remaining_time": "0:17:31", "throughput": 2652.09, "total_tokens": 7443000} {"current_steps": 27760, "total_steps": 38150, "loss": 0.1385, "lr": 1.0473349064623397e-05, "epoch": 7.27653997378768, "percentage": 72.77, "elapsed_time": "0:46:46", "remaining_time": "0:17:30", "throughput": 2652.18, "total_tokens": 7444488} {"current_steps": 27765, "total_steps": 38150, "loss": 0.2647, "lr": 1.0464042279752096e-05, "epoch": 7.277850589777195, "percentage": 72.78, "elapsed_time": "0:46:47", "remaining_time": "0:17:30", "throughput": 2652.29, "total_tokens": 7446088} {"current_steps": 27770, "total_steps": 38150, "loss": 0.195, "lr": 1.0454738537231628e-05, "epoch": 7.2791612057667106, "percentage": 72.79, "elapsed_time": "0:46:47", "remaining_time": "0:17:29", "throughput": 2652.37, "total_tokens": 7447464} {"current_steps": 27775, "total_steps": 38150, "loss": 0.2396, "lr": 1.0445437839009265e-05, "epoch": 7.280471821756225, "percentage": 72.8, "elapsed_time": "0:46:48", "remaining_time": "0:17:28", "throughput": 2652.39, "total_tokens": 7448664} {"current_steps": 27780, "total_steps": 38150, "loss": 0.2957, "lr": 1.0436140187031601e-05, "epoch": 7.281782437745741, "percentage": 72.82, "elapsed_time": "0:46:48", "remaining_time": "0:17:28", "throughput": 2652.34, "total_tokens": 7449640} {"current_steps": 27785, "total_steps": 38150, "loss": 0.224, "lr": 1.0426845583244632e-05, "epoch": 7.283093053735255, "percentage": 72.83, "elapsed_time": "0:46:49", "remaining_time": "0:17:27", "throughput": 2652.38, "total_tokens": 7450984} {"current_steps": 27790, "total_steps": 38150, "loss": 0.2083, "lr": 1.04175540295937e-05, "epoch": 7.284403669724771, "percentage": 72.84, "elapsed_time": "0:46:49", "remaining_time": "0:17:27", "throughput": 2652.4, "total_tokens": 7452200} {"current_steps": 27795, "total_steps": 38150, "loss": 0.2145, "lr": 1.0408265528023508e-05, "epoch": 7.285714285714286, "percentage": 72.86, "elapsed_time": "0:46:50", "remaining_time": "0:17:26", "throughput": 2652.35, "total_tokens": 7453160} {"current_steps": 27800, "total_steps": 38150, "loss": 0.1871, "lr": 1.0398980080478139e-05, "epoch": 7.287024901703801, "percentage": 72.87, "elapsed_time": "0:46:50", "remaining_time": "0:17:26", "throughput": 2652.36, "total_tokens": 7454280} {"current_steps": 27805, "total_steps": 38150, "loss": 0.272, "lr": 1.0389697688901003e-05, "epoch": 7.288335517693316, "percentage": 72.88, "elapsed_time": "0:46:50", "remaining_time": "0:17:25", "throughput": 2652.53, "total_tokens": 7456184} {"current_steps": 27810, "total_steps": 38150, "loss": 0.1587, "lr": 1.038041835523491e-05, "epoch": 7.289646133682831, "percentage": 72.9, "elapsed_time": "0:46:51", "remaining_time": "0:17:25", "throughput": 2652.58, "total_tokens": 7457496} {"current_steps": 27815, "total_steps": 38150, "loss": 0.2651, "lr": 1.0371142081421987e-05, "epoch": 7.290956749672346, "percentage": 72.91, "elapsed_time": "0:46:51", "remaining_time": "0:17:24", "throughput": 2652.64, "total_tokens": 7458824} {"current_steps": 27820, "total_steps": 38150, "loss": 0.1845, "lr": 1.0361868869403745e-05, "epoch": 7.292267365661861, "percentage": 72.92, "elapsed_time": "0:46:52", "remaining_time": "0:17:24", "throughput": 2652.65, "total_tokens": 7459960} {"current_steps": 27825, "total_steps": 38150, "loss": 0.3349, "lr": 1.035259872112106e-05, "epoch": 7.293577981651376, "percentage": 72.94, "elapsed_time": "0:46:52", "remaining_time": "0:17:23", "throughput": 2652.66, "total_tokens": 7461256} {"current_steps": 27830, "total_steps": 38150, "loss": 0.1357, "lr": 1.0343331638514154e-05, "epoch": 7.294888597640891, "percentage": 72.95, "elapsed_time": "0:46:53", "remaining_time": "0:17:23", "throughput": 2652.68, "total_tokens": 7462440} {"current_steps": 27835, "total_steps": 38150, "loss": 0.0934, "lr": 1.0334067623522609e-05, "epoch": 7.296199213630406, "percentage": 72.96, "elapsed_time": "0:46:53", "remaining_time": "0:17:22", "throughput": 2652.71, "total_tokens": 7463688} {"current_steps": 27840, "total_steps": 38150, "loss": 0.2306, "lr": 1.032480667808537e-05, "epoch": 7.297509829619921, "percentage": 72.98, "elapsed_time": "0:46:54", "remaining_time": "0:17:22", "throughput": 2652.77, "total_tokens": 7465096} {"current_steps": 27845, "total_steps": 38150, "loss": 0.1768, "lr": 1.0315548804140736e-05, "epoch": 7.2988204456094365, "percentage": 72.99, "elapsed_time": "0:46:54", "remaining_time": "0:17:21", "throughput": 2652.87, "total_tokens": 7466680} {"current_steps": 27850, "total_steps": 38150, "loss": 0.1358, "lr": 1.0306294003626365e-05, "epoch": 7.300131061598951, "percentage": 73.0, "elapsed_time": "0:46:54", "remaining_time": "0:17:21", "throughput": 2652.86, "total_tokens": 7467768} {"current_steps": 27855, "total_steps": 38150, "loss": 0.1667, "lr": 1.029704227847927e-05, "epoch": 7.301441677588467, "percentage": 73.01, "elapsed_time": "0:46:55", "remaining_time": "0:17:20", "throughput": 2652.89, "total_tokens": 7468984} {"current_steps": 27860, "total_steps": 38150, "loss": 0.1694, "lr": 1.0287793630635822e-05, "epoch": 7.302752293577981, "percentage": 73.03, "elapsed_time": "0:46:55", "remaining_time": "0:17:20", "throughput": 2653.0, "total_tokens": 7470584} {"current_steps": 27865, "total_steps": 38150, "loss": 0.2222, "lr": 1.0278548062031748e-05, "epoch": 7.304062909567497, "percentage": 73.04, "elapsed_time": "0:46:56", "remaining_time": "0:17:19", "throughput": 2653.1, "total_tokens": 7472056} {"current_steps": 27870, "total_steps": 38150, "loss": 0.172, "lr": 1.0269305574602125e-05, "epoch": 7.305373525557012, "percentage": 73.05, "elapsed_time": "0:46:56", "remaining_time": "0:17:18", "throughput": 2653.2, "total_tokens": 7473576} {"current_steps": 27875, "total_steps": 38150, "loss": 0.1201, "lr": 1.0260066170281395e-05, "epoch": 7.306684141546527, "percentage": 73.07, "elapsed_time": "0:46:57", "remaining_time": "0:17:18", "throughput": 2653.24, "total_tokens": 7474856} {"current_steps": 27880, "total_steps": 38150, "loss": 0.1915, "lr": 1.0250829851003346e-05, "epoch": 7.307994757536042, "percentage": 73.08, "elapsed_time": "0:46:57", "remaining_time": "0:17:17", "throughput": 2653.32, "total_tokens": 7476392} {"current_steps": 27885, "total_steps": 38150, "loss": 0.273, "lr": 1.0241596618701124e-05, "epoch": 7.309305373525557, "percentage": 73.09, "elapsed_time": "0:46:58", "remaining_time": "0:17:17", "throughput": 2653.35, "total_tokens": 7477624} {"current_steps": 27890, "total_steps": 38150, "loss": 0.2311, "lr": 1.0232366475307228e-05, "epoch": 7.310615989515072, "percentage": 73.11, "elapsed_time": "0:46:58", "remaining_time": "0:17:16", "throughput": 2653.3, "total_tokens": 7478584} {"current_steps": 27895, "total_steps": 38150, "loss": 0.1526, "lr": 1.0223139422753524e-05, "epoch": 7.3119266055045875, "percentage": 73.12, "elapsed_time": "0:46:59", "remaining_time": "0:17:16", "throughput": 2653.32, "total_tokens": 7479848} {"current_steps": 27900, "total_steps": 38150, "loss": 0.2061, "lr": 1.0213915462971197e-05, "epoch": 7.313237221494102, "percentage": 73.13, "elapsed_time": "0:46:59", "remaining_time": "0:17:15", "throughput": 2653.43, "total_tokens": 7481512} {"current_steps": 27905, "total_steps": 38150, "loss": 0.2136, "lr": 1.0204694597890812e-05, "epoch": 7.314547837483618, "percentage": 73.15, "elapsed_time": "0:47:00", "remaining_time": "0:17:15", "throughput": 2653.42, "total_tokens": 7482728} {"current_steps": 27910, "total_steps": 38150, "loss": 0.2246, "lr": 1.0195476829442277e-05, "epoch": 7.315858453473132, "percentage": 73.16, "elapsed_time": "0:47:00", "remaining_time": "0:17:14", "throughput": 2653.45, "total_tokens": 7483944} {"current_steps": 27915, "total_steps": 38150, "loss": 0.3531, "lr": 1.0186262159554872e-05, "epoch": 7.317169069462647, "percentage": 73.17, "elapsed_time": "0:47:00", "remaining_time": "0:17:14", "throughput": 2653.59, "total_tokens": 7485608} {"current_steps": 27920, "total_steps": 38150, "loss": 0.167, "lr": 1.0177050590157197e-05, "epoch": 7.3184796854521625, "percentage": 73.18, "elapsed_time": "0:47:01", "remaining_time": "0:17:13", "throughput": 2653.59, "total_tokens": 7486728} {"current_steps": 27925, "total_steps": 38150, "loss": 0.2035, "lr": 1.0167842123177223e-05, "epoch": 7.319790301441677, "percentage": 73.2, "elapsed_time": "0:47:01", "remaining_time": "0:17:13", "throughput": 2653.61, "total_tokens": 7487912} {"current_steps": 27930, "total_steps": 38150, "loss": 0.1424, "lr": 1.0158636760542276e-05, "epoch": 7.321100917431193, "percentage": 73.21, "elapsed_time": "0:47:02", "remaining_time": "0:17:12", "throughput": 2653.62, "total_tokens": 7489048} {"current_steps": 27935, "total_steps": 38150, "loss": 0.2243, "lr": 1.0149434504178997e-05, "epoch": 7.322411533420707, "percentage": 73.22, "elapsed_time": "0:47:02", "remaining_time": "0:17:12", "throughput": 2653.65, "total_tokens": 7490312} {"current_steps": 27940, "total_steps": 38150, "loss": 0.1223, "lr": 1.0140235356013422e-05, "epoch": 7.323722149410223, "percentage": 73.24, "elapsed_time": "0:47:03", "remaining_time": "0:17:11", "throughput": 2653.63, "total_tokens": 7491352} {"current_steps": 27945, "total_steps": 38150, "loss": 0.1216, "lr": 1.0131039317970908e-05, "epoch": 7.325032765399738, "percentage": 73.25, "elapsed_time": "0:47:03", "remaining_time": "0:17:11", "throughput": 2653.57, "total_tokens": 7492280} {"current_steps": 27950, "total_steps": 38150, "loss": 0.3751, "lr": 1.0121846391976173e-05, "epoch": 7.326343381389253, "percentage": 73.26, "elapsed_time": "0:47:03", "remaining_time": "0:17:10", "throughput": 2653.64, "total_tokens": 7493800} {"current_steps": 27955, "total_steps": 38150, "loss": 0.1727, "lr": 1.0112656579953283e-05, "epoch": 7.327653997378768, "percentage": 73.28, "elapsed_time": "0:47:04", "remaining_time": "0:17:10", "throughput": 2653.69, "total_tokens": 7495176} {"current_steps": 27960, "total_steps": 38150, "loss": 0.4218, "lr": 1.0103469883825645e-05, "epoch": 7.328964613368283, "percentage": 73.29, "elapsed_time": "0:47:04", "remaining_time": "0:17:09", "throughput": 2653.74, "total_tokens": 7496472} {"current_steps": 27965, "total_steps": 38150, "loss": 0.1761, "lr": 1.0094286305516023e-05, "epoch": 7.330275229357798, "percentage": 73.3, "elapsed_time": "0:47:05", "remaining_time": "0:17:09", "throughput": 2653.75, "total_tokens": 7497752} {"current_steps": 27970, "total_steps": 38150, "loss": 0.2032, "lr": 1.008510584694652e-05, "epoch": 7.3315858453473135, "percentage": 73.32, "elapsed_time": "0:47:05", "remaining_time": "0:17:08", "throughput": 2653.79, "total_tokens": 7499000} {"current_steps": 27975, "total_steps": 38150, "loss": 0.1141, "lr": 1.0075928510038593e-05, "epoch": 7.332896461336828, "percentage": 73.33, "elapsed_time": "0:47:06", "remaining_time": "0:17:07", "throughput": 2653.75, "total_tokens": 7499992} {"current_steps": 27980, "total_steps": 38150, "loss": 0.1367, "lr": 1.0066754296713043e-05, "epoch": 7.334207077326344, "percentage": 73.34, "elapsed_time": "0:47:06", "remaining_time": "0:17:07", "throughput": 2653.77, "total_tokens": 7501192} {"current_steps": 27985, "total_steps": 38150, "loss": 0.139, "lr": 1.0057583208890017e-05, "epoch": 7.335517693315858, "percentage": 73.36, "elapsed_time": "0:47:07", "remaining_time": "0:17:06", "throughput": 2653.83, "total_tokens": 7502504} {"current_steps": 27990, "total_steps": 38150, "loss": 0.1818, "lr": 1.0048415248489004e-05, "epoch": 7.336828309305374, "percentage": 73.37, "elapsed_time": "0:47:07", "remaining_time": "0:17:06", "throughput": 2653.91, "total_tokens": 7503944} {"current_steps": 27995, "total_steps": 38150, "loss": 0.1791, "lr": 1.0039250417428847e-05, "epoch": 7.3381389252948885, "percentage": 73.38, "elapsed_time": "0:47:07", "remaining_time": "0:17:05", "throughput": 2653.96, "total_tokens": 7505240} {"current_steps": 28000, "total_steps": 38150, "loss": 0.1993, "lr": 1.0030088717627729e-05, "epoch": 7.339449541284404, "percentage": 73.39, "elapsed_time": "0:47:08", "remaining_time": "0:17:05", "throughput": 2653.95, "total_tokens": 7506344} {"current_steps": 28005, "total_steps": 38150, "loss": 0.1155, "lr": 1.0020930151003174e-05, "epoch": 7.340760157273919, "percentage": 73.41, "elapsed_time": "0:47:08", "remaining_time": "0:17:04", "throughput": 2653.99, "total_tokens": 7507688} {"current_steps": 28010, "total_steps": 38150, "loss": 0.2441, "lr": 1.0011774719472064e-05, "epoch": 7.342070773263433, "percentage": 73.42, "elapsed_time": "0:47:09", "remaining_time": "0:17:04", "throughput": 2653.98, "total_tokens": 7508760} {"current_steps": 28015, "total_steps": 38150, "loss": 0.1519, "lr": 1.0002622424950604e-05, "epoch": 7.343381389252949, "percentage": 73.43, "elapsed_time": "0:47:09", "remaining_time": "0:17:03", "throughput": 2654.03, "total_tokens": 7510136} {"current_steps": 28020, "total_steps": 38150, "loss": 0.1632, "lr": 9.99347326935435e-06, "epoch": 7.344692005242464, "percentage": 73.45, "elapsed_time": "0:47:10", "remaining_time": "0:17:03", "throughput": 2654.18, "total_tokens": 7511864} {"current_steps": 28025, "total_steps": 38150, "loss": 0.136, "lr": 9.984327254598208e-06, "epoch": 7.346002621231979, "percentage": 73.46, "elapsed_time": "0:47:10", "remaining_time": "0:17:02", "throughput": 2654.2, "total_tokens": 7513096} {"current_steps": 28030, "total_steps": 38150, "loss": 0.1587, "lr": 9.975184382596434e-06, "epoch": 7.347313237221494, "percentage": 73.47, "elapsed_time": "0:47:11", "remaining_time": "0:17:02", "throughput": 2654.18, "total_tokens": 7514136} {"current_steps": 28035, "total_steps": 38150, "loss": 0.1126, "lr": 9.966044655262607e-06, "epoch": 7.348623853211009, "percentage": 73.49, "elapsed_time": "0:47:11", "remaining_time": "0:17:01", "throughput": 2654.24, "total_tokens": 7515544} {"current_steps": 28040, "total_steps": 38150, "loss": 0.1726, "lr": 9.956908074509658e-06, "epoch": 7.349934469200524, "percentage": 73.5, "elapsed_time": "0:47:11", "remaining_time": "0:17:01", "throughput": 2654.28, "total_tokens": 7516888} {"current_steps": 28045, "total_steps": 38150, "loss": 0.1383, "lr": 9.947774642249863e-06, "epoch": 7.3512450851900395, "percentage": 73.51, "elapsed_time": "0:47:12", "remaining_time": "0:17:00", "throughput": 2654.27, "total_tokens": 7517944} {"current_steps": 28050, "total_steps": 38150, "loss": 0.2021, "lr": 9.938644360394822e-06, "epoch": 7.352555701179554, "percentage": 73.53, "elapsed_time": "0:47:12", "remaining_time": "0:17:00", "throughput": 2654.39, "total_tokens": 7519560} {"current_steps": 28055, "total_steps": 38150, "loss": 0.1219, "lr": 9.92951723085549e-06, "epoch": 7.35386631716907, "percentage": 73.54, "elapsed_time": "0:47:13", "remaining_time": "0:16:59", "throughput": 2654.41, "total_tokens": 7520808} {"current_steps": 28060, "total_steps": 38150, "loss": 0.1509, "lr": 9.920393255542163e-06, "epoch": 7.355176933158584, "percentage": 73.55, "elapsed_time": "0:47:13", "remaining_time": "0:16:58", "throughput": 2654.41, "total_tokens": 7521944} {"current_steps": 28065, "total_steps": 38150, "loss": 0.208, "lr": 9.911272436364469e-06, "epoch": 7.3564875491481, "percentage": 73.56, "elapsed_time": "0:47:14", "remaining_time": "0:16:58", "throughput": 2654.51, "total_tokens": 7523464} {"current_steps": 28070, "total_steps": 38150, "loss": 0.2006, "lr": 9.902154775231386e-06, "epoch": 7.3577981651376145, "percentage": 73.58, "elapsed_time": "0:47:14", "remaining_time": "0:16:57", "throughput": 2654.68, "total_tokens": 7525304} {"current_steps": 28075, "total_steps": 38150, "loss": 0.1914, "lr": 9.893040274051221e-06, "epoch": 7.35910878112713, "percentage": 73.59, "elapsed_time": "0:47:15", "remaining_time": "0:16:57", "throughput": 2654.76, "total_tokens": 7526792} {"current_steps": 28080, "total_steps": 38150, "loss": 0.2899, "lr": 9.883928934731615e-06, "epoch": 7.360419397116645, "percentage": 73.6, "elapsed_time": "0:47:15", "remaining_time": "0:16:56", "throughput": 2654.74, "total_tokens": 7527864} {"current_steps": 28085, "total_steps": 38150, "loss": 0.2128, "lr": 9.874820759179581e-06, "epoch": 7.36173001310616, "percentage": 73.62, "elapsed_time": "0:47:16", "remaining_time": "0:16:56", "throughput": 2654.78, "total_tokens": 7529208} {"current_steps": 28090, "total_steps": 38150, "loss": 0.1866, "lr": 9.865715749301419e-06, "epoch": 7.363040629095675, "percentage": 73.63, "elapsed_time": "0:47:16", "remaining_time": "0:16:55", "throughput": 2654.85, "total_tokens": 7530696} {"current_steps": 28095, "total_steps": 38150, "loss": 0.1459, "lr": 9.8566139070028e-06, "epoch": 7.3643512450851905, "percentage": 73.64, "elapsed_time": "0:47:17", "remaining_time": "0:16:55", "throughput": 2654.84, "total_tokens": 7531800} {"current_steps": 28100, "total_steps": 38150, "loss": 0.2061, "lr": 9.847515234188726e-06, "epoch": 7.365661861074705, "percentage": 73.66, "elapsed_time": "0:47:17", "remaining_time": "0:16:54", "throughput": 2654.85, "total_tokens": 7532968} {"current_steps": 28105, "total_steps": 38150, "loss": 0.1245, "lr": 9.838419732763531e-06, "epoch": 7.36697247706422, "percentage": 73.67, "elapsed_time": "0:47:17", "remaining_time": "0:16:54", "throughput": 2654.87, "total_tokens": 7534264} {"current_steps": 28110, "total_steps": 38150, "loss": 0.1856, "lr": 9.829327404630891e-06, "epoch": 7.368283093053735, "percentage": 73.68, "elapsed_time": "0:47:18", "remaining_time": "0:16:53", "throughput": 2654.95, "total_tokens": 7535720} {"current_steps": 28115, "total_steps": 38150, "loss": 0.255, "lr": 9.820238251693811e-06, "epoch": 7.36959370904325, "percentage": 73.7, "elapsed_time": "0:47:18", "remaining_time": "0:16:53", "throughput": 2654.94, "total_tokens": 7536792} {"current_steps": 28120, "total_steps": 38150, "loss": 0.165, "lr": 9.811152275854635e-06, "epoch": 7.3709043250327655, "percentage": 73.71, "elapsed_time": "0:47:19", "remaining_time": "0:16:52", "throughput": 2654.93, "total_tokens": 7537864} {"current_steps": 28125, "total_steps": 38150, "loss": 0.2255, "lr": 9.802069479015044e-06, "epoch": 7.37221494102228, "percentage": 73.72, "elapsed_time": "0:47:19", "remaining_time": "0:16:52", "throughput": 2654.98, "total_tokens": 7539272} {"current_steps": 28130, "total_steps": 38150, "loss": 0.2841, "lr": 9.792989863076064e-06, "epoch": 7.373525557011796, "percentage": 73.74, "elapsed_time": "0:47:20", "remaining_time": "0:16:51", "throughput": 2654.95, "total_tokens": 7540296} {"current_steps": 28135, "total_steps": 38150, "loss": 0.2792, "lr": 9.783913429938015e-06, "epoch": 7.37483617300131, "percentage": 73.75, "elapsed_time": "0:47:20", "remaining_time": "0:16:51", "throughput": 2655.05, "total_tokens": 7541768} {"current_steps": 28140, "total_steps": 38150, "loss": 0.1949, "lr": 9.774840181500588e-06, "epoch": 7.376146788990826, "percentage": 73.76, "elapsed_time": "0:47:20", "remaining_time": "0:16:50", "throughput": 2655.07, "total_tokens": 7542952} {"current_steps": 28145, "total_steps": 38150, "loss": 0.1595, "lr": 9.765770119662813e-06, "epoch": 7.3774574049803405, "percentage": 73.77, "elapsed_time": "0:47:21", "remaining_time": "0:16:50", "throughput": 2655.01, "total_tokens": 7543912} {"current_steps": 28150, "total_steps": 38150, "loss": 0.2023, "lr": 9.756703246323026e-06, "epoch": 7.378768020969856, "percentage": 73.79, "elapsed_time": "0:47:21", "remaining_time": "0:16:49", "throughput": 2654.96, "total_tokens": 7544856} {"current_steps": 28155, "total_steps": 38150, "loss": 0.1786, "lr": 9.747639563378916e-06, "epoch": 7.380078636959371, "percentage": 73.8, "elapsed_time": "0:47:22", "remaining_time": "0:16:48", "throughput": 2654.96, "total_tokens": 7545992} {"current_steps": 28160, "total_steps": 38150, "loss": 0.1745, "lr": 9.738579072727488e-06, "epoch": 7.381389252948886, "percentage": 73.81, "elapsed_time": "0:47:22", "remaining_time": "0:16:48", "throughput": 2655.04, "total_tokens": 7547496} {"current_steps": 28165, "total_steps": 38150, "loss": 0.2385, "lr": 9.7295217762651e-06, "epoch": 7.382699868938401, "percentage": 73.83, "elapsed_time": "0:47:23", "remaining_time": "0:16:47", "throughput": 2655.02, "total_tokens": 7548552} {"current_steps": 28170, "total_steps": 38150, "loss": 0.2788, "lr": 9.72046767588741e-06, "epoch": 7.3840104849279165, "percentage": 73.84, "elapsed_time": "0:47:23", "remaining_time": "0:16:47", "throughput": 2655.15, "total_tokens": 7550280} {"current_steps": 28175, "total_steps": 38150, "loss": 0.1578, "lr": 9.711416773489434e-06, "epoch": 7.385321100917431, "percentage": 73.85, "elapsed_time": "0:47:24", "remaining_time": "0:16:46", "throughput": 2655.13, "total_tokens": 7551368} {"current_steps": 28180, "total_steps": 38150, "loss": 0.2236, "lr": 9.702369070965512e-06, "epoch": 7.386631716906947, "percentage": 73.87, "elapsed_time": "0:47:24", "remaining_time": "0:16:46", "throughput": 2655.19, "total_tokens": 7552808} {"current_steps": 28185, "total_steps": 38150, "loss": 0.1668, "lr": 9.693324570209312e-06, "epoch": 7.387942332896461, "percentage": 73.88, "elapsed_time": "0:47:25", "remaining_time": "0:16:45", "throughput": 2655.2, "total_tokens": 7554072} {"current_steps": 28190, "total_steps": 38150, "loss": 0.3536, "lr": 9.684283273113829e-06, "epoch": 7.389252948885977, "percentage": 73.89, "elapsed_time": "0:47:25", "remaining_time": "0:16:45", "throughput": 2655.25, "total_tokens": 7555336} {"current_steps": 28195, "total_steps": 38150, "loss": 0.0981, "lr": 9.675245181571385e-06, "epoch": 7.3905635648754915, "percentage": 73.91, "elapsed_time": "0:47:25", "remaining_time": "0:16:44", "throughput": 2655.26, "total_tokens": 7556536} {"current_steps": 28200, "total_steps": 38150, "loss": 0.2001, "lr": 9.666210297473663e-06, "epoch": 7.391874180865006, "percentage": 73.92, "elapsed_time": "0:47:26", "remaining_time": "0:16:44", "throughput": 2655.25, "total_tokens": 7557592} {"current_steps": 28205, "total_steps": 38150, "loss": 0.1113, "lr": 9.657178622711624e-06, "epoch": 7.393184796854522, "percentage": 73.93, "elapsed_time": "0:47:26", "remaining_time": "0:16:43", "throughput": 2655.25, "total_tokens": 7558808} {"current_steps": 28210, "total_steps": 38150, "loss": 0.1483, "lr": 9.648150159175587e-06, "epoch": 7.394495412844036, "percentage": 73.94, "elapsed_time": "0:47:27", "remaining_time": "0:16:43", "throughput": 2655.26, "total_tokens": 7559992} {"current_steps": 28215, "total_steps": 38150, "loss": 0.1676, "lr": 9.639124908755196e-06, "epoch": 7.395806028833552, "percentage": 73.96, "elapsed_time": "0:47:27", "remaining_time": "0:16:42", "throughput": 2655.36, "total_tokens": 7561560} {"current_steps": 28220, "total_steps": 38150, "loss": 0.1342, "lr": 9.630102873339419e-06, "epoch": 7.3971166448230665, "percentage": 73.97, "elapsed_time": "0:47:28", "remaining_time": "0:16:42", "throughput": 2655.43, "total_tokens": 7563000} {"current_steps": 28225, "total_steps": 38150, "loss": 0.1716, "lr": 9.621084054816557e-06, "epoch": 7.398427260812582, "percentage": 73.98, "elapsed_time": "0:47:28", "remaining_time": "0:16:41", "throughput": 2655.55, "total_tokens": 7564664} {"current_steps": 28230, "total_steps": 38150, "loss": 0.1514, "lr": 9.612068455074227e-06, "epoch": 7.399737876802097, "percentage": 74.0, "elapsed_time": "0:47:29", "remaining_time": "0:16:41", "throughput": 2655.64, "total_tokens": 7566056} {"current_steps": 28235, "total_steps": 38150, "loss": 0.3266, "lr": 9.603056075999382e-06, "epoch": 7.401048492791612, "percentage": 74.01, "elapsed_time": "0:47:29", "remaining_time": "0:16:40", "throughput": 2655.65, "total_tokens": 7567288} {"current_steps": 28240, "total_steps": 38150, "loss": 0.3235, "lr": 9.594046919478294e-06, "epoch": 7.402359108781127, "percentage": 74.02, "elapsed_time": "0:47:29", "remaining_time": "0:16:40", "throughput": 2655.74, "total_tokens": 7568824} {"current_steps": 28245, "total_steps": 38150, "loss": 0.2551, "lr": 9.58504098739658e-06, "epoch": 7.4036697247706424, "percentage": 74.04, "elapsed_time": "0:47:30", "remaining_time": "0:16:39", "throughput": 2655.86, "total_tokens": 7570504} {"current_steps": 28250, "total_steps": 38150, "loss": 0.2206, "lr": 9.576038281639138e-06, "epoch": 7.404980340760157, "percentage": 74.05, "elapsed_time": "0:47:30", "remaining_time": "0:16:39", "throughput": 2655.91, "total_tokens": 7571784} {"current_steps": 28255, "total_steps": 38150, "loss": 0.2567, "lr": 9.567038804090227e-06, "epoch": 7.406290956749673, "percentage": 74.06, "elapsed_time": "0:47:31", "remaining_time": "0:16:38", "throughput": 2655.95, "total_tokens": 7573112} {"current_steps": 28260, "total_steps": 38150, "loss": 0.242, "lr": 9.55804255663344e-06, "epoch": 7.407601572739187, "percentage": 74.08, "elapsed_time": "0:47:31", "remaining_time": "0:16:38", "throughput": 2656.02, "total_tokens": 7574536} {"current_steps": 28265, "total_steps": 38150, "loss": 0.2277, "lr": 9.549049541151659e-06, "epoch": 7.408912188728703, "percentage": 74.09, "elapsed_time": "0:47:32", "remaining_time": "0:16:37", "throughput": 2656.06, "total_tokens": 7575848} {"current_steps": 28270, "total_steps": 38150, "loss": 0.2386, "lr": 9.540059759527115e-06, "epoch": 7.4102228047182175, "percentage": 74.1, "elapsed_time": "0:47:32", "remaining_time": "0:16:36", "throughput": 2656.04, "total_tokens": 7577016} {"current_steps": 28275, "total_steps": 38150, "loss": 0.1807, "lr": 9.53107321364135e-06, "epoch": 7.411533420707733, "percentage": 74.12, "elapsed_time": "0:47:33", "remaining_time": "0:16:36", "throughput": 2656.14, "total_tokens": 7578488} {"current_steps": 28280, "total_steps": 38150, "loss": 0.2544, "lr": 9.522089905375231e-06, "epoch": 7.412844036697248, "percentage": 74.13, "elapsed_time": "0:47:33", "remaining_time": "0:16:35", "throughput": 2656.23, "total_tokens": 7579960} {"current_steps": 28285, "total_steps": 38150, "loss": 0.1058, "lr": 9.513109836608963e-06, "epoch": 7.414154652686763, "percentage": 74.14, "elapsed_time": "0:47:34", "remaining_time": "0:16:35", "throughput": 2656.3, "total_tokens": 7581432} {"current_steps": 28290, "total_steps": 38150, "loss": 0.1817, "lr": 9.504133009222035e-06, "epoch": 7.415465268676278, "percentage": 74.15, "elapsed_time": "0:47:34", "remaining_time": "0:16:34", "throughput": 2656.3, "total_tokens": 7582552} {"current_steps": 28295, "total_steps": 38150, "loss": 0.1553, "lr": 9.495159425093298e-06, "epoch": 7.4167758846657925, "percentage": 74.17, "elapsed_time": "0:47:35", "remaining_time": "0:16:34", "throughput": 2656.35, "total_tokens": 7583944} {"current_steps": 28300, "total_steps": 38150, "loss": 0.2329, "lr": 9.4861890861009e-06, "epoch": 7.418086500655308, "percentage": 74.18, "elapsed_time": "0:47:35", "remaining_time": "0:16:33", "throughput": 2656.43, "total_tokens": 7585320} {"current_steps": 28305, "total_steps": 38150, "loss": 0.2881, "lr": 9.477221994122321e-06, "epoch": 7.419397116644823, "percentage": 74.19, "elapsed_time": "0:47:35", "remaining_time": "0:16:33", "throughput": 2656.44, "total_tokens": 7586456} {"current_steps": 28310, "total_steps": 38150, "loss": 0.2024, "lr": 9.468258151034349e-06, "epoch": 7.420707732634338, "percentage": 74.21, "elapsed_time": "0:47:36", "remaining_time": "0:16:32", "throughput": 2656.43, "total_tokens": 7587560} {"current_steps": 28315, "total_steps": 38150, "loss": 0.2976, "lr": 9.459297558713115e-06, "epoch": 7.422018348623853, "percentage": 74.22, "elapsed_time": "0:47:36", "remaining_time": "0:16:32", "throughput": 2656.42, "total_tokens": 7588664} {"current_steps": 28320, "total_steps": 38150, "loss": 0.2961, "lr": 9.45034021903406e-06, "epoch": 7.423328964613368, "percentage": 74.23, "elapsed_time": "0:47:37", "remaining_time": "0:16:31", "throughput": 2656.44, "total_tokens": 7589848} {"current_steps": 28325, "total_steps": 38150, "loss": 0.319, "lr": 9.441386133871922e-06, "epoch": 7.424639580602883, "percentage": 74.25, "elapsed_time": "0:47:37", "remaining_time": "0:16:31", "throughput": 2656.43, "total_tokens": 7590920} {"current_steps": 28330, "total_steps": 38150, "loss": 0.2633, "lr": 9.432435305100782e-06, "epoch": 7.425950196592399, "percentage": 74.26, "elapsed_time": "0:47:37", "remaining_time": "0:16:30", "throughput": 2656.48, "total_tokens": 7592232} {"current_steps": 28335, "total_steps": 38150, "loss": 0.1862, "lr": 9.423487734594036e-06, "epoch": 7.427260812581913, "percentage": 74.27, "elapsed_time": "0:47:38", "remaining_time": "0:16:30", "throughput": 2656.56, "total_tokens": 7593624} {"current_steps": 28340, "total_steps": 38150, "loss": 0.2588, "lr": 9.41454342422439e-06, "epoch": 7.428571428571429, "percentage": 74.29, "elapsed_time": "0:47:38", "remaining_time": "0:16:29", "throughput": 2656.63, "total_tokens": 7595096} {"current_steps": 28345, "total_steps": 38150, "loss": 0.1975, "lr": 9.405602375863876e-06, "epoch": 7.4298820445609435, "percentage": 74.3, "elapsed_time": "0:47:39", "remaining_time": "0:16:29", "throughput": 2656.74, "total_tokens": 7596664} {"current_steps": 28350, "total_steps": 38150, "loss": 0.1713, "lr": 9.39666459138384e-06, "epoch": 7.431192660550459, "percentage": 74.31, "elapsed_time": "0:47:39", "remaining_time": "0:16:28", "throughput": 2656.69, "total_tokens": 7597624} {"current_steps": 28355, "total_steps": 38150, "loss": 0.2336, "lr": 9.387730072654946e-06, "epoch": 7.432503276539974, "percentage": 74.33, "elapsed_time": "0:47:40", "remaining_time": "0:16:28", "throughput": 2656.77, "total_tokens": 7598984} {"current_steps": 28360, "total_steps": 38150, "loss": 0.3892, "lr": 9.378798821547171e-06, "epoch": 7.433813892529489, "percentage": 74.34, "elapsed_time": "0:47:40", "remaining_time": "0:16:27", "throughput": 2656.79, "total_tokens": 7600216} {"current_steps": 28365, "total_steps": 38150, "loss": 0.2003, "lr": 9.36987083992982e-06, "epoch": 7.435124508519004, "percentage": 74.35, "elapsed_time": "0:47:41", "remaining_time": "0:16:26", "throughput": 2656.81, "total_tokens": 7601496} {"current_steps": 28370, "total_steps": 38150, "loss": 0.3527, "lr": 9.36094612967148e-06, "epoch": 7.436435124508519, "percentage": 74.36, "elapsed_time": "0:47:41", "remaining_time": "0:16:26", "throughput": 2656.96, "total_tokens": 7603400} {"current_steps": 28375, "total_steps": 38150, "loss": 0.1718, "lr": 9.352024692640098e-06, "epoch": 7.437745740498034, "percentage": 74.38, "elapsed_time": "0:47:42", "remaining_time": "0:16:25", "throughput": 2656.99, "total_tokens": 7604632} {"current_steps": 28380, "total_steps": 38150, "loss": 0.1599, "lr": 9.343106530702913e-06, "epoch": 7.43905635648755, "percentage": 74.39, "elapsed_time": "0:47:42", "remaining_time": "0:16:25", "throughput": 2656.97, "total_tokens": 7605672} {"current_steps": 28385, "total_steps": 38150, "loss": 0.166, "lr": 9.334191645726475e-06, "epoch": 7.440366972477064, "percentage": 74.4, "elapsed_time": "0:47:42", "remaining_time": "0:16:24", "throughput": 2656.96, "total_tokens": 7606856} {"current_steps": 28390, "total_steps": 38150, "loss": 0.219, "lr": 9.325280039576661e-06, "epoch": 7.441677588466579, "percentage": 74.42, "elapsed_time": "0:47:43", "remaining_time": "0:16:24", "throughput": 2657.01, "total_tokens": 7608120} {"current_steps": 28395, "total_steps": 38150, "loss": 0.1425, "lr": 9.31637171411865e-06, "epoch": 7.442988204456094, "percentage": 74.43, "elapsed_time": "0:47:43", "remaining_time": "0:16:23", "throughput": 2657.01, "total_tokens": 7609224} {"current_steps": 28400, "total_steps": 38150, "loss": 0.2925, "lr": 9.307466671216946e-06, "epoch": 7.444298820445609, "percentage": 74.44, "elapsed_time": "0:47:44", "remaining_time": "0:16:23", "throughput": 2657.04, "total_tokens": 7610520} {"current_steps": 28405, "total_steps": 38150, "loss": 0.2493, "lr": 9.298564912735347e-06, "epoch": 7.445609436435125, "percentage": 74.46, "elapsed_time": "0:47:44", "remaining_time": "0:16:22", "throughput": 2657.17, "total_tokens": 7612328} {"current_steps": 28410, "total_steps": 38150, "loss": 0.2172, "lr": 9.289666440536981e-06, "epoch": 7.446920052424639, "percentage": 74.47, "elapsed_time": "0:47:45", "remaining_time": "0:16:22", "throughput": 2657.26, "total_tokens": 7613784} {"current_steps": 28415, "total_steps": 38150, "loss": 0.3083, "lr": 9.280771256484284e-06, "epoch": 7.448230668414155, "percentage": 74.48, "elapsed_time": "0:47:45", "remaining_time": "0:16:21", "throughput": 2657.35, "total_tokens": 7615224} {"current_steps": 28420, "total_steps": 38150, "loss": 0.191, "lr": 9.271879362439e-06, "epoch": 7.4495412844036695, "percentage": 74.5, "elapsed_time": "0:47:46", "remaining_time": "0:16:21", "throughput": 2657.42, "total_tokens": 7616600} {"current_steps": 28425, "total_steps": 38150, "loss": 0.1163, "lr": 9.262990760262183e-06, "epoch": 7.450851900393185, "percentage": 74.51, "elapsed_time": "0:47:46", "remaining_time": "0:16:20", "throughput": 2657.42, "total_tokens": 7617720} {"current_steps": 28430, "total_steps": 38150, "loss": 0.2161, "lr": 9.254105451814215e-06, "epoch": 7.4521625163827, "percentage": 74.52, "elapsed_time": "0:47:47", "remaining_time": "0:16:20", "throughput": 2657.54, "total_tokens": 7619432} {"current_steps": 28435, "total_steps": 38150, "loss": 0.1713, "lr": 9.245223438954781e-06, "epoch": 7.453473132372215, "percentage": 74.53, "elapsed_time": "0:47:47", "remaining_time": "0:16:19", "throughput": 2657.5, "total_tokens": 7620408} {"current_steps": 28440, "total_steps": 38150, "loss": 0.1316, "lr": 9.236344723542847e-06, "epoch": 7.45478374836173, "percentage": 74.55, "elapsed_time": "0:47:47", "remaining_time": "0:16:19", "throughput": 2657.53, "total_tokens": 7621624} {"current_steps": 28445, "total_steps": 38150, "loss": 0.152, "lr": 9.227469307436728e-06, "epoch": 7.456094364351245, "percentage": 74.56, "elapsed_time": "0:47:48", "remaining_time": "0:16:18", "throughput": 2657.59, "total_tokens": 7623080} {"current_steps": 28450, "total_steps": 38150, "loss": 0.1525, "lr": 9.21859719249403e-06, "epoch": 7.45740498034076, "percentage": 74.57, "elapsed_time": "0:47:48", "remaining_time": "0:16:18", "throughput": 2657.56, "total_tokens": 7624120} {"current_steps": 28455, "total_steps": 38150, "loss": 0.1754, "lr": 9.209728380571669e-06, "epoch": 7.458715596330276, "percentage": 74.59, "elapsed_time": "0:47:49", "remaining_time": "0:16:17", "throughput": 2657.6, "total_tokens": 7625496} {"current_steps": 28460, "total_steps": 38150, "loss": 0.2337, "lr": 9.200862873525876e-06, "epoch": 7.46002621231979, "percentage": 74.6, "elapsed_time": "0:47:49", "remaining_time": "0:16:17", "throughput": 2657.82, "total_tokens": 7627656} {"current_steps": 28465, "total_steps": 38150, "loss": 0.1826, "lr": 9.192000673212184e-06, "epoch": 7.461336828309306, "percentage": 74.61, "elapsed_time": "0:47:50", "remaining_time": "0:16:16", "throughput": 2657.89, "total_tokens": 7629000} {"current_steps": 28470, "total_steps": 38150, "loss": 0.1923, "lr": 9.183141781485439e-06, "epoch": 7.46264744429882, "percentage": 74.63, "elapsed_time": "0:47:50", "remaining_time": "0:16:16", "throughput": 2657.91, "total_tokens": 7630200} {"current_steps": 28475, "total_steps": 38150, "loss": 0.209, "lr": 9.174286200199786e-06, "epoch": 7.463958060288336, "percentage": 74.64, "elapsed_time": "0:47:51", "remaining_time": "0:16:15", "throughput": 2657.88, "total_tokens": 7631208} {"current_steps": 28480, "total_steps": 38150, "loss": 0.222, "lr": 9.165433931208697e-06, "epoch": 7.465268676277851, "percentage": 74.65, "elapsed_time": "0:47:51", "remaining_time": "0:16:15", "throughput": 2657.88, "total_tokens": 7632360} {"current_steps": 28485, "total_steps": 38150, "loss": 0.2613, "lr": 9.15658497636491e-06, "epoch": 7.466579292267365, "percentage": 74.67, "elapsed_time": "0:47:52", "remaining_time": "0:16:14", "throughput": 2657.95, "total_tokens": 7633704} {"current_steps": 28490, "total_steps": 38150, "loss": 0.1635, "lr": 9.147739337520519e-06, "epoch": 7.467889908256881, "percentage": 74.68, "elapsed_time": "0:47:52", "remaining_time": "0:16:13", "throughput": 2657.93, "total_tokens": 7634776} {"current_steps": 28495, "total_steps": 38150, "loss": 0.3299, "lr": 9.138897016526895e-06, "epoch": 7.4692005242463955, "percentage": 74.69, "elapsed_time": "0:47:52", "remaining_time": "0:16:13", "throughput": 2658.05, "total_tokens": 7636456} {"current_steps": 28500, "total_steps": 38150, "loss": 0.2708, "lr": 9.130058015234722e-06, "epoch": 7.470511140235911, "percentage": 74.71, "elapsed_time": "0:47:53", "remaining_time": "0:16:12", "throughput": 2658.06, "total_tokens": 7637704} {"current_steps": 28505, "total_steps": 38150, "loss": 0.1146, "lr": 9.12122233549398e-06, "epoch": 7.471821756225426, "percentage": 74.72, "elapsed_time": "0:47:53", "remaining_time": "0:16:12", "throughput": 2658.08, "total_tokens": 7639000} {"current_steps": 28510, "total_steps": 38150, "loss": 0.1682, "lr": 9.11238997915397e-06, "epoch": 7.473132372214941, "percentage": 74.73, "elapsed_time": "0:47:54", "remaining_time": "0:16:11", "throughput": 2658.11, "total_tokens": 7640200} {"current_steps": 28515, "total_steps": 38150, "loss": 0.2563, "lr": 9.103560948063286e-06, "epoch": 7.474442988204456, "percentage": 74.74, "elapsed_time": "0:47:54", "remaining_time": "0:16:11", "throughput": 2658.18, "total_tokens": 7641640} {"current_steps": 28520, "total_steps": 38150, "loss": 0.1207, "lr": 9.094735244069839e-06, "epoch": 7.475753604193971, "percentage": 74.76, "elapsed_time": "0:47:55", "remaining_time": "0:16:10", "throughput": 2658.21, "total_tokens": 7642872} {"current_steps": 28525, "total_steps": 38150, "loss": 0.2718, "lr": 9.08591286902081e-06, "epoch": 7.477064220183486, "percentage": 74.77, "elapsed_time": "0:47:55", "remaining_time": "0:16:10", "throughput": 2658.34, "total_tokens": 7644456} {"current_steps": 28530, "total_steps": 38150, "loss": 0.207, "lr": 9.077093824762722e-06, "epoch": 7.478374836173002, "percentage": 74.78, "elapsed_time": "0:47:56", "remaining_time": "0:16:09", "throughput": 2658.34, "total_tokens": 7645592} {"current_steps": 28535, "total_steps": 38150, "loss": 0.1083, "lr": 9.068278113141385e-06, "epoch": 7.479685452162516, "percentage": 74.8, "elapsed_time": "0:47:56", "remaining_time": "0:16:09", "throughput": 2658.34, "total_tokens": 7646744} {"current_steps": 28540, "total_steps": 38150, "loss": 0.2862, "lr": 9.059465736001901e-06, "epoch": 7.480996068152032, "percentage": 74.81, "elapsed_time": "0:47:56", "remaining_time": "0:16:08", "throughput": 2658.47, "total_tokens": 7648392} {"current_steps": 28545, "total_steps": 38150, "loss": 0.244, "lr": 9.050656695188706e-06, "epoch": 7.482306684141546, "percentage": 74.82, "elapsed_time": "0:47:57", "remaining_time": "0:16:08", "throughput": 2658.63, "total_tokens": 7650344} {"current_steps": 28550, "total_steps": 38150, "loss": 0.1656, "lr": 9.041850992545503e-06, "epoch": 7.483617300131062, "percentage": 74.84, "elapsed_time": "0:47:57", "remaining_time": "0:16:07", "throughput": 2658.65, "total_tokens": 7651544} {"current_steps": 28555, "total_steps": 38150, "loss": 0.1908, "lr": 9.033048629915326e-06, "epoch": 7.484927916120577, "percentage": 74.85, "elapsed_time": "0:47:58", "remaining_time": "0:16:07", "throughput": 2658.76, "total_tokens": 7653160} {"current_steps": 28560, "total_steps": 38150, "loss": 0.1111, "lr": 9.02424960914047e-06, "epoch": 7.486238532110092, "percentage": 74.86, "elapsed_time": "0:47:58", "remaining_time": "0:16:06", "throughput": 2658.72, "total_tokens": 7654152} {"current_steps": 28565, "total_steps": 38150, "loss": 0.1187, "lr": 9.015453932062568e-06, "epoch": 7.487549148099607, "percentage": 74.88, "elapsed_time": "0:47:59", "remaining_time": "0:16:06", "throughput": 2658.8, "total_tokens": 7655560} {"current_steps": 28570, "total_steps": 38150, "loss": 0.3093, "lr": 9.006661600522539e-06, "epoch": 7.488859764089122, "percentage": 74.89, "elapsed_time": "0:47:59", "remaining_time": "0:16:05", "throughput": 2658.81, "total_tokens": 7656744} {"current_steps": 28575, "total_steps": 38150, "loss": 0.3119, "lr": 8.997872616360603e-06, "epoch": 7.490170380078637, "percentage": 74.9, "elapsed_time": "0:48:00", "remaining_time": "0:16:05", "throughput": 2658.87, "total_tokens": 7658216} {"current_steps": 28580, "total_steps": 38150, "loss": 0.2344, "lr": 8.989086981416278e-06, "epoch": 7.491480996068152, "percentage": 74.91, "elapsed_time": "0:48:00", "remaining_time": "0:16:04", "throughput": 2659.13, "total_tokens": 7660504} {"current_steps": 28585, "total_steps": 38150, "loss": 0.2531, "lr": 8.980304697528385e-06, "epoch": 7.492791612057667, "percentage": 74.93, "elapsed_time": "0:48:01", "remaining_time": "0:16:04", "throughput": 2659.15, "total_tokens": 7661720} {"current_steps": 28590, "total_steps": 38150, "loss": 0.2914, "lr": 8.971525766535038e-06, "epoch": 7.494102228047182, "percentage": 74.94, "elapsed_time": "0:48:01", "remaining_time": "0:16:03", "throughput": 2659.24, "total_tokens": 7663448} {"current_steps": 28595, "total_steps": 38150, "loss": 0.3201, "lr": 8.962750190273653e-06, "epoch": 7.495412844036697, "percentage": 74.95, "elapsed_time": "0:48:02", "remaining_time": "0:16:03", "throughput": 2659.37, "total_tokens": 7665048} {"current_steps": 28600, "total_steps": 38150, "loss": 0.1528, "lr": 8.953977970580942e-06, "epoch": 7.496723460026212, "percentage": 74.97, "elapsed_time": "0:48:02", "remaining_time": "0:16:02", "throughput": 2659.47, "total_tokens": 7666600} {"current_steps": 28605, "total_steps": 38150, "loss": 0.2277, "lr": 8.945209109292919e-06, "epoch": 7.498034076015728, "percentage": 74.98, "elapsed_time": "0:48:03", "remaining_time": "0:16:02", "throughput": 2659.54, "total_tokens": 7667960} {"current_steps": 28610, "total_steps": 38150, "loss": 0.195, "lr": 8.936443608244885e-06, "epoch": 7.499344692005242, "percentage": 74.99, "elapsed_time": "0:48:03", "remaining_time": "0:16:01", "throughput": 2659.59, "total_tokens": 7669336} {"current_steps": 28615, "total_steps": 38150, "loss": 0.2152, "lr": 8.927681469271451e-06, "epoch": 7.500655307994758, "percentage": 75.01, "elapsed_time": "0:48:04", "remaining_time": "0:16:01", "throughput": 2659.63, "total_tokens": 7670600} {"current_steps": 28620, "total_steps": 38150, "loss": 0.2348, "lr": 8.918922694206513e-06, "epoch": 7.501965923984272, "percentage": 75.02, "elapsed_time": "0:48:04", "remaining_time": "0:16:00", "throughput": 2659.71, "total_tokens": 7672088} {"current_steps": 28620, "total_steps": 38150, "eval_loss": 0.7353919148445129, "epoch": 7.501965923984272, "percentage": 75.02, "elapsed_time": "0:48:21", "remaining_time": "0:16:06", "throughput": 2644.24, "total_tokens": 7672088} {"current_steps": 28625, "total_steps": 38150, "loss": 0.2059, "lr": 8.91016728488327e-06, "epoch": 7.503276539973788, "percentage": 75.03, "elapsed_time": "0:48:23", "remaining_time": "0:16:06", "throughput": 2642.92, "total_tokens": 7673528} {"current_steps": 28630, "total_steps": 38150, "loss": 0.1385, "lr": 8.901415243134211e-06, "epoch": 7.504587155963303, "percentage": 75.05, "elapsed_time": "0:48:23", "remaining_time": "0:16:05", "throughput": 2642.96, "total_tokens": 7674808} {"current_steps": 28635, "total_steps": 38150, "loss": 0.1382, "lr": 8.892666570791136e-06, "epoch": 7.505897771952818, "percentage": 75.06, "elapsed_time": "0:48:24", "remaining_time": "0:16:05", "throughput": 2642.99, "total_tokens": 7676008} {"current_steps": 28640, "total_steps": 38150, "loss": 0.2967, "lr": 8.883921269685108e-06, "epoch": 7.507208387942333, "percentage": 75.07, "elapsed_time": "0:48:24", "remaining_time": "0:16:04", "throughput": 2643.11, "total_tokens": 7677736} {"current_steps": 28645, "total_steps": 38150, "loss": 0.2796, "lr": 8.875179341646511e-06, "epoch": 7.508519003931848, "percentage": 75.09, "elapsed_time": "0:48:25", "remaining_time": "0:16:04", "throughput": 2643.18, "total_tokens": 7679192} {"current_steps": 28650, "total_steps": 38150, "loss": 0.1383, "lr": 8.866440788505018e-06, "epoch": 7.509829619921363, "percentage": 75.1, "elapsed_time": "0:48:25", "remaining_time": "0:16:03", "throughput": 2643.23, "total_tokens": 7680600} {"current_steps": 28655, "total_steps": 38150, "loss": 0.2365, "lr": 8.857705612089581e-06, "epoch": 7.511140235910878, "percentage": 75.11, "elapsed_time": "0:48:26", "remaining_time": "0:16:02", "throughput": 2643.3, "total_tokens": 7681992} {"current_steps": 28660, "total_steps": 38150, "loss": 0.1568, "lr": 8.848973814228478e-06, "epoch": 7.512450851900393, "percentage": 75.12, "elapsed_time": "0:48:26", "remaining_time": "0:16:02", "throughput": 2643.3, "total_tokens": 7683112} {"current_steps": 28665, "total_steps": 38150, "loss": 0.182, "lr": 8.840245396749247e-06, "epoch": 7.513761467889909, "percentage": 75.14, "elapsed_time": "0:48:27", "remaining_time": "0:16:01", "throughput": 2643.33, "total_tokens": 7684440} {"current_steps": 28670, "total_steps": 38150, "loss": 0.2084, "lr": 8.831520361478744e-06, "epoch": 7.515072083879423, "percentage": 75.15, "elapsed_time": "0:48:27", "remaining_time": "0:16:01", "throughput": 2643.49, "total_tokens": 7686264} {"current_steps": 28675, "total_steps": 38150, "loss": 0.1396, "lr": 8.82279871024308e-06, "epoch": 7.516382699868938, "percentage": 75.16, "elapsed_time": "0:48:28", "remaining_time": "0:16:00", "throughput": 2643.54, "total_tokens": 7687688} {"current_steps": 28680, "total_steps": 38150, "loss": 0.3554, "lr": 8.814080444867695e-06, "epoch": 7.517693315858454, "percentage": 75.18, "elapsed_time": "0:48:28", "remaining_time": "0:16:00", "throughput": 2643.77, "total_tokens": 7690104} {"current_steps": 28685, "total_steps": 38150, "loss": 0.1457, "lr": 8.805365567177307e-06, "epoch": 7.519003931847968, "percentage": 75.19, "elapsed_time": "0:48:29", "remaining_time": "0:15:59", "throughput": 2643.86, "total_tokens": 7691544} {"current_steps": 28690, "total_steps": 38150, "loss": 0.1052, "lr": 8.796654078995921e-06, "epoch": 7.520314547837484, "percentage": 75.2, "elapsed_time": "0:48:29", "remaining_time": "0:15:59", "throughput": 2643.87, "total_tokens": 7692712} {"current_steps": 28695, "total_steps": 38150, "loss": 0.1591, "lr": 8.787945982146841e-06, "epoch": 7.521625163826998, "percentage": 75.22, "elapsed_time": "0:48:30", "remaining_time": "0:15:58", "throughput": 2643.84, "total_tokens": 7693736} {"current_steps": 28700, "total_steps": 38150, "loss": 0.1529, "lr": 8.779241278452657e-06, "epoch": 7.522935779816514, "percentage": 75.23, "elapsed_time": "0:48:30", "remaining_time": "0:15:58", "throughput": 2643.89, "total_tokens": 7695032} {"current_steps": 28705, "total_steps": 38150, "loss": 0.1548, "lr": 8.770539969735241e-06, "epoch": 7.524246395806029, "percentage": 75.24, "elapsed_time": "0:48:30", "remaining_time": "0:15:57", "throughput": 2643.9, "total_tokens": 7696216} {"current_steps": 28710, "total_steps": 38150, "loss": 0.2747, "lr": 8.761842057815772e-06, "epoch": 7.525557011795544, "percentage": 75.26, "elapsed_time": "0:48:31", "remaining_time": "0:15:57", "throughput": 2643.99, "total_tokens": 7697720} {"current_steps": 28715, "total_steps": 38150, "loss": 0.1229, "lr": 8.753147544514701e-06, "epoch": 7.526867627785059, "percentage": 75.27, "elapsed_time": "0:48:31", "remaining_time": "0:15:56", "throughput": 2644.07, "total_tokens": 7699144} {"current_steps": 28720, "total_steps": 38150, "loss": 0.1801, "lr": 8.744456431651777e-06, "epoch": 7.528178243774574, "percentage": 75.28, "elapsed_time": "0:48:32", "remaining_time": "0:15:56", "throughput": 2644.1, "total_tokens": 7700440} {"current_steps": 28725, "total_steps": 38150, "loss": 0.1806, "lr": 8.73576872104603e-06, "epoch": 7.529488859764089, "percentage": 75.29, "elapsed_time": "0:48:32", "remaining_time": "0:15:55", "throughput": 2644.11, "total_tokens": 7701624} {"current_steps": 28730, "total_steps": 38150, "loss": 0.1854, "lr": 8.727084414515793e-06, "epoch": 7.5307994757536045, "percentage": 75.31, "elapsed_time": "0:48:33", "remaining_time": "0:15:55", "throughput": 2644.06, "total_tokens": 7702600} {"current_steps": 28735, "total_steps": 38150, "loss": 0.1056, "lr": 8.718403513878668e-06, "epoch": 7.532110091743119, "percentage": 75.32, "elapsed_time": "0:48:33", "remaining_time": "0:15:54", "throughput": 2644.04, "total_tokens": 7703672} {"current_steps": 28740, "total_steps": 38150, "loss": 0.1901, "lr": 8.709726020951557e-06, "epoch": 7.533420707732635, "percentage": 75.33, "elapsed_time": "0:48:34", "remaining_time": "0:15:54", "throughput": 2644.04, "total_tokens": 7704776} {"current_steps": 28745, "total_steps": 38150, "loss": 0.2819, "lr": 8.701051937550638e-06, "epoch": 7.534731323722149, "percentage": 75.35, "elapsed_time": "0:48:34", "remaining_time": "0:15:53", "throughput": 2644.13, "total_tokens": 7706328} {"current_steps": 28750, "total_steps": 38150, "loss": 0.1218, "lr": 8.69238126549139e-06, "epoch": 7.536041939711664, "percentage": 75.36, "elapsed_time": "0:48:34", "remaining_time": "0:15:53", "throughput": 2644.12, "total_tokens": 7707416} {"current_steps": 28755, "total_steps": 38150, "loss": 0.2446, "lr": 8.683714006588576e-06, "epoch": 7.53735255570118, "percentage": 75.37, "elapsed_time": "0:48:35", "remaining_time": "0:15:52", "throughput": 2644.14, "total_tokens": 7708696} {"current_steps": 28760, "total_steps": 38150, "loss": 0.1938, "lr": 8.675050162656215e-06, "epoch": 7.538663171690695, "percentage": 75.39, "elapsed_time": "0:48:35", "remaining_time": "0:15:52", "throughput": 2644.17, "total_tokens": 7709992} {"current_steps": 28765, "total_steps": 38150, "loss": 0.1649, "lr": 8.666389735507648e-06, "epoch": 7.53997378768021, "percentage": 75.4, "elapsed_time": "0:48:36", "remaining_time": "0:15:51", "throughput": 2644.1, "total_tokens": 7710888} {"current_steps": 28770, "total_steps": 38150, "loss": 0.1843, "lr": 8.65773272695548e-06, "epoch": 7.541284403669724, "percentage": 75.41, "elapsed_time": "0:48:36", "remaining_time": "0:15:50", "throughput": 2644.09, "total_tokens": 7711960} {"current_steps": 28775, "total_steps": 38150, "loss": 0.2414, "lr": 8.649079138811625e-06, "epoch": 7.54259501965924, "percentage": 75.43, "elapsed_time": "0:48:37", "remaining_time": "0:15:50", "throughput": 2644.11, "total_tokens": 7713160} {"current_steps": 28780, "total_steps": 38150, "loss": 0.2081, "lr": 8.640428972887252e-06, "epoch": 7.543905635648755, "percentage": 75.44, "elapsed_time": "0:48:37", "remaining_time": "0:15:49", "throughput": 2644.24, "total_tokens": 7714792} {"current_steps": 28785, "total_steps": 38150, "loss": 0.1986, "lr": 8.63178223099283e-06, "epoch": 7.54521625163827, "percentage": 75.45, "elapsed_time": "0:48:38", "remaining_time": "0:15:49", "throughput": 2644.23, "total_tokens": 7715896} {"current_steps": 28790, "total_steps": 38150, "loss": 0.2176, "lr": 8.623138914938111e-06, "epoch": 7.546526867627785, "percentage": 75.47, "elapsed_time": "0:48:38", "remaining_time": "0:15:48", "throughput": 2644.27, "total_tokens": 7717144} {"current_steps": 28795, "total_steps": 38150, "loss": 0.2206, "lr": 8.61449902653211e-06, "epoch": 7.5478374836173, "percentage": 75.48, "elapsed_time": "0:48:38", "remaining_time": "0:15:48", "throughput": 2644.31, "total_tokens": 7718488} {"current_steps": 28800, "total_steps": 38150, "loss": 0.1621, "lr": 8.605862567583155e-06, "epoch": 7.549148099606815, "percentage": 75.49, "elapsed_time": "0:48:39", "remaining_time": "0:15:47", "throughput": 2644.44, "total_tokens": 7720312} {"current_steps": 28805, "total_steps": 38150, "loss": 0.2255, "lr": 8.597229539898835e-06, "epoch": 7.5504587155963305, "percentage": 75.5, "elapsed_time": "0:48:39", "remaining_time": "0:15:47", "throughput": 2644.45, "total_tokens": 7721432} {"current_steps": 28810, "total_steps": 38150, "loss": 0.1365, "lr": 8.588599945286033e-06, "epoch": 7.551769331585845, "percentage": 75.52, "elapsed_time": "0:48:40", "remaining_time": "0:15:46", "throughput": 2644.54, "total_tokens": 7722968} {"current_steps": 28815, "total_steps": 38150, "loss": 0.211, "lr": 8.579973785550904e-06, "epoch": 7.553079947575361, "percentage": 75.53, "elapsed_time": "0:48:40", "remaining_time": "0:15:46", "throughput": 2644.59, "total_tokens": 7724280} {"current_steps": 28820, "total_steps": 38150, "loss": 0.1485, "lr": 8.571351062498888e-06, "epoch": 7.554390563564875, "percentage": 75.54, "elapsed_time": "0:48:41", "remaining_time": "0:15:45", "throughput": 2644.55, "total_tokens": 7725256} {"current_steps": 28825, "total_steps": 38150, "loss": 0.1818, "lr": 8.562731777934713e-06, "epoch": 7.555701179554391, "percentage": 75.56, "elapsed_time": "0:48:41", "remaining_time": "0:15:45", "throughput": 2644.49, "total_tokens": 7726168} {"current_steps": 28830, "total_steps": 38150, "loss": 0.1572, "lr": 8.55411593366237e-06, "epoch": 7.557011795543906, "percentage": 75.57, "elapsed_time": "0:48:42", "remaining_time": "0:15:44", "throughput": 2644.52, "total_tokens": 7727416} {"current_steps": 28835, "total_steps": 38150, "loss": 0.0849, "lr": 8.545503531485149e-06, "epoch": 7.558322411533421, "percentage": 75.58, "elapsed_time": "0:48:42", "remaining_time": "0:15:44", "throughput": 2644.53, "total_tokens": 7728600} {"current_steps": 28840, "total_steps": 38150, "loss": 0.3689, "lr": 8.536894573205608e-06, "epoch": 7.559633027522936, "percentage": 75.6, "elapsed_time": "0:48:42", "remaining_time": "0:15:43", "throughput": 2644.6, "total_tokens": 7730008} {"current_steps": 28845, "total_steps": 38150, "loss": 0.2694, "lr": 8.528289060625586e-06, "epoch": 7.56094364351245, "percentage": 75.61, "elapsed_time": "0:48:43", "remaining_time": "0:15:43", "throughput": 2644.6, "total_tokens": 7731112} {"current_steps": 28850, "total_steps": 38150, "loss": 0.2072, "lr": 8.519686995546203e-06, "epoch": 7.562254259501966, "percentage": 75.62, "elapsed_time": "0:48:43", "remaining_time": "0:15:42", "throughput": 2644.64, "total_tokens": 7732376} {"current_steps": 28855, "total_steps": 38150, "loss": 0.1137, "lr": 8.511088379767857e-06, "epoch": 7.5635648754914815, "percentage": 75.64, "elapsed_time": "0:48:44", "remaining_time": "0:15:41", "throughput": 2644.66, "total_tokens": 7733640} {"current_steps": 28860, "total_steps": 38150, "loss": 0.2554, "lr": 8.502493215090218e-06, "epoch": 7.564875491480996, "percentage": 75.65, "elapsed_time": "0:48:44", "remaining_time": "0:15:41", "throughput": 2644.72, "total_tokens": 7735064} {"current_steps": 28865, "total_steps": 38150, "loss": 0.2417, "lr": 8.493901503312249e-06, "epoch": 7.566186107470511, "percentage": 75.66, "elapsed_time": "0:48:45", "remaining_time": "0:15:40", "throughput": 2644.76, "total_tokens": 7736328} {"current_steps": 28870, "total_steps": 38150, "loss": 0.1219, "lr": 8.48531324623218e-06, "epoch": 7.567496723460026, "percentage": 75.67, "elapsed_time": "0:48:45", "remaining_time": "0:15:40", "throughput": 2644.83, "total_tokens": 7737672} {"current_steps": 28875, "total_steps": 38150, "loss": 0.178, "lr": 8.476728445647506e-06, "epoch": 7.568807339449541, "percentage": 75.69, "elapsed_time": "0:48:46", "remaining_time": "0:15:39", "throughput": 2644.94, "total_tokens": 7739272} {"current_steps": 28880, "total_steps": 38150, "loss": 0.2379, "lr": 8.468147103355018e-06, "epoch": 7.5701179554390565, "percentage": 75.7, "elapsed_time": "0:48:46", "remaining_time": "0:15:39", "throughput": 2644.93, "total_tokens": 7740376} {"current_steps": 28885, "total_steps": 38150, "loss": 0.2454, "lr": 8.45956922115077e-06, "epoch": 7.571428571428571, "percentage": 75.71, "elapsed_time": "0:48:46", "remaining_time": "0:15:38", "throughput": 2645.01, "total_tokens": 7741816} {"current_steps": 28890, "total_steps": 38150, "loss": 0.2312, "lr": 8.450994800830112e-06, "epoch": 7.572739187418087, "percentage": 75.73, "elapsed_time": "0:48:47", "remaining_time": "0:15:38", "throughput": 2645.03, "total_tokens": 7743016} {"current_steps": 28895, "total_steps": 38150, "loss": 0.1186, "lr": 8.442423844187647e-06, "epoch": 7.574049803407601, "percentage": 75.74, "elapsed_time": "0:48:47", "remaining_time": "0:15:37", "throughput": 2644.97, "total_tokens": 7743928} {"current_steps": 28900, "total_steps": 38150, "loss": 0.1307, "lr": 8.433856353017261e-06, "epoch": 7.575360419397117, "percentage": 75.75, "elapsed_time": "0:48:48", "remaining_time": "0:15:37", "throughput": 2645.04, "total_tokens": 7745320} {"current_steps": 28905, "total_steps": 38150, "loss": 0.1158, "lr": 8.425292329112124e-06, "epoch": 7.576671035386632, "percentage": 75.77, "elapsed_time": "0:48:48", "remaining_time": "0:15:36", "throughput": 2645.07, "total_tokens": 7746584} {"current_steps": 28910, "total_steps": 38150, "loss": 0.2377, "lr": 8.416731774264658e-06, "epoch": 7.577981651376147, "percentage": 75.78, "elapsed_time": "0:48:49", "remaining_time": "0:15:36", "throughput": 2645.19, "total_tokens": 7748168} {"current_steps": 28915, "total_steps": 38150, "loss": 0.1742, "lr": 8.408174690266577e-06, "epoch": 7.579292267365662, "percentage": 75.79, "elapsed_time": "0:48:49", "remaining_time": "0:15:35", "throughput": 2645.21, "total_tokens": 7749400} {"current_steps": 28920, "total_steps": 38150, "loss": 0.1367, "lr": 8.399621078908865e-06, "epoch": 7.580602883355177, "percentage": 75.81, "elapsed_time": "0:48:50", "remaining_time": "0:15:35", "throughput": 2645.17, "total_tokens": 7750488} {"current_steps": 28925, "total_steps": 38150, "loss": 0.2637, "lr": 8.391070941981778e-06, "epoch": 7.581913499344692, "percentage": 75.82, "elapsed_time": "0:48:50", "remaining_time": "0:15:34", "throughput": 2645.14, "total_tokens": 7751512} {"current_steps": 28930, "total_steps": 38150, "loss": 0.2389, "lr": 8.382524281274844e-06, "epoch": 7.5832241153342075, "percentage": 75.83, "elapsed_time": "0:48:50", "remaining_time": "0:15:34", "throughput": 2645.1, "total_tokens": 7752504} {"current_steps": 28935, "total_steps": 38150, "loss": 0.2442, "lr": 8.373981098576865e-06, "epoch": 7.584534731323722, "percentage": 75.85, "elapsed_time": "0:48:51", "remaining_time": "0:15:33", "throughput": 2645.21, "total_tokens": 7754120} {"current_steps": 28940, "total_steps": 38150, "loss": 0.2255, "lr": 8.365441395675907e-06, "epoch": 7.585845347313237, "percentage": 75.86, "elapsed_time": "0:48:51", "remaining_time": "0:15:33", "throughput": 2645.3, "total_tokens": 7755640} {"current_steps": 28945, "total_steps": 38150, "loss": 0.1553, "lr": 8.356905174359338e-06, "epoch": 7.587155963302752, "percentage": 75.87, "elapsed_time": "0:48:52", "remaining_time": "0:15:32", "throughput": 2645.38, "total_tokens": 7757048} {"current_steps": 28950, "total_steps": 38150, "loss": 0.1661, "lr": 8.348372436413754e-06, "epoch": 7.588466579292267, "percentage": 75.88, "elapsed_time": "0:48:52", "remaining_time": "0:15:31", "throughput": 2645.39, "total_tokens": 7758232} {"current_steps": 28955, "total_steps": 38150, "loss": 0.1877, "lr": 8.339843183625046e-06, "epoch": 7.5897771952817825, "percentage": 75.9, "elapsed_time": "0:48:53", "remaining_time": "0:15:31", "throughput": 2645.43, "total_tokens": 7759576} {"current_steps": 28960, "total_steps": 38150, "loss": 0.1838, "lr": 8.33131741777837e-06, "epoch": 7.591087811271297, "percentage": 75.91, "elapsed_time": "0:48:53", "remaining_time": "0:15:30", "throughput": 2645.51, "total_tokens": 7761032} {"current_steps": 28965, "total_steps": 38150, "loss": 0.1707, "lr": 8.32279514065816e-06, "epoch": 7.592398427260813, "percentage": 75.92, "elapsed_time": "0:48:54", "remaining_time": "0:15:30", "throughput": 2645.57, "total_tokens": 7762392} {"current_steps": 28970, "total_steps": 38150, "loss": 0.2644, "lr": 8.314276354048109e-06, "epoch": 7.593709043250327, "percentage": 75.94, "elapsed_time": "0:48:54", "remaining_time": "0:15:29", "throughput": 2645.68, "total_tokens": 7763992} {"current_steps": 28975, "total_steps": 38150, "loss": 0.2363, "lr": 8.30576105973119e-06, "epoch": 7.595019659239843, "percentage": 75.95, "elapsed_time": "0:48:55", "remaining_time": "0:15:29", "throughput": 2645.63, "total_tokens": 7764936} {"current_steps": 28980, "total_steps": 38150, "loss": 0.2531, "lr": 8.297249259489634e-06, "epoch": 7.5963302752293576, "percentage": 75.96, "elapsed_time": "0:48:55", "remaining_time": "0:15:28", "throughput": 2645.78, "total_tokens": 7766728} {"current_steps": 28985, "total_steps": 38150, "loss": 0.1444, "lr": 8.288740955104946e-06, "epoch": 7.597640891218873, "percentage": 75.98, "elapsed_time": "0:48:55", "remaining_time": "0:15:28", "throughput": 2645.85, "total_tokens": 7768088} {"current_steps": 28990, "total_steps": 38150, "loss": 0.1922, "lr": 8.280236148357911e-06, "epoch": 7.598951507208388, "percentage": 75.99, "elapsed_time": "0:48:56", "remaining_time": "0:15:27", "throughput": 2645.89, "total_tokens": 7769416} {"current_steps": 28995, "total_steps": 38150, "loss": 0.1441, "lr": 8.271734841028553e-06, "epoch": 7.600262123197903, "percentage": 76.0, "elapsed_time": "0:48:56", "remaining_time": "0:15:27", "throughput": 2645.89, "total_tokens": 7770552} {"current_steps": 29000, "total_steps": 38150, "loss": 0.1716, "lr": 8.263237034896179e-06, "epoch": 7.601572739187418, "percentage": 76.02, "elapsed_time": "0:48:57", "remaining_time": "0:15:26", "throughput": 2646.02, "total_tokens": 7772232} {"current_steps": 29005, "total_steps": 38150, "loss": 0.1892, "lr": 8.254742731739384e-06, "epoch": 7.6028833551769335, "percentage": 76.03, "elapsed_time": "0:48:57", "remaining_time": "0:15:26", "throughput": 2646.05, "total_tokens": 7773432} {"current_steps": 29010, "total_steps": 38150, "loss": 0.1786, "lr": 8.246251933336e-06, "epoch": 7.604193971166448, "percentage": 76.04, "elapsed_time": "0:48:58", "remaining_time": "0:15:25", "throughput": 2646.03, "total_tokens": 7774472} {"current_steps": 29015, "total_steps": 38150, "loss": 0.1191, "lr": 8.237764641463139e-06, "epoch": 7.605504587155964, "percentage": 76.06, "elapsed_time": "0:48:58", "remaining_time": "0:15:25", "throughput": 2645.99, "total_tokens": 7775448} {"current_steps": 29020, "total_steps": 38150, "loss": 0.2219, "lr": 8.229280857897176e-06, "epoch": 7.606815203145478, "percentage": 76.07, "elapsed_time": "0:48:59", "remaining_time": "0:15:24", "throughput": 2645.97, "total_tokens": 7776520} {"current_steps": 29025, "total_steps": 38150, "loss": 0.3057, "lr": 8.22080058441376e-06, "epoch": 7.608125819134994, "percentage": 76.08, "elapsed_time": "0:48:59", "remaining_time": "0:15:24", "throughput": 2646.09, "total_tokens": 7778200} {"current_steps": 29030, "total_steps": 38150, "loss": 0.2024, "lr": 8.212323822787782e-06, "epoch": 7.6094364351245085, "percentage": 76.09, "elapsed_time": "0:48:59", "remaining_time": "0:15:23", "throughput": 2646.12, "total_tokens": 7779432} {"current_steps": 29035, "total_steps": 38150, "loss": 0.2262, "lr": 8.20385057479342e-06, "epoch": 7.610747051114023, "percentage": 76.11, "elapsed_time": "0:49:00", "remaining_time": "0:15:23", "throughput": 2646.23, "total_tokens": 7781032} {"current_steps": 29040, "total_steps": 38150, "loss": 0.2644, "lr": 8.195380842204112e-06, "epoch": 7.612057667103539, "percentage": 76.12, "elapsed_time": "0:49:00", "remaining_time": "0:15:22", "throughput": 2646.4, "total_tokens": 7782936} {"current_steps": 29045, "total_steps": 38150, "loss": 0.1689, "lr": 8.186914626792558e-06, "epoch": 7.613368283093053, "percentage": 76.13, "elapsed_time": "0:49:01", "remaining_time": "0:15:22", "throughput": 2646.46, "total_tokens": 7784280} {"current_steps": 29050, "total_steps": 38150, "loss": 0.2334, "lr": 8.178451930330719e-06, "epoch": 7.614678899082569, "percentage": 76.15, "elapsed_time": "0:49:01", "remaining_time": "0:15:21", "throughput": 2646.52, "total_tokens": 7785688} {"current_steps": 29055, "total_steps": 38150, "loss": 0.36, "lr": 8.169992754589819e-06, "epoch": 7.6159895150720835, "percentage": 76.16, "elapsed_time": "0:49:02", "remaining_time": "0:15:21", "throughput": 2646.56, "total_tokens": 7786952} {"current_steps": 29060, "total_steps": 38150, "loss": 0.2597, "lr": 8.161537101340375e-06, "epoch": 7.617300131061599, "percentage": 76.17, "elapsed_time": "0:49:02", "remaining_time": "0:15:20", "throughput": 2646.49, "total_tokens": 7787864} {"current_steps": 29065, "total_steps": 38150, "loss": 0.2185, "lr": 8.15308497235211e-06, "epoch": 7.618610747051114, "percentage": 76.19, "elapsed_time": "0:49:03", "remaining_time": "0:15:19", "throughput": 2646.55, "total_tokens": 7789320} {"current_steps": 29070, "total_steps": 38150, "loss": 0.2264, "lr": 8.144636369394048e-06, "epoch": 7.619921363040629, "percentage": 76.2, "elapsed_time": "0:49:03", "remaining_time": "0:15:19", "throughput": 2646.62, "total_tokens": 7790680} {"current_steps": 29075, "total_steps": 38150, "loss": 0.1938, "lr": 8.136191294234474e-06, "epoch": 7.621231979030144, "percentage": 76.21, "elapsed_time": "0:49:04", "remaining_time": "0:15:18", "throughput": 2646.65, "total_tokens": 7791976} {"current_steps": 29080, "total_steps": 38150, "loss": 0.2082, "lr": 8.127749748640923e-06, "epoch": 7.6225425950196595, "percentage": 76.23, "elapsed_time": "0:49:04", "remaining_time": "0:15:18", "throughput": 2646.67, "total_tokens": 7793256} {"current_steps": 29085, "total_steps": 38150, "loss": 0.1307, "lr": 8.119311734380197e-06, "epoch": 7.623853211009174, "percentage": 76.24, "elapsed_time": "0:49:04", "remaining_time": "0:15:17", "throughput": 2646.68, "total_tokens": 7794408} {"current_steps": 29090, "total_steps": 38150, "loss": 0.2023, "lr": 8.110877253218358e-06, "epoch": 7.62516382699869, "percentage": 76.25, "elapsed_time": "0:49:05", "remaining_time": "0:15:17", "throughput": 2646.7, "total_tokens": 7795608} {"current_steps": 29095, "total_steps": 38150, "loss": 0.2908, "lr": 8.102446306920725e-06, "epoch": 7.626474442988204, "percentage": 76.26, "elapsed_time": "0:49:05", "remaining_time": "0:15:16", "throughput": 2646.74, "total_tokens": 7796968} {"current_steps": 29100, "total_steps": 38150, "loss": 0.1881, "lr": 8.094018897251887e-06, "epoch": 7.62778505897772, "percentage": 76.28, "elapsed_time": "0:49:06", "remaining_time": "0:15:16", "throughput": 2646.74, "total_tokens": 7798088} {"current_steps": 29105, "total_steps": 38150, "loss": 0.2073, "lr": 8.085595025975687e-06, "epoch": 7.6290956749672345, "percentage": 76.29, "elapsed_time": "0:49:06", "remaining_time": "0:15:15", "throughput": 2646.74, "total_tokens": 7799272} {"current_steps": 29110, "total_steps": 38150, "loss": 0.2214, "lr": 8.077174694855216e-06, "epoch": 7.63040629095675, "percentage": 76.3, "elapsed_time": "0:49:07", "remaining_time": "0:15:15", "throughput": 2646.79, "total_tokens": 7800648} {"current_steps": 29115, "total_steps": 38150, "loss": 0.1661, "lr": 8.068757905652832e-06, "epoch": 7.631716906946265, "percentage": 76.32, "elapsed_time": "0:49:07", "remaining_time": "0:15:14", "throughput": 2646.91, "total_tokens": 7802200} {"current_steps": 29120, "total_steps": 38150, "loss": 0.2171, "lr": 8.060344660130172e-06, "epoch": 7.63302752293578, "percentage": 76.33, "elapsed_time": "0:49:08", "remaining_time": "0:15:14", "throughput": 2646.9, "total_tokens": 7803304} {"current_steps": 29125, "total_steps": 38150, "loss": 0.1575, "lr": 8.051934960048104e-06, "epoch": 7.634338138925295, "percentage": 76.34, "elapsed_time": "0:49:08", "remaining_time": "0:15:13", "throughput": 2646.81, "total_tokens": 7804136} {"current_steps": 29130, "total_steps": 38150, "loss": 0.3155, "lr": 8.043528807166767e-06, "epoch": 7.6356487549148095, "percentage": 76.36, "elapsed_time": "0:49:08", "remaining_time": "0:15:13", "throughput": 2646.91, "total_tokens": 7805608} {"current_steps": 29135, "total_steps": 38150, "loss": 0.1423, "lr": 8.035126203245552e-06, "epoch": 7.636959370904325, "percentage": 76.37, "elapsed_time": "0:49:09", "remaining_time": "0:15:12", "throughput": 2646.92, "total_tokens": 7806808} {"current_steps": 29140, "total_steps": 38150, "loss": 0.238, "lr": 8.026727150043118e-06, "epoch": 7.63826998689384, "percentage": 76.38, "elapsed_time": "0:49:09", "remaining_time": "0:15:12", "throughput": 2647.0, "total_tokens": 7808312} {"current_steps": 29145, "total_steps": 38150, "loss": 0.1327, "lr": 8.018331649317353e-06, "epoch": 7.639580602883355, "percentage": 76.4, "elapsed_time": "0:49:10", "remaining_time": "0:15:11", "throughput": 2647.0, "total_tokens": 7809496} {"current_steps": 29150, "total_steps": 38150, "loss": 0.2315, "lr": 8.009939702825433e-06, "epoch": 7.64089121887287, "percentage": 76.41, "elapsed_time": "0:49:10", "remaining_time": "0:15:11", "throughput": 2647.04, "total_tokens": 7810792} {"current_steps": 29155, "total_steps": 38150, "loss": 0.158, "lr": 8.001551312323776e-06, "epoch": 7.6422018348623855, "percentage": 76.42, "elapsed_time": "0:49:11", "remaining_time": "0:15:10", "throughput": 2647.02, "total_tokens": 7811832} {"current_steps": 29160, "total_steps": 38150, "loss": 0.1487, "lr": 7.993166479568063e-06, "epoch": 7.6435124508519, "percentage": 76.44, "elapsed_time": "0:49:11", "remaining_time": "0:15:09", "throughput": 2647.04, "total_tokens": 7813032} {"current_steps": 29165, "total_steps": 38150, "loss": 0.2398, "lr": 7.984785206313213e-06, "epoch": 7.644823066841416, "percentage": 76.45, "elapsed_time": "0:49:12", "remaining_time": "0:15:09", "throughput": 2647.11, "total_tokens": 7814472} {"current_steps": 29170, "total_steps": 38150, "loss": 0.2023, "lr": 7.976407494313418e-06, "epoch": 7.64613368283093, "percentage": 76.46, "elapsed_time": "0:49:12", "remaining_time": "0:15:08", "throughput": 2647.28, "total_tokens": 7816312} {"current_steps": 29175, "total_steps": 38150, "loss": 0.1471, "lr": 7.968033345322123e-06, "epoch": 7.647444298820446, "percentage": 76.47, "elapsed_time": "0:49:13", "remaining_time": "0:15:08", "throughput": 2647.32, "total_tokens": 7817736} {"current_steps": 29180, "total_steps": 38150, "loss": 0.1396, "lr": 7.95966276109203e-06, "epoch": 7.6487549148099605, "percentage": 76.49, "elapsed_time": "0:49:13", "remaining_time": "0:15:07", "throughput": 2647.34, "total_tokens": 7818984} {"current_steps": 29185, "total_steps": 38150, "loss": 0.2793, "lr": 7.95129574337507e-06, "epoch": 7.650065530799476, "percentage": 76.5, "elapsed_time": "0:49:13", "remaining_time": "0:15:07", "throughput": 2647.38, "total_tokens": 7820280} {"current_steps": 29190, "total_steps": 38150, "loss": 0.1857, "lr": 7.942932293922453e-06, "epoch": 7.651376146788991, "percentage": 76.51, "elapsed_time": "0:49:14", "remaining_time": "0:15:06", "throughput": 2647.4, "total_tokens": 7821544} {"current_steps": 29195, "total_steps": 38150, "loss": 0.1434, "lr": 7.934572414484634e-06, "epoch": 7.652686762778506, "percentage": 76.53, "elapsed_time": "0:49:14", "remaining_time": "0:15:06", "throughput": 2647.42, "total_tokens": 7822776} {"current_steps": 29200, "total_steps": 38150, "loss": 0.1456, "lr": 7.926216106811321e-06, "epoch": 7.653997378768021, "percentage": 76.54, "elapsed_time": "0:49:15", "remaining_time": "0:15:05", "throughput": 2647.45, "total_tokens": 7824008} {"current_steps": 29205, "total_steps": 38150, "loss": 0.214, "lr": 7.917863372651477e-06, "epoch": 7.655307994757536, "percentage": 76.55, "elapsed_time": "0:49:15", "remaining_time": "0:15:05", "throughput": 2647.55, "total_tokens": 7825528} {"current_steps": 29210, "total_steps": 38150, "loss": 0.1285, "lr": 7.909514213753314e-06, "epoch": 7.656618610747051, "percentage": 76.57, "elapsed_time": "0:49:16", "remaining_time": "0:15:04", "throughput": 2647.61, "total_tokens": 7826952} {"current_steps": 29215, "total_steps": 38150, "loss": 0.1871, "lr": 7.901168631864294e-06, "epoch": 7.657929226736567, "percentage": 76.58, "elapsed_time": "0:49:16", "remaining_time": "0:15:04", "throughput": 2647.63, "total_tokens": 7828152} {"current_steps": 29220, "total_steps": 38150, "loss": 0.3198, "lr": 7.892826628731135e-06, "epoch": 7.659239842726081, "percentage": 76.59, "elapsed_time": "0:49:17", "remaining_time": "0:15:03", "throughput": 2647.75, "total_tokens": 7829864} {"current_steps": 29225, "total_steps": 38150, "loss": 0.1838, "lr": 7.884488206099814e-06, "epoch": 7.660550458715596, "percentage": 76.61, "elapsed_time": "0:49:17", "remaining_time": "0:15:03", "throughput": 2647.78, "total_tokens": 7831096} {"current_steps": 29230, "total_steps": 38150, "loss": 0.2283, "lr": 7.876153365715519e-06, "epoch": 7.6618610747051115, "percentage": 76.62, "elapsed_time": "0:49:18", "remaining_time": "0:15:02", "throughput": 2647.83, "total_tokens": 7832392} {"current_steps": 29235, "total_steps": 38150, "loss": 0.1794, "lr": 7.867822109322747e-06, "epoch": 7.663171690694626, "percentage": 76.63, "elapsed_time": "0:49:18", "remaining_time": "0:15:02", "throughput": 2647.84, "total_tokens": 7833528} {"current_steps": 29240, "total_steps": 38150, "loss": 0.2338, "lr": 7.859494438665204e-06, "epoch": 7.664482306684142, "percentage": 76.64, "elapsed_time": "0:49:18", "remaining_time": "0:15:01", "throughput": 2647.93, "total_tokens": 7835064} {"current_steps": 29245, "total_steps": 38150, "loss": 0.1282, "lr": 7.85117035548586e-06, "epoch": 7.665792922673656, "percentage": 76.66, "elapsed_time": "0:49:19", "remaining_time": "0:15:01", "throughput": 2648.0, "total_tokens": 7836440} {"current_steps": 29250, "total_steps": 38150, "loss": 0.2502, "lr": 7.842849861526929e-06, "epoch": 7.667103538663172, "percentage": 76.67, "elapsed_time": "0:49:19", "remaining_time": "0:15:00", "throughput": 2648.05, "total_tokens": 7837736} {"current_steps": 29255, "total_steps": 38150, "loss": 0.1531, "lr": 7.834532958529878e-06, "epoch": 7.6684141546526865, "percentage": 76.68, "elapsed_time": "0:49:20", "remaining_time": "0:15:00", "throughput": 2648.07, "total_tokens": 7838920} {"current_steps": 29260, "total_steps": 38150, "loss": 0.1391, "lr": 7.826219648235424e-06, "epoch": 7.669724770642202, "percentage": 76.7, "elapsed_time": "0:49:20", "remaining_time": "0:14:59", "throughput": 2648.13, "total_tokens": 7840296} {"current_steps": 29265, "total_steps": 38150, "loss": 0.3512, "lr": 7.817909932383519e-06, "epoch": 7.671035386631717, "percentage": 76.71, "elapsed_time": "0:49:21", "remaining_time": "0:14:59", "throughput": 2648.24, "total_tokens": 7841928} {"current_steps": 29270, "total_steps": 38150, "loss": 0.1721, "lr": 7.809603812713373e-06, "epoch": 7.672346002621232, "percentage": 76.72, "elapsed_time": "0:49:21", "remaining_time": "0:14:58", "throughput": 2648.23, "total_tokens": 7843000} {"current_steps": 29275, "total_steps": 38150, "loss": 0.2855, "lr": 7.80130129096345e-06, "epoch": 7.673656618610747, "percentage": 76.74, "elapsed_time": "0:49:22", "remaining_time": "0:14:57", "throughput": 2648.32, "total_tokens": 7844616} {"current_steps": 29280, "total_steps": 38150, "loss": 0.1903, "lr": 7.793002368871446e-06, "epoch": 7.674967234600262, "percentage": 76.75, "elapsed_time": "0:49:22", "remaining_time": "0:14:57", "throughput": 2648.33, "total_tokens": 7845752} {"current_steps": 29285, "total_steps": 38150, "loss": 0.1655, "lr": 7.78470704817431e-06, "epoch": 7.676277850589777, "percentage": 76.76, "elapsed_time": "0:49:22", "remaining_time": "0:14:56", "throughput": 2648.37, "total_tokens": 7847112} {"current_steps": 29290, "total_steps": 38150, "loss": 0.1413, "lr": 7.77641533060825e-06, "epoch": 7.677588466579293, "percentage": 76.78, "elapsed_time": "0:49:23", "remaining_time": "0:14:56", "throughput": 2648.38, "total_tokens": 7848264} {"current_steps": 29295, "total_steps": 38150, "loss": 0.2575, "lr": 7.76812721790871e-06, "epoch": 7.678899082568807, "percentage": 76.79, "elapsed_time": "0:49:23", "remaining_time": "0:14:55", "throughput": 2648.43, "total_tokens": 7849672} {"current_steps": 29300, "total_steps": 38150, "loss": 0.2388, "lr": 7.759842711810361e-06, "epoch": 7.680209698558322, "percentage": 76.8, "elapsed_time": "0:49:24", "remaining_time": "0:14:55", "throughput": 2648.47, "total_tokens": 7850952} {"current_steps": 29305, "total_steps": 38150, "loss": 0.3193, "lr": 7.751561814047142e-06, "epoch": 7.6815203145478375, "percentage": 76.82, "elapsed_time": "0:49:24", "remaining_time": "0:14:54", "throughput": 2648.51, "total_tokens": 7852216} {"current_steps": 29310, "total_steps": 38150, "loss": 0.1397, "lr": 7.743284526352235e-06, "epoch": 7.682830930537353, "percentage": 76.83, "elapsed_time": "0:49:25", "remaining_time": "0:14:54", "throughput": 2648.52, "total_tokens": 7853368} {"current_steps": 29315, "total_steps": 38150, "loss": 0.2549, "lr": 7.735010850458057e-06, "epoch": 7.684141546526868, "percentage": 76.84, "elapsed_time": "0:49:25", "remaining_time": "0:14:53", "throughput": 2648.63, "total_tokens": 7855080} {"current_steps": 29320, "total_steps": 38150, "loss": 0.2116, "lr": 7.726740788096276e-06, "epoch": 7.685452162516382, "percentage": 76.85, "elapsed_time": "0:49:26", "remaining_time": "0:14:53", "throughput": 2648.7, "total_tokens": 7856536} {"current_steps": 29325, "total_steps": 38150, "loss": 0.3091, "lr": 7.718474340997804e-06, "epoch": 7.686762778505898, "percentage": 76.87, "elapsed_time": "0:49:26", "remaining_time": "0:14:52", "throughput": 2648.79, "total_tokens": 7858104} {"current_steps": 29330, "total_steps": 38150, "loss": 0.3406, "lr": 7.710211510892792e-06, "epoch": 7.6880733944954125, "percentage": 76.88, "elapsed_time": "0:49:27", "remaining_time": "0:14:52", "throughput": 2648.91, "total_tokens": 7859752} {"current_steps": 29335, "total_steps": 38150, "loss": 0.1943, "lr": 7.701952299510634e-06, "epoch": 7.689384010484928, "percentage": 76.89, "elapsed_time": "0:49:27", "remaining_time": "0:14:51", "throughput": 2649.22, "total_tokens": 7862760} {"current_steps": 29340, "total_steps": 38150, "loss": 0.1738, "lr": 7.69369670857998e-06, "epoch": 7.690694626474443, "percentage": 76.91, "elapsed_time": "0:49:28", "remaining_time": "0:14:51", "throughput": 2649.35, "total_tokens": 7864632} {"current_steps": 29345, "total_steps": 38150, "loss": 0.1281, "lr": 7.685444739828688e-06, "epoch": 7.692005242463958, "percentage": 76.92, "elapsed_time": "0:49:29", "remaining_time": "0:14:50", "throughput": 2649.39, "total_tokens": 7866152} {"current_steps": 29350, "total_steps": 38150, "loss": 0.1849, "lr": 7.677196394983902e-06, "epoch": 7.693315858453473, "percentage": 76.93, "elapsed_time": "0:49:29", "remaining_time": "0:14:50", "throughput": 2649.38, "total_tokens": 7867336} {"current_steps": 29355, "total_steps": 38150, "loss": 0.1859, "lr": 7.668951675771979e-06, "epoch": 7.694626474442988, "percentage": 76.95, "elapsed_time": "0:49:29", "remaining_time": "0:14:49", "throughput": 2649.41, "total_tokens": 7868568} {"current_steps": 29360, "total_steps": 38150, "loss": 0.1822, "lr": 7.660710583918524e-06, "epoch": 7.695937090432503, "percentage": 76.96, "elapsed_time": "0:49:30", "remaining_time": "0:14:49", "throughput": 2649.41, "total_tokens": 7869784} {"current_steps": 29365, "total_steps": 38150, "loss": 0.3343, "lr": 7.652473121148383e-06, "epoch": 7.697247706422019, "percentage": 76.97, "elapsed_time": "0:49:30", "remaining_time": "0:14:48", "throughput": 2649.45, "total_tokens": 7871112} {"current_steps": 29370, "total_steps": 38150, "loss": 0.2481, "lr": 7.644239289185644e-06, "epoch": 7.698558322411533, "percentage": 76.99, "elapsed_time": "0:49:31", "remaining_time": "0:14:48", "throughput": 2649.55, "total_tokens": 7872776} {"current_steps": 29375, "total_steps": 38150, "loss": 0.1546, "lr": 7.636009089753643e-06, "epoch": 7.699868938401049, "percentage": 77.0, "elapsed_time": "0:49:31", "remaining_time": "0:14:47", "throughput": 2649.6, "total_tokens": 7874056} {"current_steps": 29380, "total_steps": 38150, "loss": 0.2443, "lr": 7.627782524574925e-06, "epoch": 7.7011795543905635, "percentage": 77.01, "elapsed_time": "0:49:32", "remaining_time": "0:14:47", "throughput": 2649.61, "total_tokens": 7875224} {"current_steps": 29385, "total_steps": 38150, "loss": 0.1775, "lr": 7.619559595371312e-06, "epoch": 7.702490170380079, "percentage": 77.02, "elapsed_time": "0:49:32", "remaining_time": "0:14:46", "throughput": 2649.63, "total_tokens": 7876536} {"current_steps": 29390, "total_steps": 38150, "loss": 0.171, "lr": 7.611340303863843e-06, "epoch": 7.703800786369594, "percentage": 77.04, "elapsed_time": "0:49:33", "remaining_time": "0:14:46", "throughput": 2649.64, "total_tokens": 7877688} {"current_steps": 29395, "total_steps": 38150, "loss": 0.2037, "lr": 7.603124651772803e-06, "epoch": 7.705111402359108, "percentage": 77.05, "elapsed_time": "0:49:33", "remaining_time": "0:14:45", "throughput": 2649.68, "total_tokens": 7878968} {"current_steps": 29400, "total_steps": 38150, "loss": 0.0796, "lr": 7.594912640817705e-06, "epoch": 7.706422018348624, "percentage": 77.06, "elapsed_time": "0:49:34", "remaining_time": "0:14:45", "throughput": 2649.7, "total_tokens": 7880312} {"current_steps": 29405, "total_steps": 38150, "loss": 0.2009, "lr": 7.586704272717327e-06, "epoch": 7.707732634338139, "percentage": 77.08, "elapsed_time": "0:49:34", "remaining_time": "0:14:44", "throughput": 2649.79, "total_tokens": 7881832} {"current_steps": 29410, "total_steps": 38150, "loss": 0.1215, "lr": 7.578499549189655e-06, "epoch": 7.709043250327654, "percentage": 77.09, "elapsed_time": "0:49:34", "remaining_time": "0:14:44", "throughput": 2649.79, "total_tokens": 7882984} {"current_steps": 29415, "total_steps": 38150, "loss": 0.1318, "lr": 7.570298471951934e-06, "epoch": 7.710353866317169, "percentage": 77.1, "elapsed_time": "0:49:35", "remaining_time": "0:14:43", "throughput": 2649.86, "total_tokens": 7884440} {"current_steps": 29420, "total_steps": 38150, "loss": 0.3664, "lr": 7.562101042720621e-06, "epoch": 7.711664482306684, "percentage": 77.12, "elapsed_time": "0:49:35", "remaining_time": "0:14:43", "throughput": 2649.91, "total_tokens": 7885800} {"current_steps": 29425, "total_steps": 38150, "loss": 0.2453, "lr": 7.553907263211427e-06, "epoch": 7.712975098296199, "percentage": 77.13, "elapsed_time": "0:49:36", "remaining_time": "0:14:42", "throughput": 2649.92, "total_tokens": 7886968} {"current_steps": 29430, "total_steps": 38150, "loss": 0.188, "lr": 7.545717135139299e-06, "epoch": 7.714285714285714, "percentage": 77.14, "elapsed_time": "0:49:36", "remaining_time": "0:14:42", "throughput": 2650.11, "total_tokens": 7888904} {"current_steps": 29435, "total_steps": 38150, "loss": 0.1203, "lr": 7.537530660218414e-06, "epoch": 7.715596330275229, "percentage": 77.16, "elapsed_time": "0:49:37", "remaining_time": "0:14:41", "throughput": 2650.09, "total_tokens": 7889944} {"current_steps": 29440, "total_steps": 38150, "loss": 0.2101, "lr": 7.529347840162193e-06, "epoch": 7.716906946264745, "percentage": 77.17, "elapsed_time": "0:49:37", "remaining_time": "0:14:40", "throughput": 2650.08, "total_tokens": 7891048} {"current_steps": 29445, "total_steps": 38150, "loss": 0.2084, "lr": 7.52116867668328e-06, "epoch": 7.718217562254259, "percentage": 77.18, "elapsed_time": "0:49:38", "remaining_time": "0:14:40", "throughput": 2650.16, "total_tokens": 7892504} {"current_steps": 29450, "total_steps": 38150, "loss": 0.2564, "lr": 7.51299317149356e-06, "epoch": 7.719528178243775, "percentage": 77.2, "elapsed_time": "0:49:38", "remaining_time": "0:14:39", "throughput": 2650.22, "total_tokens": 7893848} {"current_steps": 29455, "total_steps": 38150, "loss": 0.1654, "lr": 7.504821326304157e-06, "epoch": 7.7208387942332894, "percentage": 77.21, "elapsed_time": "0:49:39", "remaining_time": "0:14:39", "throughput": 2650.26, "total_tokens": 7895192} {"current_steps": 29460, "total_steps": 38150, "loss": 0.1511, "lr": 7.496653142825419e-06, "epoch": 7.722149410222805, "percentage": 77.22, "elapsed_time": "0:49:39", "remaining_time": "0:14:38", "throughput": 2650.27, "total_tokens": 7896424} {"current_steps": 29465, "total_steps": 38150, "loss": 0.1353, "lr": 7.4884886227669375e-06, "epoch": 7.72346002621232, "percentage": 77.23, "elapsed_time": "0:49:39", "remaining_time": "0:14:38", "throughput": 2650.36, "total_tokens": 7897992} {"current_steps": 29470, "total_steps": 38150, "loss": 0.1758, "lr": 7.480327767837525e-06, "epoch": 7.724770642201835, "percentage": 77.25, "elapsed_time": "0:49:40", "remaining_time": "0:14:37", "throughput": 2650.34, "total_tokens": 7899128} {"current_steps": 29475, "total_steps": 38150, "loss": 0.2879, "lr": 7.472170579745244e-06, "epoch": 7.72608125819135, "percentage": 77.26, "elapsed_time": "0:49:40", "remaining_time": "0:14:37", "throughput": 2650.4, "total_tokens": 7900568} {"current_steps": 29480, "total_steps": 38150, "loss": 0.214, "lr": 7.464017060197373e-06, "epoch": 7.727391874180865, "percentage": 77.27, "elapsed_time": "0:49:41", "remaining_time": "0:14:36", "throughput": 2650.47, "total_tokens": 7902024} {"current_steps": 29485, "total_steps": 38150, "loss": 0.0902, "lr": 7.45586721090043e-06, "epoch": 7.72870249017038, "percentage": 77.29, "elapsed_time": "0:49:41", "remaining_time": "0:14:36", "throughput": 2650.52, "total_tokens": 7903416} {"current_steps": 29490, "total_steps": 38150, "loss": 0.202, "lr": 7.447721033560168e-06, "epoch": 7.730013106159895, "percentage": 77.3, "elapsed_time": "0:49:42", "remaining_time": "0:14:35", "throughput": 2650.52, "total_tokens": 7904552} {"current_steps": 29495, "total_steps": 38150, "loss": 0.146, "lr": 7.439578529881572e-06, "epoch": 7.73132372214941, "percentage": 77.31, "elapsed_time": "0:49:42", "remaining_time": "0:14:35", "throughput": 2650.54, "total_tokens": 7905752} {"current_steps": 29500, "total_steps": 38150, "loss": 0.1485, "lr": 7.431439701568841e-06, "epoch": 7.732634338138926, "percentage": 77.33, "elapsed_time": "0:49:43", "remaining_time": "0:14:34", "throughput": 2650.62, "total_tokens": 7907240} {"current_steps": 29505, "total_steps": 38150, "loss": 0.2169, "lr": 7.423304550325422e-06, "epoch": 7.73394495412844, "percentage": 77.34, "elapsed_time": "0:49:43", "remaining_time": "0:14:34", "throughput": 2650.61, "total_tokens": 7908296} {"current_steps": 29510, "total_steps": 38150, "loss": 0.1363, "lr": 7.415173077853993e-06, "epoch": 7.735255570117955, "percentage": 77.35, "elapsed_time": "0:49:44", "remaining_time": "0:14:33", "throughput": 2650.58, "total_tokens": 7909384} {"current_steps": 29515, "total_steps": 38150, "loss": 0.2264, "lr": 7.407045285856445e-06, "epoch": 7.736566186107471, "percentage": 77.37, "elapsed_time": "0:49:44", "remaining_time": "0:14:33", "throughput": 2650.7, "total_tokens": 7911080} {"current_steps": 29520, "total_steps": 38150, "loss": 0.2178, "lr": 7.39892117603393e-06, "epoch": 7.737876802096985, "percentage": 77.38, "elapsed_time": "0:49:44", "remaining_time": "0:14:32", "throughput": 2650.63, "total_tokens": 7911976} {"current_steps": 29525, "total_steps": 38150, "loss": 0.2724, "lr": 7.390800750086799e-06, "epoch": 7.739187418086501, "percentage": 77.39, "elapsed_time": "0:49:45", "remaining_time": "0:14:32", "throughput": 2650.69, "total_tokens": 7913416} {"current_steps": 29530, "total_steps": 38150, "loss": 0.2077, "lr": 7.382684009714652e-06, "epoch": 7.740498034076015, "percentage": 77.4, "elapsed_time": "0:49:45", "remaining_time": "0:14:31", "throughput": 2650.78, "total_tokens": 7914936} {"current_steps": 29535, "total_steps": 38150, "loss": 0.4136, "lr": 7.374570956616295e-06, "epoch": 7.741808650065531, "percentage": 77.42, "elapsed_time": "0:49:46", "remaining_time": "0:14:31", "throughput": 2651.13, "total_tokens": 7918200} {"current_steps": 29540, "total_steps": 38150, "loss": 0.2349, "lr": 7.366461592489782e-06, "epoch": 7.743119266055046, "percentage": 77.43, "elapsed_time": "0:49:47", "remaining_time": "0:14:30", "throughput": 2651.09, "total_tokens": 7919208} {"current_steps": 29545, "total_steps": 38150, "loss": 0.1775, "lr": 7.358355919032389e-06, "epoch": 7.744429882044561, "percentage": 77.44, "elapsed_time": "0:49:47", "remaining_time": "0:14:30", "throughput": 2651.16, "total_tokens": 7920648} {"current_steps": 29550, "total_steps": 38150, "loss": 0.123, "lr": 7.350253937940621e-06, "epoch": 7.745740498034076, "percentage": 77.46, "elapsed_time": "0:49:48", "remaining_time": "0:14:29", "throughput": 2651.09, "total_tokens": 7921544} {"current_steps": 29555, "total_steps": 38150, "loss": 0.1088, "lr": 7.342155650910207e-06, "epoch": 7.747051114023591, "percentage": 77.47, "elapsed_time": "0:49:48", "remaining_time": "0:14:29", "throughput": 2651.1, "total_tokens": 7922648} {"current_steps": 29560, "total_steps": 38150, "loss": 0.1437, "lr": 7.334061059636102e-06, "epoch": 7.748361730013106, "percentage": 77.48, "elapsed_time": "0:49:48", "remaining_time": "0:14:28", "throughput": 2651.12, "total_tokens": 7923880} {"current_steps": 29565, "total_steps": 38150, "loss": 0.1718, "lr": 7.325970165812496e-06, "epoch": 7.749672346002622, "percentage": 77.5, "elapsed_time": "0:49:49", "remaining_time": "0:14:28", "throughput": 2651.22, "total_tokens": 7925592} {"current_steps": 29570, "total_steps": 38150, "loss": 0.1819, "lr": 7.3178829711327945e-06, "epoch": 7.750982961992136, "percentage": 77.51, "elapsed_time": "0:49:49", "remaining_time": "0:14:27", "throughput": 2651.27, "total_tokens": 7926856} {"current_steps": 29575, "total_steps": 38150, "loss": 0.2214, "lr": 7.309799477289636e-06, "epoch": 7.752293577981652, "percentage": 77.52, "elapsed_time": "0:49:50", "remaining_time": "0:14:27", "throughput": 2651.27, "total_tokens": 7928056} {"current_steps": 29580, "total_steps": 38150, "loss": 0.2201, "lr": 7.301719685974881e-06, "epoch": 7.753604193971166, "percentage": 77.54, "elapsed_time": "0:49:50", "remaining_time": "0:14:26", "throughput": 2651.23, "total_tokens": 7929032} {"current_steps": 29585, "total_steps": 38150, "loss": 0.1874, "lr": 7.293643598879612e-06, "epoch": 7.754914809960681, "percentage": 77.55, "elapsed_time": "0:49:51", "remaining_time": "0:14:25", "throughput": 2651.19, "total_tokens": 7930056} {"current_steps": 29590, "total_steps": 38150, "loss": 0.2376, "lr": 7.285571217694148e-06, "epoch": 7.756225425950197, "percentage": 77.56, "elapsed_time": "0:49:51", "remaining_time": "0:14:25", "throughput": 2651.23, "total_tokens": 7931288} {"current_steps": 29595, "total_steps": 38150, "loss": 0.2171, "lr": 7.277502544108017e-06, "epoch": 7.757536041939712, "percentage": 77.58, "elapsed_time": "0:49:52", "remaining_time": "0:14:24", "throughput": 2651.2, "total_tokens": 7932424} {"current_steps": 29600, "total_steps": 38150, "loss": 0.1685, "lr": 7.2694375798099815e-06, "epoch": 7.758846657929227, "percentage": 77.59, "elapsed_time": "0:49:52", "remaining_time": "0:14:24", "throughput": 2651.3, "total_tokens": 7933880} {"current_steps": 29605, "total_steps": 38150, "loss": 0.3557, "lr": 7.261376326488026e-06, "epoch": 7.760157273918741, "percentage": 77.6, "elapsed_time": "0:49:52", "remaining_time": "0:14:23", "throughput": 2651.32, "total_tokens": 7935080} {"current_steps": 29610, "total_steps": 38150, "loss": 0.2368, "lr": 7.253318785829363e-06, "epoch": 7.761467889908257, "percentage": 77.61, "elapsed_time": "0:49:53", "remaining_time": "0:14:23", "throughput": 2651.31, "total_tokens": 7936168} {"current_steps": 29615, "total_steps": 38150, "loss": 0.1456, "lr": 7.245264959520406e-06, "epoch": 7.762778505897772, "percentage": 77.63, "elapsed_time": "0:49:53", "remaining_time": "0:14:22", "throughput": 2651.33, "total_tokens": 7937352} {"current_steps": 29620, "total_steps": 38150, "loss": 0.1666, "lr": 7.237214849246815e-06, "epoch": 7.764089121887287, "percentage": 77.64, "elapsed_time": "0:49:54", "remaining_time": "0:14:22", "throughput": 2651.37, "total_tokens": 7938712} {"current_steps": 29625, "total_steps": 38150, "loss": 0.3286, "lr": 7.2291684566934634e-06, "epoch": 7.765399737876802, "percentage": 77.65, "elapsed_time": "0:49:54", "remaining_time": "0:14:21", "throughput": 2651.55, "total_tokens": 7940664} {"current_steps": 29630, "total_steps": 38150, "loss": 0.2081, "lr": 7.221125783544441e-06, "epoch": 7.766710353866317, "percentage": 77.67, "elapsed_time": "0:49:55", "remaining_time": "0:14:21", "throughput": 2651.62, "total_tokens": 7942088} {"current_steps": 29635, "total_steps": 38150, "loss": 0.1321, "lr": 7.213086831483082e-06, "epoch": 7.768020969855832, "percentage": 77.68, "elapsed_time": "0:49:55", "remaining_time": "0:14:20", "throughput": 2651.64, "total_tokens": 7943352} {"current_steps": 29640, "total_steps": 38150, "loss": 0.1755, "lr": 7.205051602191914e-06, "epoch": 7.7693315858453476, "percentage": 77.69, "elapsed_time": "0:49:56", "remaining_time": "0:14:20", "throughput": 2651.71, "total_tokens": 7944728} {"current_steps": 29645, "total_steps": 38150, "loss": 0.2649, "lr": 7.1970200973527e-06, "epoch": 7.770642201834862, "percentage": 77.71, "elapsed_time": "0:49:56", "remaining_time": "0:14:19", "throughput": 2651.75, "total_tokens": 7946072} {"current_steps": 29650, "total_steps": 38150, "loss": 0.1881, "lr": 7.188992318646423e-06, "epoch": 7.771952817824378, "percentage": 77.72, "elapsed_time": "0:49:56", "remaining_time": "0:14:19", "throughput": 2651.67, "total_tokens": 7946920} {"current_steps": 29655, "total_steps": 38150, "loss": 0.2668, "lr": 7.180968267753274e-06, "epoch": 7.773263433813892, "percentage": 77.73, "elapsed_time": "0:49:57", "remaining_time": "0:14:18", "throughput": 2651.78, "total_tokens": 7948616} {"current_steps": 29660, "total_steps": 38150, "loss": 0.1905, "lr": 7.172947946352676e-06, "epoch": 7.774574049803408, "percentage": 77.75, "elapsed_time": "0:49:57", "remaining_time": "0:14:18", "throughput": 2651.98, "total_tokens": 7950600} {"current_steps": 29665, "total_steps": 38150, "loss": 0.2299, "lr": 7.164931356123269e-06, "epoch": 7.775884665792923, "percentage": 77.76, "elapsed_time": "0:49:58", "remaining_time": "0:14:17", "throughput": 2651.98, "total_tokens": 7951752} {"current_steps": 29670, "total_steps": 38150, "loss": 0.2351, "lr": 7.156918498742915e-06, "epoch": 7.777195281782438, "percentage": 77.77, "elapsed_time": "0:49:58", "remaining_time": "0:14:17", "throughput": 2652.06, "total_tokens": 7953256} {"current_steps": 29675, "total_steps": 38150, "loss": 0.086, "lr": 7.148909375888688e-06, "epoch": 7.778505897771953, "percentage": 77.79, "elapsed_time": "0:49:59", "remaining_time": "0:14:16", "throughput": 2652.09, "total_tokens": 7954488} {"current_steps": 29680, "total_steps": 38150, "loss": 0.2752, "lr": 7.140903989236886e-06, "epoch": 7.779816513761467, "percentage": 77.8, "elapsed_time": "0:49:59", "remaining_time": "0:14:16", "throughput": 2652.12, "total_tokens": 7955816} {"current_steps": 29685, "total_steps": 38150, "loss": 0.2498, "lr": 7.132902340463018e-06, "epoch": 7.781127129750983, "percentage": 77.81, "elapsed_time": "0:50:00", "remaining_time": "0:14:15", "throughput": 2652.2, "total_tokens": 7957304} {"current_steps": 29690, "total_steps": 38150, "loss": 0.3091, "lr": 7.124904431241819e-06, "epoch": 7.7824377457404985, "percentage": 77.82, "elapsed_time": "0:50:00", "remaining_time": "0:14:15", "throughput": 2652.24, "total_tokens": 7958616} {"current_steps": 29695, "total_steps": 38150, "loss": 0.1254, "lr": 7.116910263247237e-06, "epoch": 7.783748361730013, "percentage": 77.84, "elapsed_time": "0:50:01", "remaining_time": "0:14:14", "throughput": 2652.27, "total_tokens": 7959848} {"current_steps": 29700, "total_steps": 38150, "loss": 0.208, "lr": 7.108919838152436e-06, "epoch": 7.785058977719528, "percentage": 77.85, "elapsed_time": "0:50:01", "remaining_time": "0:14:13", "throughput": 2652.27, "total_tokens": 7961048} {"current_steps": 29705, "total_steps": 38150, "loss": 0.2412, "lr": 7.100933157629802e-06, "epoch": 7.786369593709043, "percentage": 77.86, "elapsed_time": "0:50:02", "remaining_time": "0:14:13", "throughput": 2652.38, "total_tokens": 7962648} {"current_steps": 29710, "total_steps": 38150, "loss": 0.2704, "lr": 7.09295022335093e-06, "epoch": 7.787680209698558, "percentage": 77.88, "elapsed_time": "0:50:02", "remaining_time": "0:14:12", "throughput": 2652.45, "total_tokens": 7964008} {"current_steps": 29715, "total_steps": 38150, "loss": 0.2455, "lr": 7.0849710369866345e-06, "epoch": 7.7889908256880735, "percentage": 77.89, "elapsed_time": "0:50:02", "remaining_time": "0:14:12", "throughput": 2652.47, "total_tokens": 7965176} {"current_steps": 29720, "total_steps": 38150, "loss": 0.2208, "lr": 7.076995600206948e-06, "epoch": 7.790301441677588, "percentage": 77.9, "elapsed_time": "0:50:03", "remaining_time": "0:14:11", "throughput": 2652.51, "total_tokens": 7966568} {"current_steps": 29725, "total_steps": 38150, "loss": 0.2394, "lr": 7.069023914681111e-06, "epoch": 7.791612057667104, "percentage": 77.92, "elapsed_time": "0:50:03", "remaining_time": "0:14:11", "throughput": 2652.56, "total_tokens": 7967880} {"current_steps": 29730, "total_steps": 38150, "loss": 0.2955, "lr": 7.0610559820775965e-06, "epoch": 7.792922673656618, "percentage": 77.93, "elapsed_time": "0:50:04", "remaining_time": "0:14:10", "throughput": 2652.63, "total_tokens": 7969448} {"current_steps": 29735, "total_steps": 38150, "loss": 0.2498, "lr": 7.05309180406406e-06, "epoch": 7.794233289646134, "percentage": 77.94, "elapsed_time": "0:50:04", "remaining_time": "0:14:10", "throughput": 2652.6, "total_tokens": 7970488} {"current_steps": 29740, "total_steps": 38150, "loss": 0.1972, "lr": 7.045131382307399e-06, "epoch": 7.795543905635649, "percentage": 77.96, "elapsed_time": "0:50:05", "remaining_time": "0:14:09", "throughput": 2652.57, "total_tokens": 7971560} {"current_steps": 29745, "total_steps": 38150, "loss": 0.2823, "lr": 7.0371747184737075e-06, "epoch": 7.796854521625164, "percentage": 77.97, "elapsed_time": "0:50:05", "remaining_time": "0:14:09", "throughput": 2652.63, "total_tokens": 7973032} {"current_steps": 29750, "total_steps": 38150, "loss": 0.3024, "lr": 7.02922181422832e-06, "epoch": 7.798165137614679, "percentage": 77.98, "elapsed_time": "0:50:06", "remaining_time": "0:14:08", "throughput": 2652.84, "total_tokens": 7975176} {"current_steps": 29755, "total_steps": 38150, "loss": 0.3936, "lr": 7.021272671235754e-06, "epoch": 7.799475753604194, "percentage": 77.99, "elapsed_time": "0:50:06", "remaining_time": "0:14:08", "throughput": 2652.87, "total_tokens": 7976392} {"current_steps": 29760, "total_steps": 38150, "loss": 0.2025, "lr": 7.013327291159755e-06, "epoch": 7.800786369593709, "percentage": 78.01, "elapsed_time": "0:50:07", "remaining_time": "0:14:07", "throughput": 2652.96, "total_tokens": 7977848} {"current_steps": 29765, "total_steps": 38150, "loss": 0.1868, "lr": 7.0053856756632815e-06, "epoch": 7.8020969855832245, "percentage": 78.02, "elapsed_time": "0:50:07", "remaining_time": "0:14:07", "throughput": 2653.06, "total_tokens": 7979368} {"current_steps": 29770, "total_steps": 38150, "loss": 0.3531, "lr": 6.997447826408485e-06, "epoch": 7.803407601572739, "percentage": 78.03, "elapsed_time": "0:50:08", "remaining_time": "0:14:06", "throughput": 2653.1, "total_tokens": 7980616} {"current_steps": 29775, "total_steps": 38150, "loss": 0.1942, "lr": 6.989513745056753e-06, "epoch": 7.804718217562254, "percentage": 78.05, "elapsed_time": "0:50:08", "remaining_time": "0:14:06", "throughput": 2653.09, "total_tokens": 7981688} {"current_steps": 29780, "total_steps": 38150, "loss": 0.2228, "lr": 6.981583433268676e-06, "epoch": 7.806028833551769, "percentage": 78.06, "elapsed_time": "0:50:08", "remaining_time": "0:14:05", "throughput": 2653.13, "total_tokens": 7983112} {"current_steps": 29785, "total_steps": 38150, "loss": 0.1075, "lr": 6.97365689270405e-06, "epoch": 7.807339449541285, "percentage": 78.07, "elapsed_time": "0:50:09", "remaining_time": "0:14:05", "throughput": 2653.08, "total_tokens": 7984088} {"current_steps": 29790, "total_steps": 38150, "loss": 0.1692, "lr": 6.965734125021892e-06, "epoch": 7.8086500655307995, "percentage": 78.09, "elapsed_time": "0:50:09", "remaining_time": "0:14:04", "throughput": 2653.14, "total_tokens": 7985512} {"current_steps": 29795, "total_steps": 38150, "loss": 0.2548, "lr": 6.957815131880421e-06, "epoch": 7.809960681520314, "percentage": 78.1, "elapsed_time": "0:50:10", "remaining_time": "0:14:04", "throughput": 2653.23, "total_tokens": 7987096} {"current_steps": 29800, "total_steps": 38150, "loss": 0.2288, "lr": 6.949899914937066e-06, "epoch": 7.81127129750983, "percentage": 78.11, "elapsed_time": "0:50:10", "remaining_time": "0:14:03", "throughput": 2653.36, "total_tokens": 7988824} {"current_steps": 29805, "total_steps": 38150, "loss": 0.1631, "lr": 6.941988475848474e-06, "epoch": 7.812581913499344, "percentage": 78.13, "elapsed_time": "0:50:11", "remaining_time": "0:14:03", "throughput": 2653.44, "total_tokens": 7990408} {"current_steps": 29810, "total_steps": 38150, "loss": 0.2424, "lr": 6.934080816270488e-06, "epoch": 7.81389252948886, "percentage": 78.14, "elapsed_time": "0:50:11", "remaining_time": "0:14:02", "throughput": 2653.44, "total_tokens": 7991544} {"current_steps": 29815, "total_steps": 38150, "loss": 0.3012, "lr": 6.926176937858175e-06, "epoch": 7.815203145478375, "percentage": 78.15, "elapsed_time": "0:50:12", "remaining_time": "0:14:02", "throughput": 2653.48, "total_tokens": 7992808} {"current_steps": 29820, "total_steps": 38150, "loss": 0.1259, "lr": 6.9182768422658e-06, "epoch": 7.81651376146789, "percentage": 78.17, "elapsed_time": "0:50:12", "remaining_time": "0:14:01", "throughput": 2653.53, "total_tokens": 7994088} {"current_steps": 29825, "total_steps": 38150, "loss": 0.4491, "lr": 6.910380531146837e-06, "epoch": 7.817824377457405, "percentage": 78.18, "elapsed_time": "0:50:13", "remaining_time": "0:14:01", "throughput": 2653.59, "total_tokens": 7995496} {"current_steps": 29830, "total_steps": 38150, "loss": 0.3341, "lr": 6.902488006153973e-06, "epoch": 7.81913499344692, "percentage": 78.19, "elapsed_time": "0:50:13", "remaining_time": "0:14:00", "throughput": 2653.66, "total_tokens": 7996856} {"current_steps": 29835, "total_steps": 38150, "loss": 0.2747, "lr": 6.894599268939101e-06, "epoch": 7.820445609436435, "percentage": 78.2, "elapsed_time": "0:50:13", "remaining_time": "0:13:59", "throughput": 2653.67, "total_tokens": 7998008} {"current_steps": 29840, "total_steps": 38150, "loss": 0.2795, "lr": 6.886714321153315e-06, "epoch": 7.8217562254259505, "percentage": 78.22, "elapsed_time": "0:50:14", "remaining_time": "0:13:59", "throughput": 2653.75, "total_tokens": 7999432} {"current_steps": 29845, "total_steps": 38150, "loss": 0.1314, "lr": 6.8788331644469265e-06, "epoch": 7.823066841415465, "percentage": 78.23, "elapsed_time": "0:50:14", "remaining_time": "0:13:58", "throughput": 2653.79, "total_tokens": 8000680} {"current_steps": 29850, "total_steps": 38150, "loss": 0.1013, "lr": 6.870955800469453e-06, "epoch": 7.824377457404981, "percentage": 78.24, "elapsed_time": "0:50:15", "remaining_time": "0:13:58", "throughput": 2653.81, "total_tokens": 8001880} {"current_steps": 29855, "total_steps": 38150, "loss": 0.206, "lr": 6.863082230869597e-06, "epoch": 7.825688073394495, "percentage": 78.26, "elapsed_time": "0:50:15", "remaining_time": "0:13:57", "throughput": 2653.87, "total_tokens": 8003288} {"current_steps": 29860, "total_steps": 38150, "loss": 0.256, "lr": 6.855212457295285e-06, "epoch": 7.826998689384011, "percentage": 78.27, "elapsed_time": "0:50:16", "remaining_time": "0:13:57", "throughput": 2653.97, "total_tokens": 8004888} {"current_steps": 29865, "total_steps": 38150, "loss": 0.1669, "lr": 6.847346481393663e-06, "epoch": 7.8283093053735255, "percentage": 78.28, "elapsed_time": "0:50:16", "remaining_time": "0:13:56", "throughput": 2653.95, "total_tokens": 8005944} {"current_steps": 29870, "total_steps": 38150, "loss": 0.2208, "lr": 6.839484304811055e-06, "epoch": 7.82961992136304, "percentage": 78.3, "elapsed_time": "0:50:17", "remaining_time": "0:13:56", "throughput": 2653.98, "total_tokens": 8007240} {"current_steps": 29875, "total_steps": 38150, "loss": 0.1929, "lr": 6.831625929193006e-06, "epoch": 7.830930537352556, "percentage": 78.31, "elapsed_time": "0:50:17", "remaining_time": "0:13:55", "throughput": 2654.0, "total_tokens": 8008440} {"current_steps": 29880, "total_steps": 38150, "loss": 0.196, "lr": 6.8237713561842556e-06, "epoch": 7.832241153342071, "percentage": 78.32, "elapsed_time": "0:50:17", "remaining_time": "0:13:55", "throughput": 2654.0, "total_tokens": 8009576} {"current_steps": 29885, "total_steps": 38150, "loss": 0.2311, "lr": 6.815920587428759e-06, "epoch": 7.833551769331586, "percentage": 78.34, "elapsed_time": "0:50:18", "remaining_time": "0:13:54", "throughput": 2654.11, "total_tokens": 8011288} {"current_steps": 29890, "total_steps": 38150, "loss": 0.2279, "lr": 6.808073624569661e-06, "epoch": 7.834862385321101, "percentage": 78.35, "elapsed_time": "0:50:19", "remaining_time": "0:13:54", "throughput": 2654.48, "total_tokens": 8014760} {"current_steps": 29895, "total_steps": 38150, "loss": 0.329, "lr": 6.8002304692493165e-06, "epoch": 7.836173001310616, "percentage": 78.36, "elapsed_time": "0:50:19", "remaining_time": "0:13:53", "throughput": 2654.43, "total_tokens": 8015736} {"current_steps": 29900, "total_steps": 38150, "loss": 0.1806, "lr": 6.79239112310929e-06, "epoch": 7.837483617300131, "percentage": 78.37, "elapsed_time": "0:50:20", "remaining_time": "0:13:53", "throughput": 2654.46, "total_tokens": 8017032} {"current_steps": 29905, "total_steps": 38150, "loss": 0.1839, "lr": 6.784555587790342e-06, "epoch": 7.838794233289646, "percentage": 78.39, "elapsed_time": "0:50:20", "remaining_time": "0:13:52", "throughput": 2654.57, "total_tokens": 8018600} {"current_steps": 29910, "total_steps": 38150, "loss": 0.2603, "lr": 6.7767238649324325e-06, "epoch": 7.840104849279161, "percentage": 78.4, "elapsed_time": "0:50:21", "remaining_time": "0:13:52", "throughput": 2654.63, "total_tokens": 8019944} {"current_steps": 29915, "total_steps": 38150, "loss": 0.2834, "lr": 6.768895956174726e-06, "epoch": 7.8414154652686765, "percentage": 78.41, "elapsed_time": "0:50:21", "remaining_time": "0:13:51", "throughput": 2654.77, "total_tokens": 8021784} {"current_steps": 29920, "total_steps": 38150, "loss": 0.2841, "lr": 6.761071863155607e-06, "epoch": 7.842726081258191, "percentage": 78.43, "elapsed_time": "0:50:22", "remaining_time": "0:13:51", "throughput": 2654.75, "total_tokens": 8022920} {"current_steps": 29925, "total_steps": 38150, "loss": 0.2864, "lr": 6.7532515875126295e-06, "epoch": 7.844036697247707, "percentage": 78.44, "elapsed_time": "0:50:22", "remaining_time": "0:13:50", "throughput": 2654.77, "total_tokens": 8024200} {"current_steps": 29930, "total_steps": 38150, "loss": 0.2904, "lr": 6.7454351308825634e-06, "epoch": 7.845347313237221, "percentage": 78.45, "elapsed_time": "0:50:23", "remaining_time": "0:13:50", "throughput": 2654.83, "total_tokens": 8025640} {"current_steps": 29935, "total_steps": 38150, "loss": 0.3199, "lr": 6.737622494901383e-06, "epoch": 7.846657929226737, "percentage": 78.47, "elapsed_time": "0:50:23", "remaining_time": "0:13:49", "throughput": 2654.82, "total_tokens": 8026696} {"current_steps": 29940, "total_steps": 38150, "loss": 0.1805, "lr": 6.7298136812042615e-06, "epoch": 7.8479685452162515, "percentage": 78.48, "elapsed_time": "0:50:23", "remaining_time": "0:13:49", "throughput": 2654.8, "total_tokens": 8027768} {"current_steps": 29945, "total_steps": 38150, "loss": 0.2143, "lr": 6.722008691425566e-06, "epoch": 7.849279161205767, "percentage": 78.49, "elapsed_time": "0:50:24", "remaining_time": "0:13:48", "throughput": 2654.9, "total_tokens": 8029384} {"current_steps": 29950, "total_steps": 38150, "loss": 0.1939, "lr": 6.7142075271988705e-06, "epoch": 7.850589777195282, "percentage": 78.51, "elapsed_time": "0:50:24", "remaining_time": "0:13:48", "throughput": 2655.03, "total_tokens": 8031144} {"current_steps": 29955, "total_steps": 38150, "loss": 0.1934, "lr": 6.706410190156945e-06, "epoch": 7.851900393184797, "percentage": 78.52, "elapsed_time": "0:50:25", "remaining_time": "0:13:47", "throughput": 2655.1, "total_tokens": 8032536} {"current_steps": 29960, "total_steps": 38150, "loss": 0.2379, "lr": 6.698616681931754e-06, "epoch": 7.853211009174312, "percentage": 78.53, "elapsed_time": "0:50:25", "remaining_time": "0:13:47", "throughput": 2655.11, "total_tokens": 8033672} {"current_steps": 29965, "total_steps": 38150, "loss": 0.284, "lr": 6.6908270041544815e-06, "epoch": 7.854521625163827, "percentage": 78.55, "elapsed_time": "0:50:26", "remaining_time": "0:13:46", "throughput": 2655.18, "total_tokens": 8035112} {"current_steps": 29970, "total_steps": 38150, "loss": 0.2982, "lr": 6.683041158455472e-06, "epoch": 7.855832241153342, "percentage": 78.56, "elapsed_time": "0:50:26", "remaining_time": "0:13:46", "throughput": 2655.18, "total_tokens": 8036264} {"current_steps": 29975, "total_steps": 38150, "loss": 0.1454, "lr": 6.675259146464291e-06, "epoch": 7.857142857142857, "percentage": 78.57, "elapsed_time": "0:50:27", "remaining_time": "0:13:45", "throughput": 2655.25, "total_tokens": 8037768} {"current_steps": 29980, "total_steps": 38150, "loss": 0.2075, "lr": 6.667480969809714e-06, "epoch": 7.858453473132372, "percentage": 78.58, "elapsed_time": "0:50:27", "remaining_time": "0:13:45", "throughput": 2655.24, "total_tokens": 8038840} {"current_steps": 29985, "total_steps": 38150, "loss": 0.1442, "lr": 6.659706630119697e-06, "epoch": 7.859764089121887, "percentage": 78.6, "elapsed_time": "0:50:28", "remaining_time": "0:13:44", "throughput": 2655.28, "total_tokens": 8040184} {"current_steps": 29990, "total_steps": 38150, "loss": 0.1478, "lr": 6.651936129021391e-06, "epoch": 7.8610747051114025, "percentage": 78.61, "elapsed_time": "0:50:28", "remaining_time": "0:13:44", "throughput": 2655.34, "total_tokens": 8041576} {"current_steps": 29995, "total_steps": 38150, "loss": 0.1476, "lr": 6.644169468141148e-06, "epoch": 7.862385321100917, "percentage": 78.62, "elapsed_time": "0:50:28", "remaining_time": "0:13:43", "throughput": 2655.44, "total_tokens": 8043064} {"current_steps": 30000, "total_steps": 38150, "loss": 0.3813, "lr": 6.636406649104529e-06, "epoch": 7.863695937090433, "percentage": 78.64, "elapsed_time": "0:50:29", "remaining_time": "0:13:42", "throughput": 2655.51, "total_tokens": 8044536} {"current_steps": 30005, "total_steps": 38150, "loss": 0.1835, "lr": 6.628647673536262e-06, "epoch": 7.865006553079947, "percentage": 78.65, "elapsed_time": "0:50:29", "remaining_time": "0:13:42", "throughput": 2655.57, "total_tokens": 8045944} {"current_steps": 30010, "total_steps": 38150, "loss": 0.198, "lr": 6.620892543060292e-06, "epoch": 7.866317169069463, "percentage": 78.66, "elapsed_time": "0:50:30", "remaining_time": "0:13:41", "throughput": 2655.58, "total_tokens": 8047096} {"current_steps": 30015, "total_steps": 38150, "loss": 0.1048, "lr": 6.613141259299754e-06, "epoch": 7.8676277850589775, "percentage": 78.68, "elapsed_time": "0:50:30", "remaining_time": "0:13:41", "throughput": 2655.61, "total_tokens": 8048344} {"current_steps": 30020, "total_steps": 38150, "loss": 0.1607, "lr": 6.6053938238769845e-06, "epoch": 7.868938401048493, "percentage": 78.69, "elapsed_time": "0:50:31", "remaining_time": "0:13:40", "throughput": 2655.56, "total_tokens": 8049320} {"current_steps": 30025, "total_steps": 38150, "loss": 0.191, "lr": 6.5976502384135025e-06, "epoch": 7.870249017038008, "percentage": 78.7, "elapsed_time": "0:50:31", "remaining_time": "0:13:40", "throughput": 2655.54, "total_tokens": 8050392} {"current_steps": 30030, "total_steps": 38150, "loss": 0.2404, "lr": 6.58991050453002e-06, "epoch": 7.871559633027523, "percentage": 78.72, "elapsed_time": "0:50:32", "remaining_time": "0:13:39", "throughput": 2655.76, "total_tokens": 8052744} {"current_steps": 30035, "total_steps": 38150, "loss": 0.1696, "lr": 6.582174623846477e-06, "epoch": 7.872870249017038, "percentage": 78.73, "elapsed_time": "0:50:32", "remaining_time": "0:13:39", "throughput": 2655.79, "total_tokens": 8054056} {"current_steps": 30040, "total_steps": 38150, "loss": 0.1702, "lr": 6.57444259798195e-06, "epoch": 7.8741808650065535, "percentage": 78.74, "elapsed_time": "0:50:33", "remaining_time": "0:13:38", "throughput": 2655.8, "total_tokens": 8055208} {"current_steps": 30045, "total_steps": 38150, "loss": 0.1345, "lr": 6.566714428554752e-06, "epoch": 7.875491480996068, "percentage": 78.75, "elapsed_time": "0:50:33", "remaining_time": "0:13:38", "throughput": 2655.81, "total_tokens": 8056392} {"current_steps": 30050, "total_steps": 38150, "loss": 0.2267, "lr": 6.558990117182376e-06, "epoch": 7.876802096985584, "percentage": 78.77, "elapsed_time": "0:50:33", "remaining_time": "0:13:37", "throughput": 2655.85, "total_tokens": 8057752} {"current_steps": 30055, "total_steps": 38150, "loss": 0.1664, "lr": 6.551269665481502e-06, "epoch": 7.878112712975098, "percentage": 78.78, "elapsed_time": "0:50:34", "remaining_time": "0:13:37", "throughput": 2655.92, "total_tokens": 8059176} {"current_steps": 30060, "total_steps": 38150, "loss": 0.0945, "lr": 6.543553075068012e-06, "epoch": 7.879423328964613, "percentage": 78.79, "elapsed_time": "0:50:34", "remaining_time": "0:13:36", "throughput": 2655.91, "total_tokens": 8060296} {"current_steps": 30065, "total_steps": 38150, "loss": 0.2128, "lr": 6.535840347556971e-06, "epoch": 7.8807339449541285, "percentage": 78.81, "elapsed_time": "0:50:35", "remaining_time": "0:13:36", "throughput": 2655.97, "total_tokens": 8061640} {"current_steps": 30070, "total_steps": 38150, "loss": 0.3545, "lr": 6.528131484562644e-06, "epoch": 7.882044560943643, "percentage": 78.82, "elapsed_time": "0:50:35", "remaining_time": "0:13:35", "throughput": 2656.05, "total_tokens": 8063192} {"current_steps": 30075, "total_steps": 38150, "loss": 0.1619, "lr": 6.520426487698478e-06, "epoch": 7.883355176933159, "percentage": 78.83, "elapsed_time": "0:50:36", "remaining_time": "0:13:35", "throughput": 2656.08, "total_tokens": 8064472} {"current_steps": 30080, "total_steps": 38150, "loss": 0.2712, "lr": 6.512725358577121e-06, "epoch": 7.884665792922673, "percentage": 78.85, "elapsed_time": "0:50:36", "remaining_time": "0:13:34", "throughput": 2656.17, "total_tokens": 8065896} {"current_steps": 30085, "total_steps": 38150, "loss": 0.1848, "lr": 6.505028098810406e-06, "epoch": 7.885976408912189, "percentage": 78.86, "elapsed_time": "0:50:37", "remaining_time": "0:13:34", "throughput": 2656.13, "total_tokens": 8066920} {"current_steps": 30090, "total_steps": 38150, "loss": 0.1512, "lr": 6.497334710009342e-06, "epoch": 7.8872870249017035, "percentage": 78.87, "elapsed_time": "0:50:37", "remaining_time": "0:13:33", "throughput": 2656.19, "total_tokens": 8068248} {"current_steps": 30095, "total_steps": 38150, "loss": 0.3007, "lr": 6.489645193784158e-06, "epoch": 7.888597640891219, "percentage": 78.89, "elapsed_time": "0:50:37", "remaining_time": "0:13:33", "throughput": 2656.18, "total_tokens": 8069352} {"current_steps": 30100, "total_steps": 38150, "loss": 0.3526, "lr": 6.481959551744254e-06, "epoch": 7.889908256880734, "percentage": 78.9, "elapsed_time": "0:50:38", "remaining_time": "0:13:32", "throughput": 2656.24, "total_tokens": 8070696} {"current_steps": 30105, "total_steps": 38150, "loss": 0.1723, "lr": 6.474277785498217e-06, "epoch": 7.891218872870249, "percentage": 78.91, "elapsed_time": "0:50:38", "remaining_time": "0:13:32", "throughput": 2656.26, "total_tokens": 8072024} {"current_steps": 30110, "total_steps": 38150, "loss": 0.2456, "lr": 6.46659989665383e-06, "epoch": 7.892529488859764, "percentage": 78.93, "elapsed_time": "0:50:39", "remaining_time": "0:13:31", "throughput": 2656.31, "total_tokens": 8073384} {"current_steps": 30115, "total_steps": 38150, "loss": 0.3133, "lr": 6.458925886818062e-06, "epoch": 7.8938401048492794, "percentage": 78.94, "elapsed_time": "0:50:39", "remaining_time": "0:13:31", "throughput": 2656.41, "total_tokens": 8074888} {"current_steps": 30120, "total_steps": 38150, "loss": 0.1991, "lr": 6.451255757597078e-06, "epoch": 7.895150720838794, "percentage": 78.95, "elapsed_time": "0:50:40", "remaining_time": "0:13:30", "throughput": 2656.49, "total_tokens": 8076456} {"current_steps": 30125, "total_steps": 38150, "loss": 0.2114, "lr": 6.443589510596204e-06, "epoch": 7.89646133682831, "percentage": 78.96, "elapsed_time": "0:50:40", "remaining_time": "0:13:30", "throughput": 2656.47, "total_tokens": 8077512} {"current_steps": 30130, "total_steps": 38150, "loss": 0.094, "lr": 6.435927147419984e-06, "epoch": 7.897771952817824, "percentage": 78.98, "elapsed_time": "0:50:41", "remaining_time": "0:13:29", "throughput": 2656.4, "total_tokens": 8078392} {"current_steps": 30135, "total_steps": 38150, "loss": 0.2167, "lr": 6.4282686696721356e-06, "epoch": 7.89908256880734, "percentage": 78.99, "elapsed_time": "0:50:41", "remaining_time": "0:13:28", "throughput": 2656.48, "total_tokens": 8080120} {"current_steps": 30140, "total_steps": 38150, "loss": 0.1538, "lr": 6.420614078955564e-06, "epoch": 7.9003931847968545, "percentage": 79.0, "elapsed_time": "0:50:42", "remaining_time": "0:13:28", "throughput": 2656.55, "total_tokens": 8081512} {"current_steps": 30145, "total_steps": 38150, "loss": 0.1741, "lr": 6.412963376872358e-06, "epoch": 7.90170380078637, "percentage": 79.02, "elapsed_time": "0:50:42", "remaining_time": "0:13:27", "throughput": 2656.7, "total_tokens": 8083320} {"current_steps": 30150, "total_steps": 38150, "loss": 0.1796, "lr": 6.405316565023806e-06, "epoch": 7.903014416775885, "percentage": 79.03, "elapsed_time": "0:50:43", "remaining_time": "0:13:27", "throughput": 2656.72, "total_tokens": 8084584} {"current_steps": 30155, "total_steps": 38150, "loss": 0.1127, "lr": 6.397673645010377e-06, "epoch": 7.904325032765399, "percentage": 79.04, "elapsed_time": "0:50:43", "remaining_time": "0:13:26", "throughput": 2656.74, "total_tokens": 8085800} {"current_steps": 30160, "total_steps": 38150, "loss": 0.196, "lr": 6.390034618431704e-06, "epoch": 7.905635648754915, "percentage": 79.06, "elapsed_time": "0:50:43", "remaining_time": "0:13:26", "throughput": 2656.75, "total_tokens": 8086952} {"current_steps": 30165, "total_steps": 38150, "loss": 0.1889, "lr": 6.382399486886631e-06, "epoch": 7.9069462647444295, "percentage": 79.07, "elapsed_time": "0:50:44", "remaining_time": "0:13:25", "throughput": 2656.81, "total_tokens": 8088296} {"current_steps": 30170, "total_steps": 38150, "loss": 0.1001, "lr": 6.374768251973174e-06, "epoch": 7.908256880733945, "percentage": 79.08, "elapsed_time": "0:50:44", "remaining_time": "0:13:25", "throughput": 2656.83, "total_tokens": 8089528} {"current_steps": 30175, "total_steps": 38150, "loss": 0.3033, "lr": 6.367140915288542e-06, "epoch": 7.90956749672346, "percentage": 79.1, "elapsed_time": "0:50:45", "remaining_time": "0:13:24", "throughput": 2656.94, "total_tokens": 8091192} {"current_steps": 30180, "total_steps": 38150, "loss": 0.2737, "lr": 6.3595174784291195e-06, "epoch": 7.910878112712975, "percentage": 79.11, "elapsed_time": "0:50:45", "remaining_time": "0:13:24", "throughput": 2657.09, "total_tokens": 8093176} {"current_steps": 30185, "total_steps": 38150, "loss": 0.2397, "lr": 6.351897942990481e-06, "epoch": 7.91218872870249, "percentage": 79.12, "elapsed_time": "0:50:46", "remaining_time": "0:13:23", "throughput": 2657.11, "total_tokens": 8094408} {"current_steps": 30190, "total_steps": 38150, "loss": 0.2564, "lr": 6.344282310567384e-06, "epoch": 7.913499344692005, "percentage": 79.13, "elapsed_time": "0:50:46", "remaining_time": "0:13:23", "throughput": 2657.24, "total_tokens": 8096088} {"current_steps": 30195, "total_steps": 38150, "loss": 0.2566, "lr": 6.336670582753762e-06, "epoch": 7.91480996068152, "percentage": 79.15, "elapsed_time": "0:50:47", "remaining_time": "0:13:22", "throughput": 2657.23, "total_tokens": 8097224} {"current_steps": 30200, "total_steps": 38150, "loss": 0.1294, "lr": 6.329062761142748e-06, "epoch": 7.916120576671036, "percentage": 79.16, "elapsed_time": "0:50:47", "remaining_time": "0:13:22", "throughput": 2657.2, "total_tokens": 8098216} {"current_steps": 30205, "total_steps": 38150, "loss": 0.1478, "lr": 6.3214588473266225e-06, "epoch": 7.91743119266055, "percentage": 79.17, "elapsed_time": "0:50:48", "remaining_time": "0:13:21", "throughput": 2657.21, "total_tokens": 8099400} {"current_steps": 30210, "total_steps": 38150, "loss": 0.1646, "lr": 6.313858842896895e-06, "epoch": 7.918741808650066, "percentage": 79.19, "elapsed_time": "0:50:48", "remaining_time": "0:13:21", "throughput": 2657.15, "total_tokens": 8100312} {"current_steps": 30215, "total_steps": 38150, "loss": 0.207, "lr": 6.306262749444219e-06, "epoch": 7.9200524246395805, "percentage": 79.2, "elapsed_time": "0:50:48", "remaining_time": "0:13:20", "throughput": 2657.2, "total_tokens": 8101672} {"current_steps": 30220, "total_steps": 38150, "loss": 0.1617, "lr": 6.298670568558454e-06, "epoch": 7.921363040629096, "percentage": 79.21, "elapsed_time": "0:50:49", "remaining_time": "0:13:20", "throughput": 2657.23, "total_tokens": 8103000} {"current_steps": 30225, "total_steps": 38150, "loss": 0.1353, "lr": 6.291082301828624e-06, "epoch": 7.922673656618611, "percentage": 79.23, "elapsed_time": "0:50:49", "remaining_time": "0:13:19", "throughput": 2657.23, "total_tokens": 8104104} {"current_steps": 30230, "total_steps": 38150, "loss": 0.1883, "lr": 6.283497950842942e-06, "epoch": 7.923984272608125, "percentage": 79.24, "elapsed_time": "0:50:50", "remaining_time": "0:13:19", "throughput": 2657.28, "total_tokens": 8105432} {"current_steps": 30235, "total_steps": 38150, "loss": 0.2394, "lr": 6.275917517188809e-06, "epoch": 7.925294888597641, "percentage": 79.25, "elapsed_time": "0:50:50", "remaining_time": "0:13:18", "throughput": 2657.24, "total_tokens": 8106424} {"current_steps": 30240, "total_steps": 38150, "loss": 0.1554, "lr": 6.2683410024527764e-06, "epoch": 7.926605504587156, "percentage": 79.27, "elapsed_time": "0:50:51", "remaining_time": "0:13:18", "throughput": 2657.33, "total_tokens": 8107928} {"current_steps": 30245, "total_steps": 38150, "loss": 0.2353, "lr": 6.260768408220607e-06, "epoch": 7.927916120576671, "percentage": 79.28, "elapsed_time": "0:50:51", "remaining_time": "0:13:17", "throughput": 2657.35, "total_tokens": 8109208} {"current_steps": 30250, "total_steps": 38150, "loss": 0.1276, "lr": 6.253199736077231e-06, "epoch": 7.929226736566186, "percentage": 79.29, "elapsed_time": "0:50:52", "remaining_time": "0:13:17", "throughput": 2657.37, "total_tokens": 8110472} {"current_steps": 30255, "total_steps": 38150, "loss": 0.2494, "lr": 6.24563498760676e-06, "epoch": 7.930537352555701, "percentage": 79.31, "elapsed_time": "0:50:52", "remaining_time": "0:13:16", "throughput": 2657.4, "total_tokens": 8111688} {"current_steps": 30260, "total_steps": 38150, "loss": 0.132, "lr": 6.238074164392471e-06, "epoch": 7.931847968545216, "percentage": 79.32, "elapsed_time": "0:50:52", "remaining_time": "0:13:16", "throughput": 2657.41, "total_tokens": 8112872} {"current_steps": 30265, "total_steps": 38150, "loss": 0.1409, "lr": 6.23051726801685e-06, "epoch": 7.933158584534731, "percentage": 79.33, "elapsed_time": "0:50:53", "remaining_time": "0:13:15", "throughput": 2657.38, "total_tokens": 8113944} {"current_steps": 30270, "total_steps": 38150, "loss": 0.1205, "lr": 6.22296430006154e-06, "epoch": 7.934469200524246, "percentage": 79.34, "elapsed_time": "0:50:53", "remaining_time": "0:13:14", "throughput": 2657.47, "total_tokens": 8115384} {"current_steps": 30275, "total_steps": 38150, "loss": 0.3338, "lr": 6.215415262107352e-06, "epoch": 7.935779816513762, "percentage": 79.36, "elapsed_time": "0:50:54", "remaining_time": "0:13:14", "throughput": 2657.71, "total_tokens": 8118120} {"current_steps": 30280, "total_steps": 38150, "loss": 0.2079, "lr": 6.207870155734291e-06, "epoch": 7.937090432503276, "percentage": 79.37, "elapsed_time": "0:50:54", "remaining_time": "0:13:14", "throughput": 2657.69, "total_tokens": 8119176} {"current_steps": 30285, "total_steps": 38150, "loss": 0.1976, "lr": 6.200328982521536e-06, "epoch": 7.938401048492792, "percentage": 79.38, "elapsed_time": "0:50:55", "remaining_time": "0:13:13", "throughput": 2657.7, "total_tokens": 8120360} {"current_steps": 30290, "total_steps": 38150, "loss": 0.223, "lr": 6.192791744047444e-06, "epoch": 7.9397116644823065, "percentage": 79.4, "elapsed_time": "0:50:55", "remaining_time": "0:13:12", "throughput": 2657.71, "total_tokens": 8121528} {"current_steps": 30295, "total_steps": 38150, "loss": 0.207, "lr": 6.185258441889541e-06, "epoch": 7.941022280471822, "percentage": 79.41, "elapsed_time": "0:50:56", "remaining_time": "0:13:12", "throughput": 2657.77, "total_tokens": 8122856} {"current_steps": 30300, "total_steps": 38150, "loss": 0.3076, "lr": 6.177729077624539e-06, "epoch": 7.942332896461337, "percentage": 79.42, "elapsed_time": "0:50:56", "remaining_time": "0:13:11", "throughput": 2657.79, "total_tokens": 8124072} {"current_steps": 30305, "total_steps": 38150, "loss": 0.2308, "lr": 6.170203652828316e-06, "epoch": 7.943643512450852, "percentage": 79.44, "elapsed_time": "0:50:57", "remaining_time": "0:13:11", "throughput": 2657.91, "total_tokens": 8125752} {"current_steps": 30310, "total_steps": 38150, "loss": 0.2995, "lr": 6.162682169075934e-06, "epoch": 7.944954128440367, "percentage": 79.45, "elapsed_time": "0:50:57", "remaining_time": "0:13:10", "throughput": 2657.92, "total_tokens": 8126904} {"current_steps": 30315, "total_steps": 38150, "loss": 0.224, "lr": 6.155164627941626e-06, "epoch": 7.946264744429882, "percentage": 79.46, "elapsed_time": "0:50:58", "remaining_time": "0:13:10", "throughput": 2657.95, "total_tokens": 8128168} {"current_steps": 30320, "total_steps": 38150, "loss": 0.263, "lr": 6.147651030998799e-06, "epoch": 7.947575360419397, "percentage": 79.48, "elapsed_time": "0:50:58", "remaining_time": "0:13:09", "throughput": 2658.02, "total_tokens": 8129544} {"current_steps": 30325, "total_steps": 38150, "loss": 0.1948, "lr": 6.140141379820038e-06, "epoch": 7.948885976408912, "percentage": 79.49, "elapsed_time": "0:50:58", "remaining_time": "0:13:09", "throughput": 2658.01, "total_tokens": 8130616} {"current_steps": 30330, "total_steps": 38150, "loss": 0.228, "lr": 6.132635675977099e-06, "epoch": 7.950196592398427, "percentage": 79.5, "elapsed_time": "0:50:59", "remaining_time": "0:13:08", "throughput": 2657.92, "total_tokens": 8131432} {"current_steps": 30335, "total_steps": 38150, "loss": 0.0924, "lr": 6.125133921040912e-06, "epoch": 7.951507208387943, "percentage": 79.52, "elapsed_time": "0:50:59", "remaining_time": "0:13:08", "throughput": 2657.91, "total_tokens": 8132520} {"current_steps": 30340, "total_steps": 38150, "loss": 0.1194, "lr": 6.1176361165815845e-06, "epoch": 7.952817824377457, "percentage": 79.53, "elapsed_time": "0:51:00", "remaining_time": "0:13:07", "throughput": 2657.91, "total_tokens": 8133720} {"current_steps": 30345, "total_steps": 38150, "loss": 0.1714, "lr": 6.1101422641683895e-06, "epoch": 7.954128440366972, "percentage": 79.54, "elapsed_time": "0:51:00", "remaining_time": "0:13:07", "throughput": 2658.07, "total_tokens": 8135528} {"current_steps": 30350, "total_steps": 38150, "loss": 0.165, "lr": 6.102652365369779e-06, "epoch": 7.955439056356488, "percentage": 79.55, "elapsed_time": "0:51:01", "remaining_time": "0:13:06", "throughput": 2658.2, "total_tokens": 8137240} {"current_steps": 30355, "total_steps": 38150, "loss": 0.2718, "lr": 6.095166421753385e-06, "epoch": 7.956749672346002, "percentage": 79.57, "elapsed_time": "0:51:01", "remaining_time": "0:13:06", "throughput": 2658.18, "total_tokens": 8138296} {"current_steps": 30360, "total_steps": 38150, "loss": 0.2091, "lr": 6.087684434885985e-06, "epoch": 7.958060288335518, "percentage": 79.58, "elapsed_time": "0:51:02", "remaining_time": "0:13:05", "throughput": 2658.25, "total_tokens": 8139816} {"current_steps": 30365, "total_steps": 38150, "loss": 0.2295, "lr": 6.080206406333555e-06, "epoch": 7.9593709043250325, "percentage": 79.59, "elapsed_time": "0:51:02", "remaining_time": "0:13:05", "throughput": 2658.21, "total_tokens": 8140840} {"current_steps": 30370, "total_steps": 38150, "loss": 0.1421, "lr": 6.072732337661236e-06, "epoch": 7.960681520314548, "percentage": 79.61, "elapsed_time": "0:51:02", "remaining_time": "0:13:04", "throughput": 2658.18, "total_tokens": 8141896} {"current_steps": 30375, "total_steps": 38150, "loss": 0.2207, "lr": 6.065262230433325e-06, "epoch": 7.961992136304063, "percentage": 79.62, "elapsed_time": "0:51:03", "remaining_time": "0:13:04", "throughput": 2658.28, "total_tokens": 8143528} {"current_steps": 30380, "total_steps": 38150, "loss": 0.2765, "lr": 6.057796086213319e-06, "epoch": 7.963302752293578, "percentage": 79.63, "elapsed_time": "0:51:03", "remaining_time": "0:13:03", "throughput": 2658.33, "total_tokens": 8144920} {"current_steps": 30385, "total_steps": 38150, "loss": 0.1783, "lr": 6.050333906563865e-06, "epoch": 7.964613368283093, "percentage": 79.65, "elapsed_time": "0:51:04", "remaining_time": "0:13:03", "throughput": 2658.39, "total_tokens": 8146392} {"current_steps": 30390, "total_steps": 38150, "loss": 0.3089, "lr": 6.0428756930467876e-06, "epoch": 7.965923984272608, "percentage": 79.66, "elapsed_time": "0:51:04", "remaining_time": "0:13:02", "throughput": 2658.44, "total_tokens": 8147768} {"current_steps": 30395, "total_steps": 38150, "loss": 0.2299, "lr": 6.035421447223064e-06, "epoch": 7.967234600262123, "percentage": 79.67, "elapsed_time": "0:51:05", "remaining_time": "0:13:02", "throughput": 2658.43, "total_tokens": 8148840} {"current_steps": 30400, "total_steps": 38150, "loss": 0.1911, "lr": 6.027971170652866e-06, "epoch": 7.968545216251639, "percentage": 79.69, "elapsed_time": "0:51:05", "remaining_time": "0:13:01", "throughput": 2658.53, "total_tokens": 8150408} {"current_steps": 30405, "total_steps": 38150, "loss": 0.2293, "lr": 6.020524864895519e-06, "epoch": 7.969855832241153, "percentage": 79.7, "elapsed_time": "0:51:06", "remaining_time": "0:13:01", "throughput": 2658.51, "total_tokens": 8151448} {"current_steps": 30410, "total_steps": 38150, "loss": 0.2263, "lr": 6.013082531509523e-06, "epoch": 7.971166448230669, "percentage": 79.71, "elapsed_time": "0:51:06", "remaining_time": "0:13:00", "throughput": 2658.59, "total_tokens": 8152936} {"current_steps": 30415, "total_steps": 38150, "loss": 0.1371, "lr": 6.005644172052549e-06, "epoch": 7.972477064220183, "percentage": 79.72, "elapsed_time": "0:51:07", "remaining_time": "0:13:00", "throughput": 2658.53, "total_tokens": 8153864} {"current_steps": 30420, "total_steps": 38150, "loss": 0.2285, "lr": 5.998209788081427e-06, "epoch": 7.973787680209698, "percentage": 79.74, "elapsed_time": "0:51:07", "remaining_time": "0:12:59", "throughput": 2658.58, "total_tokens": 8155192} {"current_steps": 30425, "total_steps": 38150, "loss": 0.2676, "lr": 5.990779381152168e-06, "epoch": 7.975098296199214, "percentage": 79.75, "elapsed_time": "0:51:07", "remaining_time": "0:12:58", "throughput": 2658.56, "total_tokens": 8156264} {"current_steps": 30430, "total_steps": 38150, "loss": 0.2229, "lr": 5.9833529528199344e-06, "epoch": 7.976408912188729, "percentage": 79.76, "elapsed_time": "0:51:08", "remaining_time": "0:12:58", "throughput": 2658.67, "total_tokens": 8158104} {"current_steps": 30435, "total_steps": 38150, "loss": 0.355, "lr": 5.9759305046390715e-06, "epoch": 7.977719528178244, "percentage": 79.78, "elapsed_time": "0:51:08", "remaining_time": "0:12:57", "throughput": 2658.73, "total_tokens": 8159464} {"current_steps": 30440, "total_steps": 38150, "loss": 0.1808, "lr": 5.968512038163085e-06, "epoch": 7.9790301441677585, "percentage": 79.79, "elapsed_time": "0:51:09", "remaining_time": "0:12:57", "throughput": 2658.7, "total_tokens": 8160520} {"current_steps": 30445, "total_steps": 38150, "loss": 0.1014, "lr": 5.9610975549446414e-06, "epoch": 7.980340760157274, "percentage": 79.8, "elapsed_time": "0:51:09", "remaining_time": "0:12:56", "throughput": 2658.7, "total_tokens": 8161640} {"current_steps": 30450, "total_steps": 38150, "loss": 0.1782, "lr": 5.953687056535584e-06, "epoch": 7.981651376146789, "percentage": 79.82, "elapsed_time": "0:51:10", "remaining_time": "0:12:56", "throughput": 2658.76, "total_tokens": 8163064} {"current_steps": 30455, "total_steps": 38150, "loss": 0.1827, "lr": 5.946280544486918e-06, "epoch": 7.982961992136304, "percentage": 79.83, "elapsed_time": "0:51:10", "remaining_time": "0:12:55", "throughput": 2658.84, "total_tokens": 8164568} {"current_steps": 30460, "total_steps": 38150, "loss": 0.2733, "lr": 5.938878020348809e-06, "epoch": 7.984272608125819, "percentage": 79.84, "elapsed_time": "0:51:11", "remaining_time": "0:12:55", "throughput": 2658.87, "total_tokens": 8165896} {"current_steps": 30465, "total_steps": 38150, "loss": 0.2831, "lr": 5.931479485670599e-06, "epoch": 7.985583224115334, "percentage": 79.86, "elapsed_time": "0:51:11", "remaining_time": "0:12:54", "throughput": 2658.9, "total_tokens": 8167128} {"current_steps": 30470, "total_steps": 38150, "loss": 0.1604, "lr": 5.924084942000787e-06, "epoch": 7.986893840104849, "percentage": 79.87, "elapsed_time": "0:51:12", "remaining_time": "0:12:54", "throughput": 2658.98, "total_tokens": 8168696} {"current_steps": 30475, "total_steps": 38150, "loss": 0.2177, "lr": 5.916694390887034e-06, "epoch": 7.988204456094365, "percentage": 79.88, "elapsed_time": "0:51:12", "remaining_time": "0:12:53", "throughput": 2659.03, "total_tokens": 8170024} {"current_steps": 30480, "total_steps": 38150, "loss": 0.1319, "lr": 5.909307833876168e-06, "epoch": 7.989515072083879, "percentage": 79.9, "elapsed_time": "0:51:13", "remaining_time": "0:12:53", "throughput": 2659.12, "total_tokens": 8171496} {"current_steps": 30485, "total_steps": 38150, "loss": 0.2552, "lr": 5.901925272514186e-06, "epoch": 7.990825688073395, "percentage": 79.91, "elapsed_time": "0:51:13", "remaining_time": "0:12:52", "throughput": 2659.18, "total_tokens": 8172824} {"current_steps": 30490, "total_steps": 38150, "loss": 0.3479, "lr": 5.8945467083462405e-06, "epoch": 7.992136304062909, "percentage": 79.92, "elapsed_time": "0:51:13", "remaining_time": "0:12:52", "throughput": 2659.28, "total_tokens": 8174408} {"current_steps": 30495, "total_steps": 38150, "loss": 0.2436, "lr": 5.887172142916663e-06, "epoch": 7.993446920052425, "percentage": 79.93, "elapsed_time": "0:51:14", "remaining_time": "0:12:51", "throughput": 2659.3, "total_tokens": 8175688} {"current_steps": 30500, "total_steps": 38150, "loss": 0.2883, "lr": 5.879801577768934e-06, "epoch": 7.99475753604194, "percentage": 79.95, "elapsed_time": "0:51:15", "remaining_time": "0:12:51", "throughput": 2659.54, "total_tokens": 8178136} {"current_steps": 30505, "total_steps": 38150, "loss": 0.195, "lr": 5.872435014445696e-06, "epoch": 7.996068152031455, "percentage": 79.96, "elapsed_time": "0:51:15", "remaining_time": "0:12:50", "throughput": 2659.65, "total_tokens": 8179800} {"current_steps": 30510, "total_steps": 38150, "loss": 0.7192, "lr": 5.865072454488765e-06, "epoch": 7.99737876802097, "percentage": 79.97, "elapsed_time": "0:51:16", "remaining_time": "0:12:50", "throughput": 2659.76, "total_tokens": 8181512} {"current_steps": 30515, "total_steps": 38150, "loss": 0.142, "lr": 5.857713899439101e-06, "epoch": 7.9986893840104845, "percentage": 79.99, "elapsed_time": "0:51:16", "remaining_time": "0:12:49", "throughput": 2659.71, "total_tokens": 8182424} {"current_steps": 30520, "total_steps": 38150, "loss": 0.2298, "lr": 5.850359350836842e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:51:16", "remaining_time": "0:12:49", "throughput": 2659.62, "total_tokens": 8183584} {"current_steps": 30525, "total_steps": 38150, "loss": 0.3334, "lr": 5.843008810221284e-06, "epoch": 8.001310615989516, "percentage": 80.01, "elapsed_time": "0:51:17", "remaining_time": "0:12:48", "throughput": 2659.54, "total_tokens": 8185008} {"current_steps": 30528, "total_steps": 38150, "eval_loss": 0.7432249784469604, "epoch": 8.002096985583224, "percentage": 80.02, "elapsed_time": "0:51:34", "remaining_time": "0:12:52", "throughput": 2645.04, "total_tokens": 8185712} {"current_steps": 30530, "total_steps": 38150, "loss": 0.3686, "lr": 5.835662279130879e-06, "epoch": 8.00262123197903, "percentage": 80.03, "elapsed_time": "0:51:36", "remaining_time": "0:12:52", "throughput": 2643.79, "total_tokens": 8186432} {"current_steps": 30535, "total_steps": 38150, "loss": 0.1328, "lr": 5.828319759103248e-06, "epoch": 8.003931847968545, "percentage": 80.04, "elapsed_time": "0:51:36", "remaining_time": "0:12:52", "throughput": 2643.88, "total_tokens": 8187968} {"current_steps": 30540, "total_steps": 38150, "loss": 0.1664, "lr": 5.8209812516751646e-06, "epoch": 8.00524246395806, "percentage": 80.05, "elapsed_time": "0:51:37", "remaining_time": "0:12:51", "throughput": 2643.85, "total_tokens": 8189072} {"current_steps": 30545, "total_steps": 38150, "loss": 0.2013, "lr": 5.8136467583825685e-06, "epoch": 8.006553079947576, "percentage": 80.07, "elapsed_time": "0:51:37", "remaining_time": "0:12:51", "throughput": 2643.86, "total_tokens": 8190256} {"current_steps": 30550, "total_steps": 38150, "loss": 0.1147, "lr": 5.806316280760551e-06, "epoch": 8.00786369593709, "percentage": 80.08, "elapsed_time": "0:51:38", "remaining_time": "0:12:50", "throughput": 2643.88, "total_tokens": 8191440} {"current_steps": 30555, "total_steps": 38150, "loss": 0.1697, "lr": 5.7989898203433725e-06, "epoch": 8.009174311926605, "percentage": 80.09, "elapsed_time": "0:51:38", "remaining_time": "0:12:50", "throughput": 2643.97, "total_tokens": 8192976} {"current_steps": 30560, "total_steps": 38150, "loss": 0.1251, "lr": 5.791667378664451e-06, "epoch": 8.01048492791612, "percentage": 80.1, "elapsed_time": "0:51:39", "remaining_time": "0:12:49", "throughput": 2644.05, "total_tokens": 8194544} {"current_steps": 30565, "total_steps": 38150, "loss": 0.1575, "lr": 5.784348957256352e-06, "epoch": 8.011795543905636, "percentage": 80.12, "elapsed_time": "0:51:39", "remaining_time": "0:12:49", "throughput": 2644.06, "total_tokens": 8195728} {"current_steps": 30570, "total_steps": 38150, "loss": 0.1739, "lr": 5.7770345576508176e-06, "epoch": 8.01310615989515, "percentage": 80.13, "elapsed_time": "0:51:40", "remaining_time": "0:12:48", "throughput": 2644.1, "total_tokens": 8196992} {"current_steps": 30575, "total_steps": 38150, "loss": 0.1627, "lr": 5.769724181378736e-06, "epoch": 8.014416775884666, "percentage": 80.14, "elapsed_time": "0:51:40", "remaining_time": "0:12:48", "throughput": 2644.19, "total_tokens": 8198544} {"current_steps": 30580, "total_steps": 38150, "loss": 0.1297, "lr": 5.7624178299701546e-06, "epoch": 8.015727391874181, "percentage": 80.16, "elapsed_time": "0:51:41", "remaining_time": "0:12:47", "throughput": 2644.15, "total_tokens": 8199504} {"current_steps": 30585, "total_steps": 38150, "loss": 0.1884, "lr": 5.755115504954284e-06, "epoch": 8.017038007863697, "percentage": 80.17, "elapsed_time": "0:51:41", "remaining_time": "0:12:47", "throughput": 2644.19, "total_tokens": 8200864} {"current_steps": 30590, "total_steps": 38150, "loss": 0.2877, "lr": 5.747817207859491e-06, "epoch": 8.01834862385321, "percentage": 80.18, "elapsed_time": "0:51:41", "remaining_time": "0:12:46", "throughput": 2644.19, "total_tokens": 8202000} {"current_steps": 30595, "total_steps": 38150, "loss": 0.1547, "lr": 5.740522940213283e-06, "epoch": 8.019659239842726, "percentage": 80.2, "elapsed_time": "0:51:42", "remaining_time": "0:12:46", "throughput": 2644.21, "total_tokens": 8203200} {"current_steps": 30600, "total_steps": 38150, "loss": 0.2441, "lr": 5.733232703542346e-06, "epoch": 8.020969855832242, "percentage": 80.21, "elapsed_time": "0:51:42", "remaining_time": "0:12:45", "throughput": 2644.25, "total_tokens": 8204480} {"current_steps": 30605, "total_steps": 38150, "loss": 0.1449, "lr": 5.725946499372506e-06, "epoch": 8.022280471821757, "percentage": 80.22, "elapsed_time": "0:51:43", "remaining_time": "0:12:45", "throughput": 2644.23, "total_tokens": 8205616} {"current_steps": 30610, "total_steps": 38150, "loss": 0.1883, "lr": 5.7186643292287705e-06, "epoch": 8.02359108781127, "percentage": 80.24, "elapsed_time": "0:51:43", "remaining_time": "0:12:44", "throughput": 2644.43, "total_tokens": 8208176} {"current_steps": 30615, "total_steps": 38150, "loss": 0.1682, "lr": 5.711386194635274e-06, "epoch": 8.024901703800786, "percentage": 80.25, "elapsed_time": "0:51:44", "remaining_time": "0:12:44", "throughput": 2644.39, "total_tokens": 8209168} {"current_steps": 30620, "total_steps": 38150, "loss": 0.2169, "lr": 5.704112097115316e-06, "epoch": 8.026212319790302, "percentage": 80.26, "elapsed_time": "0:51:44", "remaining_time": "0:12:43", "throughput": 2644.44, "total_tokens": 8210464} {"current_steps": 30625, "total_steps": 38150, "loss": 0.1186, "lr": 5.696842038191366e-06, "epoch": 8.027522935779816, "percentage": 80.28, "elapsed_time": "0:51:45", "remaining_time": "0:12:43", "throughput": 2644.44, "total_tokens": 8211616} {"current_steps": 30630, "total_steps": 38150, "loss": 0.1649, "lr": 5.689576019385015e-06, "epoch": 8.028833551769331, "percentage": 80.29, "elapsed_time": "0:51:45", "remaining_time": "0:12:42", "throughput": 2644.46, "total_tokens": 8212832} {"current_steps": 30635, "total_steps": 38150, "loss": 0.2555, "lr": 5.682314042217041e-06, "epoch": 8.030144167758847, "percentage": 80.3, "elapsed_time": "0:51:46", "remaining_time": "0:12:41", "throughput": 2644.48, "total_tokens": 8214048} {"current_steps": 30640, "total_steps": 38150, "loss": 0.1063, "lr": 5.675056108207355e-06, "epoch": 8.031454783748362, "percentage": 80.31, "elapsed_time": "0:51:46", "remaining_time": "0:12:41", "throughput": 2644.53, "total_tokens": 8215328} {"current_steps": 30645, "total_steps": 38150, "loss": 0.2083, "lr": 5.667802218875037e-06, "epoch": 8.032765399737876, "percentage": 80.33, "elapsed_time": "0:51:47", "remaining_time": "0:12:40", "throughput": 2644.58, "total_tokens": 8216720} {"current_steps": 30650, "total_steps": 38150, "loss": 0.2126, "lr": 5.66055237573831e-06, "epoch": 8.034076015727392, "percentage": 80.34, "elapsed_time": "0:51:47", "remaining_time": "0:12:40", "throughput": 2644.64, "total_tokens": 8218112} {"current_steps": 30655, "total_steps": 38150, "loss": 0.102, "lr": 5.6533065803145545e-06, "epoch": 8.035386631716907, "percentage": 80.35, "elapsed_time": "0:51:47", "remaining_time": "0:12:39", "throughput": 2644.7, "total_tokens": 8219552} {"current_steps": 30660, "total_steps": 38150, "loss": 0.1966, "lr": 5.646064834120304e-06, "epoch": 8.036697247706423, "percentage": 80.37, "elapsed_time": "0:51:48", "remaining_time": "0:12:39", "throughput": 2644.81, "total_tokens": 8221136} {"current_steps": 30665, "total_steps": 38150, "loss": 0.213, "lr": 5.638827138671243e-06, "epoch": 8.038007863695936, "percentage": 80.38, "elapsed_time": "0:51:48", "remaining_time": "0:12:38", "throughput": 2644.87, "total_tokens": 8222496} {"current_steps": 30670, "total_steps": 38150, "loss": 0.106, "lr": 5.631593495482209e-06, "epoch": 8.039318479685452, "percentage": 80.39, "elapsed_time": "0:51:49", "remaining_time": "0:12:38", "throughput": 2644.99, "total_tokens": 8224272} {"current_steps": 30675, "total_steps": 38150, "loss": 0.0945, "lr": 5.62436390606719e-06, "epoch": 8.040629095674968, "percentage": 80.41, "elapsed_time": "0:51:49", "remaining_time": "0:12:37", "throughput": 2645.05, "total_tokens": 8225632} {"current_steps": 30680, "total_steps": 38150, "loss": 0.1415, "lr": 5.617138371939326e-06, "epoch": 8.041939711664483, "percentage": 80.42, "elapsed_time": "0:51:50", "remaining_time": "0:12:37", "throughput": 2645.09, "total_tokens": 8226928} {"current_steps": 30685, "total_steps": 38150, "loss": 0.1925, "lr": 5.6099168946109114e-06, "epoch": 8.043250327653997, "percentage": 80.43, "elapsed_time": "0:51:50", "remaining_time": "0:12:36", "throughput": 2645.09, "total_tokens": 8228064} {"current_steps": 30690, "total_steps": 38150, "loss": 0.1315, "lr": 5.602699475593387e-06, "epoch": 8.044560943643512, "percentage": 80.45, "elapsed_time": "0:51:51", "remaining_time": "0:12:36", "throughput": 2645.08, "total_tokens": 8229168} {"current_steps": 30695, "total_steps": 38150, "loss": 0.1353, "lr": 5.595486116397344e-06, "epoch": 8.045871559633028, "percentage": 80.46, "elapsed_time": "0:51:51", "remaining_time": "0:12:35", "throughput": 2645.09, "total_tokens": 8230336} {"current_steps": 30700, "total_steps": 38150, "loss": 0.1671, "lr": 5.588276818532531e-06, "epoch": 8.047182175622543, "percentage": 80.47, "elapsed_time": "0:51:51", "remaining_time": "0:12:35", "throughput": 2645.07, "total_tokens": 8231408} {"current_steps": 30705, "total_steps": 38150, "loss": 0.1225, "lr": 5.5810715835078434e-06, "epoch": 8.048492791612057, "percentage": 80.48, "elapsed_time": "0:51:52", "remaining_time": "0:12:34", "throughput": 2645.14, "total_tokens": 8232784} {"current_steps": 30710, "total_steps": 38150, "loss": 0.1597, "lr": 5.573870412831314e-06, "epoch": 8.049803407601573, "percentage": 80.5, "elapsed_time": "0:51:52", "remaining_time": "0:12:34", "throughput": 2645.23, "total_tokens": 8234336} {"current_steps": 30715, "total_steps": 38150, "loss": 0.1421, "lr": 5.566673308010142e-06, "epoch": 8.051114023591088, "percentage": 80.51, "elapsed_time": "0:51:53", "remaining_time": "0:12:33", "throughput": 2645.22, "total_tokens": 8235392} {"current_steps": 30720, "total_steps": 38150, "loss": 0.1945, "lr": 5.5594802705506626e-06, "epoch": 8.052424639580602, "percentage": 80.52, "elapsed_time": "0:51:53", "remaining_time": "0:12:33", "throughput": 2645.24, "total_tokens": 8236608} {"current_steps": 30725, "total_steps": 38150, "loss": 0.2057, "lr": 5.552291301958379e-06, "epoch": 8.053735255570118, "percentage": 80.54, "elapsed_time": "0:51:54", "remaining_time": "0:12:32", "throughput": 2645.32, "total_tokens": 8238096} {"current_steps": 30730, "total_steps": 38150, "loss": 0.1444, "lr": 5.545106403737921e-06, "epoch": 8.055045871559633, "percentage": 80.55, "elapsed_time": "0:51:54", "remaining_time": "0:12:32", "throughput": 2645.32, "total_tokens": 8239280} {"current_steps": 30735, "total_steps": 38150, "loss": 0.1739, "lr": 5.537925577393077e-06, "epoch": 8.056356487549149, "percentage": 80.56, "elapsed_time": "0:51:55", "remaining_time": "0:12:31", "throughput": 2645.33, "total_tokens": 8240448} {"current_steps": 30740, "total_steps": 38150, "loss": 0.1605, "lr": 5.530748824426782e-06, "epoch": 8.057667103538662, "percentage": 80.58, "elapsed_time": "0:51:55", "remaining_time": "0:12:31", "throughput": 2645.31, "total_tokens": 8241504} {"current_steps": 30745, "total_steps": 38150, "loss": 0.1147, "lr": 5.523576146341128e-06, "epoch": 8.058977719528178, "percentage": 80.59, "elapsed_time": "0:51:55", "remaining_time": "0:12:30", "throughput": 2645.35, "total_tokens": 8242784} {"current_steps": 30750, "total_steps": 38150, "loss": 0.1971, "lr": 5.5164075446373225e-06, "epoch": 8.060288335517694, "percentage": 80.6, "elapsed_time": "0:51:56", "remaining_time": "0:12:29", "throughput": 2645.31, "total_tokens": 8243760} {"current_steps": 30755, "total_steps": 38150, "loss": 0.2547, "lr": 5.509243020815755e-06, "epoch": 8.061598951507209, "percentage": 80.62, "elapsed_time": "0:51:56", "remaining_time": "0:12:29", "throughput": 2645.52, "total_tokens": 8245888} {"current_steps": 30760, "total_steps": 38150, "loss": 0.1598, "lr": 5.502082576375947e-06, "epoch": 8.062909567496723, "percentage": 80.63, "elapsed_time": "0:51:57", "remaining_time": "0:12:28", "throughput": 2645.48, "total_tokens": 8246896} {"current_steps": 30765, "total_steps": 38150, "loss": 0.186, "lr": 5.494926212816562e-06, "epoch": 8.064220183486238, "percentage": 80.64, "elapsed_time": "0:51:57", "remaining_time": "0:12:28", "throughput": 2645.62, "total_tokens": 8248704} {"current_steps": 30770, "total_steps": 38150, "loss": 0.2152, "lr": 5.4877739316354236e-06, "epoch": 8.065530799475754, "percentage": 80.66, "elapsed_time": "0:51:58", "remaining_time": "0:12:27", "throughput": 2645.75, "total_tokens": 8250368} {"current_steps": 30775, "total_steps": 38150, "loss": 0.1572, "lr": 5.4806257343294755e-06, "epoch": 8.06684141546527, "percentage": 80.67, "elapsed_time": "0:51:58", "remaining_time": "0:12:27", "throughput": 2645.85, "total_tokens": 8252000} {"current_steps": 30780, "total_steps": 38150, "loss": 0.1138, "lr": 5.473481622394849e-06, "epoch": 8.068152031454783, "percentage": 80.68, "elapsed_time": "0:51:59", "remaining_time": "0:12:26", "throughput": 2645.86, "total_tokens": 8253248} {"current_steps": 30785, "total_steps": 38150, "loss": 0.1512, "lr": 5.466341597326774e-06, "epoch": 8.069462647444299, "percentage": 80.69, "elapsed_time": "0:51:59", "remaining_time": "0:12:26", "throughput": 2645.87, "total_tokens": 8254400} {"current_steps": 30790, "total_steps": 38150, "loss": 0.209, "lr": 5.459205660619651e-06, "epoch": 8.070773263433814, "percentage": 80.71, "elapsed_time": "0:52:00", "remaining_time": "0:12:25", "throughput": 2645.9, "total_tokens": 8255648} {"current_steps": 30795, "total_steps": 38150, "loss": 0.1918, "lr": 5.452073813767019e-06, "epoch": 8.07208387942333, "percentage": 80.72, "elapsed_time": "0:52:00", "remaining_time": "0:12:25", "throughput": 2645.94, "total_tokens": 8256928} {"current_steps": 30800, "total_steps": 38150, "loss": 0.1662, "lr": 5.444946058261563e-06, "epoch": 8.073394495412844, "percentage": 80.73, "elapsed_time": "0:52:01", "remaining_time": "0:12:24", "throughput": 2645.98, "total_tokens": 8258368} {"current_steps": 30805, "total_steps": 38150, "loss": 0.2392, "lr": 5.4378223955951074e-06, "epoch": 8.07470511140236, "percentage": 80.75, "elapsed_time": "0:52:01", "remaining_time": "0:12:24", "throughput": 2646.23, "total_tokens": 8260864} {"current_steps": 30810, "total_steps": 38150, "loss": 0.1164, "lr": 5.430702827258622e-06, "epoch": 8.076015727391875, "percentage": 80.76, "elapsed_time": "0:52:02", "remaining_time": "0:12:23", "throughput": 2646.23, "total_tokens": 8261984} {"current_steps": 30815, "total_steps": 38150, "loss": 0.1014, "lr": 5.423587354742224e-06, "epoch": 8.077326343381388, "percentage": 80.77, "elapsed_time": "0:52:02", "remaining_time": "0:12:23", "throughput": 2646.3, "total_tokens": 8263424} {"current_steps": 30820, "total_steps": 38150, "loss": 0.0985, "lr": 5.4164759795351655e-06, "epoch": 8.078636959370904, "percentage": 80.79, "elapsed_time": "0:52:03", "remaining_time": "0:12:22", "throughput": 2646.33, "total_tokens": 8264672} {"current_steps": 30825, "total_steps": 38150, "loss": 0.171, "lr": 5.4093687031258554e-06, "epoch": 8.07994757536042, "percentage": 80.8, "elapsed_time": "0:52:03", "remaining_time": "0:12:22", "throughput": 2646.41, "total_tokens": 8266272} {"current_steps": 30830, "total_steps": 38150, "loss": 0.1779, "lr": 5.402265527001818e-06, "epoch": 8.081258191349935, "percentage": 80.81, "elapsed_time": "0:52:04", "remaining_time": "0:12:21", "throughput": 2646.38, "total_tokens": 8267296} {"current_steps": 30835, "total_steps": 38150, "loss": 0.248, "lr": 5.3951664526497356e-06, "epoch": 8.082568807339449, "percentage": 80.83, "elapsed_time": "0:52:04", "remaining_time": "0:12:21", "throughput": 2646.42, "total_tokens": 8268656} {"current_steps": 30840, "total_steps": 38150, "loss": 0.1269, "lr": 5.388071481555448e-06, "epoch": 8.083879423328964, "percentage": 80.84, "elapsed_time": "0:52:04", "remaining_time": "0:12:20", "throughput": 2646.45, "total_tokens": 8269904} {"current_steps": 30845, "total_steps": 38150, "loss": 0.1724, "lr": 5.3809806152039125e-06, "epoch": 8.08519003931848, "percentage": 80.85, "elapsed_time": "0:52:05", "remaining_time": "0:12:20", "throughput": 2646.45, "total_tokens": 8270992} {"current_steps": 30850, "total_steps": 38150, "loss": 0.1834, "lr": 5.373893855079235e-06, "epoch": 8.086500655307995, "percentage": 80.87, "elapsed_time": "0:52:05", "remaining_time": "0:12:19", "throughput": 2646.49, "total_tokens": 8272352} {"current_steps": 30855, "total_steps": 38150, "loss": 0.1692, "lr": 5.366811202664662e-06, "epoch": 8.08781127129751, "percentage": 80.88, "elapsed_time": "0:52:06", "remaining_time": "0:12:19", "throughput": 2646.49, "total_tokens": 8273424} {"current_steps": 30860, "total_steps": 38150, "loss": 0.1678, "lr": 5.35973265944259e-06, "epoch": 8.089121887287025, "percentage": 80.89, "elapsed_time": "0:52:06", "remaining_time": "0:12:18", "throughput": 2646.58, "total_tokens": 8274976} {"current_steps": 30865, "total_steps": 38150, "loss": 0.1897, "lr": 5.352658226894527e-06, "epoch": 8.09043250327654, "percentage": 80.9, "elapsed_time": "0:52:07", "remaining_time": "0:12:18", "throughput": 2646.64, "total_tokens": 8276384} {"current_steps": 30870, "total_steps": 38150, "loss": 0.1283, "lr": 5.345587906501148e-06, "epoch": 8.091743119266056, "percentage": 80.92, "elapsed_time": "0:52:07", "remaining_time": "0:12:17", "throughput": 2646.73, "total_tokens": 8277920} {"current_steps": 30875, "total_steps": 38150, "loss": 0.2138, "lr": 5.338521699742263e-06, "epoch": 8.09305373525557, "percentage": 80.93, "elapsed_time": "0:52:08", "remaining_time": "0:12:17", "throughput": 2646.8, "total_tokens": 8279488} {"current_steps": 30880, "total_steps": 38150, "loss": 0.1986, "lr": 5.331459608096815e-06, "epoch": 8.094364351245085, "percentage": 80.94, "elapsed_time": "0:52:08", "remaining_time": "0:12:16", "throughput": 2646.87, "total_tokens": 8280912} {"current_steps": 30885, "total_steps": 38150, "loss": 0.2187, "lr": 5.324401633042883e-06, "epoch": 8.0956749672346, "percentage": 80.96, "elapsed_time": "0:52:09", "remaining_time": "0:12:16", "throughput": 2646.86, "total_tokens": 8282016} {"current_steps": 30890, "total_steps": 38150, "loss": 0.0858, "lr": 5.317347776057685e-06, "epoch": 8.096985583224116, "percentage": 80.97, "elapsed_time": "0:52:09", "remaining_time": "0:12:15", "throughput": 2646.85, "total_tokens": 8283120} {"current_steps": 30895, "total_steps": 38150, "loss": 0.1091, "lr": 5.310298038617606e-06, "epoch": 8.09829619921363, "percentage": 80.98, "elapsed_time": "0:52:09", "remaining_time": "0:12:14", "throughput": 2646.9, "total_tokens": 8284496} {"current_steps": 30900, "total_steps": 38150, "loss": 0.2102, "lr": 5.303252422198115e-06, "epoch": 8.099606815203146, "percentage": 81.0, "elapsed_time": "0:52:10", "remaining_time": "0:12:14", "throughput": 2646.97, "total_tokens": 8285840} {"current_steps": 30905, "total_steps": 38150, "loss": 0.226, "lr": 5.296210928273862e-06, "epoch": 8.100917431192661, "percentage": 81.01, "elapsed_time": "0:52:10", "remaining_time": "0:12:13", "throughput": 2646.97, "total_tokens": 8287008} {"current_steps": 30910, "total_steps": 38150, "loss": 0.1377, "lr": 5.289173558318617e-06, "epoch": 8.102228047182175, "percentage": 81.02, "elapsed_time": "0:52:11", "remaining_time": "0:12:13", "throughput": 2647.02, "total_tokens": 8288416} {"current_steps": 30915, "total_steps": 38150, "loss": 0.1044, "lr": 5.282140313805284e-06, "epoch": 8.10353866317169, "percentage": 81.04, "elapsed_time": "0:52:11", "remaining_time": "0:12:12", "throughput": 2647.08, "total_tokens": 8289808} {"current_steps": 30920, "total_steps": 38150, "loss": 0.1313, "lr": 5.275111196205917e-06, "epoch": 8.104849279161206, "percentage": 81.05, "elapsed_time": "0:52:12", "remaining_time": "0:12:12", "throughput": 2647.14, "total_tokens": 8291184} {"current_steps": 30925, "total_steps": 38150, "loss": 0.1698, "lr": 5.268086206991693e-06, "epoch": 8.106159895150721, "percentage": 81.06, "elapsed_time": "0:52:12", "remaining_time": "0:12:11", "throughput": 2647.25, "total_tokens": 8292784} {"current_steps": 30930, "total_steps": 38150, "loss": 0.1579, "lr": 5.2610653476329345e-06, "epoch": 8.107470511140235, "percentage": 81.07, "elapsed_time": "0:52:13", "remaining_time": "0:12:11", "throughput": 2647.33, "total_tokens": 8294304} {"current_steps": 30935, "total_steps": 38150, "loss": 0.1331, "lr": 5.254048619599089e-06, "epoch": 8.10878112712975, "percentage": 81.09, "elapsed_time": "0:52:13", "remaining_time": "0:12:10", "throughput": 2647.35, "total_tokens": 8295488} {"current_steps": 30940, "total_steps": 38150, "loss": 0.1401, "lr": 5.247036024358759e-06, "epoch": 8.110091743119266, "percentage": 81.1, "elapsed_time": "0:52:13", "remaining_time": "0:12:10", "throughput": 2647.33, "total_tokens": 8296544} {"current_steps": 30945, "total_steps": 38150, "loss": 0.2244, "lr": 5.240027563379649e-06, "epoch": 8.111402359108782, "percentage": 81.11, "elapsed_time": "0:52:14", "remaining_time": "0:12:09", "throughput": 2647.57, "total_tokens": 8299472} {"current_steps": 30950, "total_steps": 38150, "loss": 0.1349, "lr": 5.233023238128623e-06, "epoch": 8.112712975098296, "percentage": 81.13, "elapsed_time": "0:52:15", "remaining_time": "0:12:09", "throughput": 2647.86, "total_tokens": 8302656} {"current_steps": 30955, "total_steps": 38150, "loss": 0.1464, "lr": 5.226023050071682e-06, "epoch": 8.114023591087811, "percentage": 81.14, "elapsed_time": "0:52:16", "remaining_time": "0:12:08", "throughput": 2647.96, "total_tokens": 8304304} {"current_steps": 30960, "total_steps": 38150, "loss": 0.0919, "lr": 5.219027000673954e-06, "epoch": 8.115334207077327, "percentage": 81.15, "elapsed_time": "0:52:16", "remaining_time": "0:12:08", "throughput": 2647.94, "total_tokens": 8305344} {"current_steps": 30965, "total_steps": 38150, "loss": 0.1472, "lr": 5.212035091399694e-06, "epoch": 8.116644823066842, "percentage": 81.17, "elapsed_time": "0:52:16", "remaining_time": "0:12:07", "throughput": 2647.97, "total_tokens": 8306560} {"current_steps": 30970, "total_steps": 38150, "loss": 0.1379, "lr": 5.205047323712298e-06, "epoch": 8.117955439056356, "percentage": 81.18, "elapsed_time": "0:52:17", "remaining_time": "0:12:07", "throughput": 2648.0, "total_tokens": 8307888} {"current_steps": 30975, "total_steps": 38150, "loss": 0.1268, "lr": 5.198063699074293e-06, "epoch": 8.119266055045872, "percentage": 81.19, "elapsed_time": "0:52:17", "remaining_time": "0:12:06", "throughput": 2648.09, "total_tokens": 8309424} {"current_steps": 30980, "total_steps": 38150, "loss": 0.1211, "lr": 5.191084218947351e-06, "epoch": 8.120576671035387, "percentage": 81.21, "elapsed_time": "0:52:18", "remaining_time": "0:12:06", "throughput": 2648.13, "total_tokens": 8310752} {"current_steps": 30985, "total_steps": 38150, "loss": 0.0832, "lr": 5.184108884792244e-06, "epoch": 8.1218872870249, "percentage": 81.22, "elapsed_time": "0:52:18", "remaining_time": "0:12:05", "throughput": 2648.13, "total_tokens": 8311888} {"current_steps": 30990, "total_steps": 38150, "loss": 0.2004, "lr": 5.177137698068912e-06, "epoch": 8.123197903014416, "percentage": 81.23, "elapsed_time": "0:52:19", "remaining_time": "0:12:05", "throughput": 2648.1, "total_tokens": 8312896} {"current_steps": 30995, "total_steps": 38150, "loss": 0.1941, "lr": 5.170170660236406e-06, "epoch": 8.124508519003932, "percentage": 81.25, "elapsed_time": "0:52:19", "remaining_time": "0:12:04", "throughput": 2648.13, "total_tokens": 8314144} {"current_steps": 31000, "total_steps": 38150, "loss": 0.1099, "lr": 5.163207772752918e-06, "epoch": 8.125819134993447, "percentage": 81.26, "elapsed_time": "0:52:20", "remaining_time": "0:12:04", "throughput": 2648.1, "total_tokens": 8315168} {"current_steps": 31005, "total_steps": 38150, "loss": 0.2252, "lr": 5.156249037075761e-06, "epoch": 8.127129750982961, "percentage": 81.27, "elapsed_time": "0:52:20", "remaining_time": "0:12:03", "throughput": 2648.17, "total_tokens": 8316560} {"current_steps": 31010, "total_steps": 38150, "loss": 0.157, "lr": 5.149294454661399e-06, "epoch": 8.128440366972477, "percentage": 81.28, "elapsed_time": "0:52:20", "remaining_time": "0:12:03", "throughput": 2648.21, "total_tokens": 8317904} {"current_steps": 31015, "total_steps": 38150, "loss": 0.0746, "lr": 5.142344026965418e-06, "epoch": 8.129750982961992, "percentage": 81.3, "elapsed_time": "0:52:21", "remaining_time": "0:12:02", "throughput": 2648.18, "total_tokens": 8318960} {"current_steps": 31020, "total_steps": 38150, "loss": 0.1048, "lr": 5.135397755442512e-06, "epoch": 8.131061598951508, "percentage": 81.31, "elapsed_time": "0:52:21", "remaining_time": "0:12:02", "throughput": 2648.26, "total_tokens": 8320352} {"current_steps": 31025, "total_steps": 38150, "loss": 0.2734, "lr": 5.1284556415465315e-06, "epoch": 8.132372214941022, "percentage": 81.32, "elapsed_time": "0:52:22", "remaining_time": "0:12:01", "throughput": 2648.39, "total_tokens": 8322048} {"current_steps": 31030, "total_steps": 38150, "loss": 0.231, "lr": 5.121517686730451e-06, "epoch": 8.133682830930537, "percentage": 81.34, "elapsed_time": "0:52:22", "remaining_time": "0:12:01", "throughput": 2648.49, "total_tokens": 8323584} {"current_steps": 31035, "total_steps": 38150, "loss": 0.1263, "lr": 5.1145838924463725e-06, "epoch": 8.134993446920053, "percentage": 81.35, "elapsed_time": "0:52:23", "remaining_time": "0:12:00", "throughput": 2648.53, "total_tokens": 8324944} {"current_steps": 31040, "total_steps": 38150, "loss": 0.1487, "lr": 5.107654260145523e-06, "epoch": 8.136304062909568, "percentage": 81.36, "elapsed_time": "0:52:23", "remaining_time": "0:12:00", "throughput": 2648.59, "total_tokens": 8326352} {"current_steps": 31045, "total_steps": 38150, "loss": 0.1545, "lr": 5.100728791278267e-06, "epoch": 8.137614678899082, "percentage": 81.38, "elapsed_time": "0:52:24", "remaining_time": "0:11:59", "throughput": 2648.61, "total_tokens": 8327664} {"current_steps": 31050, "total_steps": 38150, "loss": 0.1261, "lr": 5.0938074872940915e-06, "epoch": 8.138925294888598, "percentage": 81.39, "elapsed_time": "0:52:24", "remaining_time": "0:11:59", "throughput": 2648.61, "total_tokens": 8328848} {"current_steps": 31055, "total_steps": 38150, "loss": 0.1558, "lr": 5.086890349641616e-06, "epoch": 8.140235910878113, "percentage": 81.4, "elapsed_time": "0:52:25", "remaining_time": "0:11:58", "throughput": 2648.61, "total_tokens": 8329984} {"current_steps": 31060, "total_steps": 38150, "loss": 0.1539, "lr": 5.079977379768588e-06, "epoch": 8.141546526867629, "percentage": 81.42, "elapsed_time": "0:52:25", "remaining_time": "0:11:58", "throughput": 2648.62, "total_tokens": 8331168} {"current_steps": 31065, "total_steps": 38150, "loss": 0.1736, "lr": 5.073068579121862e-06, "epoch": 8.142857142857142, "percentage": 81.43, "elapsed_time": "0:52:25", "remaining_time": "0:11:57", "throughput": 2648.68, "total_tokens": 8332496} {"current_steps": 31070, "total_steps": 38150, "loss": 0.239, "lr": 5.066163949147457e-06, "epoch": 8.144167758846658, "percentage": 81.44, "elapsed_time": "0:52:26", "remaining_time": "0:11:56", "throughput": 2648.67, "total_tokens": 8333616} {"current_steps": 31075, "total_steps": 38150, "loss": 0.1425, "lr": 5.059263491290495e-06, "epoch": 8.145478374836173, "percentage": 81.45, "elapsed_time": "0:52:26", "remaining_time": "0:11:56", "throughput": 2648.72, "total_tokens": 8334928} {"current_steps": 31080, "total_steps": 38150, "loss": 0.1617, "lr": 5.052367206995229e-06, "epoch": 8.146788990825687, "percentage": 81.47, "elapsed_time": "0:52:27", "remaining_time": "0:11:55", "throughput": 2648.8, "total_tokens": 8336432} {"current_steps": 31085, "total_steps": 38150, "loss": 0.1162, "lr": 5.0454750977050406e-06, "epoch": 8.148099606815203, "percentage": 81.48, "elapsed_time": "0:52:27", "remaining_time": "0:11:55", "throughput": 2648.85, "total_tokens": 8337776} {"current_steps": 31090, "total_steps": 38150, "loss": 0.1523, "lr": 5.038587164862435e-06, "epoch": 8.149410222804718, "percentage": 81.49, "elapsed_time": "0:52:28", "remaining_time": "0:11:54", "throughput": 2648.95, "total_tokens": 8339264} {"current_steps": 31095, "total_steps": 38150, "loss": 0.07, "lr": 5.031703409909052e-06, "epoch": 8.150720838794234, "percentage": 81.51, "elapsed_time": "0:52:28", "remaining_time": "0:11:54", "throughput": 2648.97, "total_tokens": 8340592} {"current_steps": 31100, "total_steps": 38150, "loss": 0.139, "lr": 5.024823834285636e-06, "epoch": 8.152031454783748, "percentage": 81.52, "elapsed_time": "0:52:29", "remaining_time": "0:11:53", "throughput": 2648.97, "total_tokens": 8341712} {"current_steps": 31105, "total_steps": 38150, "loss": 0.1164, "lr": 5.017948439432077e-06, "epoch": 8.153342070773263, "percentage": 81.53, "elapsed_time": "0:52:29", "remaining_time": "0:11:53", "throughput": 2649.05, "total_tokens": 8343312} {"current_steps": 31110, "total_steps": 38150, "loss": 0.142, "lr": 5.0110772267873836e-06, "epoch": 8.154652686762779, "percentage": 81.55, "elapsed_time": "0:52:29", "remaining_time": "0:11:52", "throughput": 2649.04, "total_tokens": 8344384} {"current_steps": 31115, "total_steps": 38150, "loss": 0.1493, "lr": 5.004210197789688e-06, "epoch": 8.155963302752294, "percentage": 81.56, "elapsed_time": "0:52:30", "remaining_time": "0:11:52", "throughput": 2649.05, "total_tokens": 8345536} {"current_steps": 31120, "total_steps": 38150, "loss": 0.1932, "lr": 4.997347353876242e-06, "epoch": 8.157273918741808, "percentage": 81.57, "elapsed_time": "0:52:30", "remaining_time": "0:11:51", "throughput": 2649.04, "total_tokens": 8346592} {"current_steps": 31125, "total_steps": 38150, "loss": 0.1223, "lr": 4.990488696483439e-06, "epoch": 8.158584534731324, "percentage": 81.59, "elapsed_time": "0:52:31", "remaining_time": "0:11:51", "throughput": 2649.01, "total_tokens": 8347616} {"current_steps": 31130, "total_steps": 38150, "loss": 0.2464, "lr": 4.983634227046785e-06, "epoch": 8.159895150720839, "percentage": 81.6, "elapsed_time": "0:52:31", "remaining_time": "0:11:50", "throughput": 2649.09, "total_tokens": 8349168} {"current_steps": 31135, "total_steps": 38150, "loss": 0.1661, "lr": 4.9767839470008935e-06, "epoch": 8.161205766710355, "percentage": 81.61, "elapsed_time": "0:52:32", "remaining_time": "0:11:50", "throughput": 2649.19, "total_tokens": 8350720} {"current_steps": 31140, "total_steps": 38150, "loss": 0.1688, "lr": 4.969937857779528e-06, "epoch": 8.162516382699868, "percentage": 81.63, "elapsed_time": "0:52:32", "remaining_time": "0:11:49", "throughput": 2649.27, "total_tokens": 8352208} {"current_steps": 31145, "total_steps": 38150, "loss": 0.1579, "lr": 4.963095960815556e-06, "epoch": 8.163826998689384, "percentage": 81.64, "elapsed_time": "0:52:33", "remaining_time": "0:11:49", "throughput": 2649.31, "total_tokens": 8353504} {"current_steps": 31150, "total_steps": 38150, "loss": 0.1863, "lr": 4.95625825754098e-06, "epoch": 8.1651376146789, "percentage": 81.65, "elapsed_time": "0:52:33", "remaining_time": "0:11:48", "throughput": 2649.29, "total_tokens": 8354560} {"current_steps": 31155, "total_steps": 38150, "loss": 0.152, "lr": 4.9494247493869165e-06, "epoch": 8.166448230668415, "percentage": 81.66, "elapsed_time": "0:52:33", "remaining_time": "0:11:48", "throughput": 2649.33, "total_tokens": 8355808} {"current_steps": 31160, "total_steps": 38150, "loss": 0.1935, "lr": 4.942595437783609e-06, "epoch": 8.167758846657929, "percentage": 81.68, "elapsed_time": "0:52:34", "remaining_time": "0:11:47", "throughput": 2649.4, "total_tokens": 8357360} {"current_steps": 31165, "total_steps": 38150, "loss": 0.1439, "lr": 4.9357703241604185e-06, "epoch": 8.169069462647444, "percentage": 81.69, "elapsed_time": "0:52:34", "remaining_time": "0:11:47", "throughput": 2649.49, "total_tokens": 8358880} {"current_steps": 31170, "total_steps": 38150, "loss": 0.1851, "lr": 4.928949409945832e-06, "epoch": 8.17038007863696, "percentage": 81.7, "elapsed_time": "0:52:35", "remaining_time": "0:11:46", "throughput": 2649.56, "total_tokens": 8360496} {"current_steps": 31175, "total_steps": 38150, "loss": 0.2108, "lr": 4.922132696567464e-06, "epoch": 8.171690694626474, "percentage": 81.72, "elapsed_time": "0:52:35", "remaining_time": "0:11:46", "throughput": 2649.58, "total_tokens": 8361776} {"current_steps": 31180, "total_steps": 38150, "loss": 0.1437, "lr": 4.915320185452013e-06, "epoch": 8.17300131061599, "percentage": 81.73, "elapsed_time": "0:52:36", "remaining_time": "0:11:45", "throughput": 2649.59, "total_tokens": 8362928} {"current_steps": 31185, "total_steps": 38150, "loss": 0.1143, "lr": 4.9085118780253515e-06, "epoch": 8.174311926605505, "percentage": 81.74, "elapsed_time": "0:52:36", "remaining_time": "0:11:45", "throughput": 2649.6, "total_tokens": 8364176} {"current_steps": 31190, "total_steps": 38150, "loss": 0.1201, "lr": 4.9017077757124385e-06, "epoch": 8.17562254259502, "percentage": 81.76, "elapsed_time": "0:52:37", "remaining_time": "0:11:44", "throughput": 2649.62, "total_tokens": 8365376} {"current_steps": 31195, "total_steps": 38150, "loss": 0.1594, "lr": 4.89490787993736e-06, "epoch": 8.176933158584534, "percentage": 81.77, "elapsed_time": "0:52:37", "remaining_time": "0:11:43", "throughput": 2649.6, "total_tokens": 8366400} {"current_steps": 31200, "total_steps": 38150, "loss": 0.2943, "lr": 4.888112192123323e-06, "epoch": 8.17824377457405, "percentage": 81.78, "elapsed_time": "0:52:38", "remaining_time": "0:11:43", "throughput": 2649.67, "total_tokens": 8367792} {"current_steps": 31205, "total_steps": 38150, "loss": 0.2473, "lr": 4.8813207136926555e-06, "epoch": 8.179554390563565, "percentage": 81.8, "elapsed_time": "0:52:38", "remaining_time": "0:11:42", "throughput": 2649.75, "total_tokens": 8369232} {"current_steps": 31210, "total_steps": 38150, "loss": 0.1915, "lr": 4.8745334460668005e-06, "epoch": 8.18086500655308, "percentage": 81.81, "elapsed_time": "0:52:38", "remaining_time": "0:11:42", "throughput": 2649.77, "total_tokens": 8370496} {"current_steps": 31215, "total_steps": 38150, "loss": 0.1185, "lr": 4.867750390666326e-06, "epoch": 8.182175622542594, "percentage": 81.82, "elapsed_time": "0:52:39", "remaining_time": "0:11:41", "throughput": 2649.74, "total_tokens": 8371488} {"current_steps": 31220, "total_steps": 38150, "loss": 0.1436, "lr": 4.860971548910903e-06, "epoch": 8.18348623853211, "percentage": 81.83, "elapsed_time": "0:52:39", "remaining_time": "0:11:41", "throughput": 2649.76, "total_tokens": 8372752} {"current_steps": 31225, "total_steps": 38150, "loss": 0.1404, "lr": 4.854196922219337e-06, "epoch": 8.184796854521625, "percentage": 81.85, "elapsed_time": "0:52:40", "remaining_time": "0:11:40", "throughput": 2649.82, "total_tokens": 8374160} {"current_steps": 31230, "total_steps": 38150, "loss": 0.0445, "lr": 4.847426512009545e-06, "epoch": 8.186107470511141, "percentage": 81.86, "elapsed_time": "0:52:40", "remaining_time": "0:11:40", "throughput": 2649.74, "total_tokens": 8375024} {"current_steps": 31235, "total_steps": 38150, "loss": 0.2824, "lr": 4.840660319698559e-06, "epoch": 8.187418086500655, "percentage": 81.87, "elapsed_time": "0:52:41", "remaining_time": "0:11:39", "throughput": 2649.8, "total_tokens": 8376448} {"current_steps": 31240, "total_steps": 38150, "loss": 0.1949, "lr": 4.8338983467025394e-06, "epoch": 8.18872870249017, "percentage": 81.89, "elapsed_time": "0:52:41", "remaining_time": "0:11:39", "throughput": 2649.9, "total_tokens": 8378016} {"current_steps": 31245, "total_steps": 38150, "loss": 0.1277, "lr": 4.827140594436752e-06, "epoch": 8.190039318479686, "percentage": 81.9, "elapsed_time": "0:52:42", "remaining_time": "0:11:38", "throughput": 2649.9, "total_tokens": 8379136} {"current_steps": 31250, "total_steps": 38150, "loss": 0.1841, "lr": 4.82038706431559e-06, "epoch": 8.191349934469201, "percentage": 81.91, "elapsed_time": "0:52:42", "remaining_time": "0:11:38", "throughput": 2650.0, "total_tokens": 8380688} {"current_steps": 31255, "total_steps": 38150, "loss": 0.1002, "lr": 4.81363775775254e-06, "epoch": 8.192660550458715, "percentage": 81.93, "elapsed_time": "0:52:42", "remaining_time": "0:11:37", "throughput": 2650.05, "total_tokens": 8382016} {"current_steps": 31260, "total_steps": 38150, "loss": 0.0979, "lr": 4.80689267616023e-06, "epoch": 8.19397116644823, "percentage": 81.94, "elapsed_time": "0:52:43", "remaining_time": "0:11:37", "throughput": 2650.02, "total_tokens": 8383056} {"current_steps": 31265, "total_steps": 38150, "loss": 0.1975, "lr": 4.800151820950391e-06, "epoch": 8.195281782437746, "percentage": 81.95, "elapsed_time": "0:52:43", "remaining_time": "0:11:36", "throughput": 2650.07, "total_tokens": 8384336} {"current_steps": 31270, "total_steps": 38150, "loss": 0.1506, "lr": 4.7934151935338706e-06, "epoch": 8.19659239842726, "percentage": 81.97, "elapsed_time": "0:52:44", "remaining_time": "0:11:36", "throughput": 2650.21, "total_tokens": 8386160} {"current_steps": 31275, "total_steps": 38150, "loss": 0.163, "lr": 4.786682795320638e-06, "epoch": 8.197903014416775, "percentage": 81.98, "elapsed_time": "0:52:44", "remaining_time": "0:11:35", "throughput": 2650.25, "total_tokens": 8387600} {"current_steps": 31280, "total_steps": 38150, "loss": 0.1773, "lr": 4.779954627719771e-06, "epoch": 8.199213630406291, "percentage": 81.99, "elapsed_time": "0:52:45", "remaining_time": "0:11:35", "throughput": 2650.32, "total_tokens": 8389072} {"current_steps": 31285, "total_steps": 38150, "loss": 0.2063, "lr": 4.773230692139463e-06, "epoch": 8.200524246395807, "percentage": 82.01, "elapsed_time": "0:52:45", "remaining_time": "0:11:34", "throughput": 2650.34, "total_tokens": 8390336} {"current_steps": 31290, "total_steps": 38150, "loss": 0.0852, "lr": 4.766510989987022e-06, "epoch": 8.20183486238532, "percentage": 82.02, "elapsed_time": "0:52:46", "remaining_time": "0:11:34", "throughput": 2650.38, "total_tokens": 8391680} {"current_steps": 31295, "total_steps": 38150, "loss": 0.1937, "lr": 4.7597955226688666e-06, "epoch": 8.203145478374836, "percentage": 82.03, "elapsed_time": "0:52:46", "remaining_time": "0:11:33", "throughput": 2650.37, "total_tokens": 8392784} {"current_steps": 31300, "total_steps": 38150, "loss": 0.18, "lr": 4.75308429159054e-06, "epoch": 8.204456094364351, "percentage": 82.04, "elapsed_time": "0:52:47", "remaining_time": "0:11:33", "throughput": 2650.45, "total_tokens": 8394288} {"current_steps": 31305, "total_steps": 38150, "loss": 0.1039, "lr": 4.746377298156685e-06, "epoch": 8.205766710353867, "percentage": 82.06, "elapsed_time": "0:52:47", "remaining_time": "0:11:32", "throughput": 2650.49, "total_tokens": 8395632} {"current_steps": 31310, "total_steps": 38150, "loss": 0.0788, "lr": 4.739674543771066e-06, "epoch": 8.20707732634338, "percentage": 82.07, "elapsed_time": "0:52:47", "remaining_time": "0:11:32", "throughput": 2650.51, "total_tokens": 8396816} {"current_steps": 31315, "total_steps": 38150, "loss": 0.1882, "lr": 4.732976029836561e-06, "epoch": 8.208387942332896, "percentage": 82.08, "elapsed_time": "0:52:48", "remaining_time": "0:11:31", "throughput": 2650.54, "total_tokens": 8398048} {"current_steps": 31320, "total_steps": 38150, "loss": 0.1798, "lr": 4.726281757755149e-06, "epoch": 8.209698558322412, "percentage": 82.1, "elapsed_time": "0:52:48", "remaining_time": "0:11:31", "throughput": 2650.58, "total_tokens": 8399408} {"current_steps": 31325, "total_steps": 38150, "loss": 0.1739, "lr": 4.719591728927938e-06, "epoch": 8.211009174311927, "percentage": 82.11, "elapsed_time": "0:52:49", "remaining_time": "0:11:30", "throughput": 2650.68, "total_tokens": 8400992} {"current_steps": 31330, "total_steps": 38150, "loss": 0.1964, "lr": 4.712905944755144e-06, "epoch": 8.212319790301441, "percentage": 82.12, "elapsed_time": "0:52:49", "remaining_time": "0:11:30", "throughput": 2650.68, "total_tokens": 8402208} {"current_steps": 31335, "total_steps": 38150, "loss": 0.111, "lr": 4.706224406636072e-06, "epoch": 8.213630406290957, "percentage": 82.14, "elapsed_time": "0:52:50", "remaining_time": "0:11:29", "throughput": 2650.73, "total_tokens": 8403520} {"current_steps": 31340, "total_steps": 38150, "loss": 0.1615, "lr": 4.699547115969172e-06, "epoch": 8.214941022280472, "percentage": 82.15, "elapsed_time": "0:52:50", "remaining_time": "0:11:28", "throughput": 2650.81, "total_tokens": 8405040} {"current_steps": 31345, "total_steps": 38150, "loss": 0.2024, "lr": 4.692874074151979e-06, "epoch": 8.216251638269988, "percentage": 82.16, "elapsed_time": "0:52:51", "remaining_time": "0:11:28", "throughput": 2650.89, "total_tokens": 8406512} {"current_steps": 31350, "total_steps": 38150, "loss": 0.171, "lr": 4.686205282581152e-06, "epoch": 8.217562254259501, "percentage": 82.18, "elapsed_time": "0:52:51", "remaining_time": "0:11:27", "throughput": 2650.87, "total_tokens": 8407584} {"current_steps": 31355, "total_steps": 38150, "loss": 0.1601, "lr": 4.679540742652463e-06, "epoch": 8.218872870249017, "percentage": 82.19, "elapsed_time": "0:52:52", "remaining_time": "0:11:27", "throughput": 2650.86, "total_tokens": 8408672} {"current_steps": 31360, "total_steps": 38150, "loss": 0.0902, "lr": 4.672880455760786e-06, "epoch": 8.220183486238533, "percentage": 82.2, "elapsed_time": "0:52:52", "remaining_time": "0:11:26", "throughput": 2650.84, "total_tokens": 8409712} {"current_steps": 31365, "total_steps": 38150, "loss": 0.2594, "lr": 4.666224423300114e-06, "epoch": 8.221494102228046, "percentage": 82.21, "elapsed_time": "0:52:52", "remaining_time": "0:11:26", "throughput": 2650.88, "total_tokens": 8411040} {"current_steps": 31370, "total_steps": 38150, "loss": 0.0952, "lr": 4.659572646663532e-06, "epoch": 8.222804718217562, "percentage": 82.23, "elapsed_time": "0:52:53", "remaining_time": "0:11:25", "throughput": 2650.94, "total_tokens": 8412448} {"current_steps": 31375, "total_steps": 38150, "loss": 0.156, "lr": 4.652925127243246e-06, "epoch": 8.224115334207077, "percentage": 82.24, "elapsed_time": "0:52:53", "remaining_time": "0:11:25", "throughput": 2650.94, "total_tokens": 8413568} {"current_steps": 31380, "total_steps": 38150, "loss": 0.3244, "lr": 4.646281866430574e-06, "epoch": 8.225425950196593, "percentage": 82.25, "elapsed_time": "0:52:54", "remaining_time": "0:11:24", "throughput": 2650.92, "total_tokens": 8414688} {"current_steps": 31385, "total_steps": 38150, "loss": 0.2225, "lr": 4.6396428656159424e-06, "epoch": 8.226736566186107, "percentage": 82.27, "elapsed_time": "0:52:54", "remaining_time": "0:11:24", "throughput": 2651.01, "total_tokens": 8416160} {"current_steps": 31390, "total_steps": 38150, "loss": 0.1971, "lr": 4.633008126188876e-06, "epoch": 8.228047182175622, "percentage": 82.28, "elapsed_time": "0:52:55", "remaining_time": "0:11:23", "throughput": 2651.01, "total_tokens": 8417344} {"current_steps": 31395, "total_steps": 38150, "loss": 0.1911, "lr": 4.626377649538019e-06, "epoch": 8.229357798165138, "percentage": 82.29, "elapsed_time": "0:52:55", "remaining_time": "0:11:23", "throughput": 2651.03, "total_tokens": 8418528} {"current_steps": 31400, "total_steps": 38150, "loss": 0.1051, "lr": 4.619751437051114e-06, "epoch": 8.230668414154653, "percentage": 82.31, "elapsed_time": "0:52:55", "remaining_time": "0:11:22", "throughput": 2651.0, "total_tokens": 8419536} {"current_steps": 31405, "total_steps": 38150, "loss": 0.1302, "lr": 4.613129490115023e-06, "epoch": 8.231979030144167, "percentage": 82.32, "elapsed_time": "0:52:56", "remaining_time": "0:11:22", "throughput": 2651.04, "total_tokens": 8420800} {"current_steps": 31410, "total_steps": 38150, "loss": 0.1199, "lr": 4.6065118101157014e-06, "epoch": 8.233289646133683, "percentage": 82.33, "elapsed_time": "0:52:56", "remaining_time": "0:11:21", "throughput": 2651.04, "total_tokens": 8422016} {"current_steps": 31415, "total_steps": 38150, "loss": 0.2083, "lr": 4.599898398438221e-06, "epoch": 8.234600262123198, "percentage": 82.35, "elapsed_time": "0:52:57", "remaining_time": "0:11:21", "throughput": 2651.15, "total_tokens": 8423552} {"current_steps": 31420, "total_steps": 38150, "loss": 0.1846, "lr": 4.593289256466757e-06, "epoch": 8.235910878112714, "percentage": 82.36, "elapsed_time": "0:52:57", "remaining_time": "0:11:20", "throughput": 2651.23, "total_tokens": 8425008} {"current_steps": 31425, "total_steps": 38150, "loss": 0.0933, "lr": 4.586684385584592e-06, "epoch": 8.237221494102227, "percentage": 82.37, "elapsed_time": "0:52:58", "remaining_time": "0:11:20", "throughput": 2651.26, "total_tokens": 8426256} {"current_steps": 31430, "total_steps": 38150, "loss": 0.092, "lr": 4.580083787174114e-06, "epoch": 8.238532110091743, "percentage": 82.39, "elapsed_time": "0:52:58", "remaining_time": "0:11:19", "throughput": 2651.37, "total_tokens": 8427952} {"current_steps": 31435, "total_steps": 38150, "loss": 0.1745, "lr": 4.573487462616815e-06, "epoch": 8.239842726081259, "percentage": 82.4, "elapsed_time": "0:52:59", "remaining_time": "0:11:19", "throughput": 2651.38, "total_tokens": 8429120} {"current_steps": 31440, "total_steps": 38150, "loss": 0.0361, "lr": 4.566895413293298e-06, "epoch": 8.241153342070774, "percentage": 82.41, "elapsed_time": "0:52:59", "remaining_time": "0:11:18", "throughput": 2651.31, "total_tokens": 8430032} {"current_steps": 31445, "total_steps": 38150, "loss": 0.1567, "lr": 4.560307640583264e-06, "epoch": 8.242463958060288, "percentage": 82.42, "elapsed_time": "0:52:59", "remaining_time": "0:11:18", "throughput": 2651.27, "total_tokens": 8431024} {"current_steps": 31450, "total_steps": 38150, "loss": 0.1341, "lr": 4.553724145865529e-06, "epoch": 8.243774574049803, "percentage": 82.44, "elapsed_time": "0:53:00", "remaining_time": "0:11:17", "throughput": 2651.28, "total_tokens": 8432160} {"current_steps": 31455, "total_steps": 38150, "loss": 0.123, "lr": 4.547144930517996e-06, "epoch": 8.245085190039319, "percentage": 82.45, "elapsed_time": "0:53:00", "remaining_time": "0:11:17", "throughput": 2651.28, "total_tokens": 8433328} {"current_steps": 31460, "total_steps": 38150, "loss": 0.2065, "lr": 4.54056999591769e-06, "epoch": 8.246395806028833, "percentage": 82.46, "elapsed_time": "0:53:01", "remaining_time": "0:11:16", "throughput": 2651.44, "total_tokens": 8435280} {"current_steps": 31465, "total_steps": 38150, "loss": 0.1545, "lr": 4.533999343440728e-06, "epoch": 8.247706422018348, "percentage": 82.48, "elapsed_time": "0:53:01", "remaining_time": "0:11:16", "throughput": 2651.48, "total_tokens": 8436688} {"current_steps": 31470, "total_steps": 38150, "loss": 0.1007, "lr": 4.527432974462345e-06, "epoch": 8.249017038007864, "percentage": 82.49, "elapsed_time": "0:53:02", "remaining_time": "0:11:15", "throughput": 2651.45, "total_tokens": 8437680} {"current_steps": 31475, "total_steps": 38150, "loss": 0.2178, "lr": 4.520870890356868e-06, "epoch": 8.25032765399738, "percentage": 82.5, "elapsed_time": "0:53:02", "remaining_time": "0:11:14", "throughput": 2651.46, "total_tokens": 8438864} {"current_steps": 31480, "total_steps": 38150, "loss": 0.1929, "lr": 4.5143130924977265e-06, "epoch": 8.251638269986893, "percentage": 82.52, "elapsed_time": "0:53:03", "remaining_time": "0:11:14", "throughput": 2651.52, "total_tokens": 8440272} {"current_steps": 31485, "total_steps": 38150, "loss": 0.1966, "lr": 4.5077595822574645e-06, "epoch": 8.252948885976409, "percentage": 82.53, "elapsed_time": "0:53:03", "remaining_time": "0:11:13", "throughput": 2651.53, "total_tokens": 8441424} {"current_steps": 31490, "total_steps": 38150, "loss": 0.1257, "lr": 4.50121036100771e-06, "epoch": 8.254259501965924, "percentage": 82.54, "elapsed_time": "0:53:04", "remaining_time": "0:11:13", "throughput": 2651.57, "total_tokens": 8442704} {"current_steps": 31495, "total_steps": 38150, "loss": 0.171, "lr": 4.494665430119208e-06, "epoch": 8.25557011795544, "percentage": 82.56, "elapsed_time": "0:53:04", "remaining_time": "0:11:12", "throughput": 2651.55, "total_tokens": 8443744} {"current_steps": 31500, "total_steps": 38150, "loss": 0.2475, "lr": 4.488124790961798e-06, "epoch": 8.256880733944953, "percentage": 82.57, "elapsed_time": "0:53:05", "remaining_time": "0:11:12", "throughput": 2651.67, "total_tokens": 8445648} {"current_steps": 31505, "total_steps": 38150, "loss": 0.0989, "lr": 4.4815884449044275e-06, "epoch": 8.258191349934469, "percentage": 82.58, "elapsed_time": "0:53:05", "remaining_time": "0:11:11", "throughput": 2651.73, "total_tokens": 8447072} {"current_steps": 31510, "total_steps": 38150, "loss": 0.1591, "lr": 4.475056393315144e-06, "epoch": 8.259501965923985, "percentage": 82.6, "elapsed_time": "0:53:05", "remaining_time": "0:11:11", "throughput": 2651.81, "total_tokens": 8448496} {"current_steps": 31515, "total_steps": 38150, "loss": 0.1652, "lr": 4.468528637561095e-06, "epoch": 8.2608125819135, "percentage": 82.61, "elapsed_time": "0:53:06", "remaining_time": "0:11:10", "throughput": 2651.95, "total_tokens": 8450336} {"current_steps": 31520, "total_steps": 38150, "loss": 0.2139, "lr": 4.462005179008525e-06, "epoch": 8.262123197903014, "percentage": 82.62, "elapsed_time": "0:53:07", "remaining_time": "0:11:10", "throughput": 2652.12, "total_tokens": 8452368} {"current_steps": 31525, "total_steps": 38150, "loss": 0.2327, "lr": 4.455486019022781e-06, "epoch": 8.26343381389253, "percentage": 82.63, "elapsed_time": "0:53:07", "remaining_time": "0:11:09", "throughput": 2652.18, "total_tokens": 8453760} {"current_steps": 31530, "total_steps": 38150, "loss": 0.1366, "lr": 4.448971158968318e-06, "epoch": 8.264744429882045, "percentage": 82.65, "elapsed_time": "0:53:07", "remaining_time": "0:11:09", "throughput": 2652.2, "total_tokens": 8455024} {"current_steps": 31535, "total_steps": 38150, "loss": 0.2513, "lr": 4.4424606002086814e-06, "epoch": 8.26605504587156, "percentage": 82.66, "elapsed_time": "0:53:08", "remaining_time": "0:11:08", "throughput": 2652.31, "total_tokens": 8456640} {"current_steps": 31540, "total_steps": 38150, "loss": 0.1906, "lr": 4.435954344106522e-06, "epoch": 8.267365661861074, "percentage": 82.67, "elapsed_time": "0:53:08", "remaining_time": "0:11:08", "throughput": 2652.35, "total_tokens": 8457920} {"current_steps": 31545, "total_steps": 38150, "loss": 0.105, "lr": 4.429452392023584e-06, "epoch": 8.26867627785059, "percentage": 82.69, "elapsed_time": "0:53:09", "remaining_time": "0:11:07", "throughput": 2652.47, "total_tokens": 8459584} {"current_steps": 31550, "total_steps": 38150, "loss": 0.1516, "lr": 4.4229547453207175e-06, "epoch": 8.269986893840105, "percentage": 82.7, "elapsed_time": "0:53:09", "remaining_time": "0:11:07", "throughput": 2652.46, "total_tokens": 8460656} {"current_steps": 31555, "total_steps": 38150, "loss": 0.1897, "lr": 4.416461405357869e-06, "epoch": 8.271297509829619, "percentage": 82.71, "elapsed_time": "0:53:10", "remaining_time": "0:11:06", "throughput": 2652.51, "total_tokens": 8462064} {"current_steps": 31560, "total_steps": 38150, "loss": 0.1938, "lr": 4.409972373494084e-06, "epoch": 8.272608125819135, "percentage": 82.73, "elapsed_time": "0:53:10", "remaining_time": "0:11:06", "throughput": 2652.53, "total_tokens": 8463264} {"current_steps": 31565, "total_steps": 38150, "loss": 0.2561, "lr": 4.403487651087509e-06, "epoch": 8.27391874180865, "percentage": 82.74, "elapsed_time": "0:53:11", "remaining_time": "0:11:05", "throughput": 2652.57, "total_tokens": 8464560} {"current_steps": 31570, "total_steps": 38150, "loss": 0.1316, "lr": 4.397007239495376e-06, "epoch": 8.275229357798166, "percentage": 82.75, "elapsed_time": "0:53:11", "remaining_time": "0:11:05", "throughput": 2652.59, "total_tokens": 8465744} {"current_steps": 31575, "total_steps": 38150, "loss": 0.185, "lr": 4.390531140074028e-06, "epoch": 8.27653997378768, "percentage": 82.77, "elapsed_time": "0:53:11", "remaining_time": "0:11:04", "throughput": 2652.71, "total_tokens": 8467376} {"current_steps": 31580, "total_steps": 38150, "loss": 0.1525, "lr": 4.384059354178893e-06, "epoch": 8.277850589777195, "percentage": 82.78, "elapsed_time": "0:53:12", "remaining_time": "0:11:04", "throughput": 2652.68, "total_tokens": 8468432} {"current_steps": 31585, "total_steps": 38150, "loss": 0.1489, "lr": 4.377591883164522e-06, "epoch": 8.27916120576671, "percentage": 82.79, "elapsed_time": "0:53:12", "remaining_time": "0:11:03", "throughput": 2652.7, "total_tokens": 8469680} {"current_steps": 31590, "total_steps": 38150, "loss": 0.2487, "lr": 4.371128728384538e-06, "epoch": 8.280471821756226, "percentage": 82.8, "elapsed_time": "0:53:13", "remaining_time": "0:11:03", "throughput": 2652.73, "total_tokens": 8471008} {"current_steps": 31595, "total_steps": 38150, "loss": 0.1395, "lr": 4.364669891191667e-06, "epoch": 8.28178243774574, "percentage": 82.82, "elapsed_time": "0:53:13", "remaining_time": "0:11:02", "throughput": 2652.8, "total_tokens": 8472400} {"current_steps": 31600, "total_steps": 38150, "loss": 0.13, "lr": 4.358215372937738e-06, "epoch": 8.283093053735255, "percentage": 82.83, "elapsed_time": "0:53:14", "remaining_time": "0:11:02", "throughput": 2652.96, "total_tokens": 8474368} {"current_steps": 31605, "total_steps": 38150, "loss": 0.1174, "lr": 4.35176517497366e-06, "epoch": 8.284403669724771, "percentage": 82.84, "elapsed_time": "0:53:14", "remaining_time": "0:11:01", "throughput": 2652.94, "total_tokens": 8475424} {"current_steps": 31610, "total_steps": 38150, "loss": 0.265, "lr": 4.34531929864945e-06, "epoch": 8.285714285714286, "percentage": 82.86, "elapsed_time": "0:53:15", "remaining_time": "0:11:01", "throughput": 2653.07, "total_tokens": 8477120} {"current_steps": 31615, "total_steps": 38150, "loss": 0.2145, "lr": 4.3388777453142265e-06, "epoch": 8.2870249017038, "percentage": 82.87, "elapsed_time": "0:53:15", "remaining_time": "0:11:00", "throughput": 2653.12, "total_tokens": 8478528} {"current_steps": 31620, "total_steps": 38150, "loss": 0.1358, "lr": 4.332440516316188e-06, "epoch": 8.288335517693316, "percentage": 82.88, "elapsed_time": "0:53:16", "remaining_time": "0:11:00", "throughput": 2653.18, "total_tokens": 8480032} {"current_steps": 31625, "total_steps": 38150, "loss": 0.163, "lr": 4.326007613002642e-06, "epoch": 8.289646133682831, "percentage": 82.9, "elapsed_time": "0:53:16", "remaining_time": "0:10:59", "throughput": 2653.21, "total_tokens": 8481280} {"current_steps": 31630, "total_steps": 38150, "loss": 0.1989, "lr": 4.319579036719979e-06, "epoch": 8.290956749672347, "percentage": 82.91, "elapsed_time": "0:53:17", "remaining_time": "0:10:59", "throughput": 2653.34, "total_tokens": 8483040} {"current_steps": 31635, "total_steps": 38150, "loss": 0.1678, "lr": 4.313154788813684e-06, "epoch": 8.29226736566186, "percentage": 82.92, "elapsed_time": "0:53:17", "remaining_time": "0:10:58", "throughput": 2653.3, "total_tokens": 8484016} {"current_steps": 31640, "total_steps": 38150, "loss": 0.1998, "lr": 4.30673487062836e-06, "epoch": 8.293577981651376, "percentage": 82.94, "elapsed_time": "0:53:17", "remaining_time": "0:10:57", "throughput": 2653.25, "total_tokens": 8484960} {"current_steps": 31645, "total_steps": 38150, "loss": 0.1946, "lr": 4.300319283507667e-06, "epoch": 8.294888597640892, "percentage": 82.95, "elapsed_time": "0:53:18", "remaining_time": "0:10:57", "throughput": 2653.26, "total_tokens": 8486112} {"current_steps": 31650, "total_steps": 38150, "loss": 0.1518, "lr": 4.29390802879438e-06, "epoch": 8.296199213630405, "percentage": 82.96, "elapsed_time": "0:53:18", "remaining_time": "0:10:56", "throughput": 2653.21, "total_tokens": 8487072} {"current_steps": 31655, "total_steps": 38150, "loss": 0.2451, "lr": 4.287501107830366e-06, "epoch": 8.297509829619921, "percentage": 82.98, "elapsed_time": "0:53:19", "remaining_time": "0:10:56", "throughput": 2653.29, "total_tokens": 8488592} {"current_steps": 31660, "total_steps": 38150, "loss": 0.1921, "lr": 4.2810985219565835e-06, "epoch": 8.298820445609437, "percentage": 82.99, "elapsed_time": "0:53:19", "remaining_time": "0:10:55", "throughput": 2653.37, "total_tokens": 8490064} {"current_steps": 31665, "total_steps": 38150, "loss": 0.114, "lr": 4.27470027251308e-06, "epoch": 8.300131061598952, "percentage": 83.0, "elapsed_time": "0:53:20", "remaining_time": "0:10:55", "throughput": 2653.46, "total_tokens": 8491648} {"current_steps": 31670, "total_steps": 38150, "loss": 0.191, "lr": 4.268306360838998e-06, "epoch": 8.301441677588466, "percentage": 83.01, "elapsed_time": "0:53:20", "remaining_time": "0:10:54", "throughput": 2653.43, "total_tokens": 8492672} {"current_steps": 31675, "total_steps": 38150, "loss": 0.3168, "lr": 4.261916788272571e-06, "epoch": 8.302752293577981, "percentage": 83.03, "elapsed_time": "0:53:21", "remaining_time": "0:10:54", "throughput": 2653.47, "total_tokens": 8494080} {"current_steps": 31680, "total_steps": 38150, "loss": 0.2365, "lr": 4.2555315561511326e-06, "epoch": 8.304062909567497, "percentage": 83.04, "elapsed_time": "0:53:21", "remaining_time": "0:10:53", "throughput": 2653.54, "total_tokens": 8495568} {"current_steps": 31685, "total_steps": 38150, "loss": 0.1154, "lr": 4.249150665811097e-06, "epoch": 8.305373525557012, "percentage": 83.05, "elapsed_time": "0:53:22", "remaining_time": "0:10:53", "throughput": 2653.56, "total_tokens": 8496768} {"current_steps": 31690, "total_steps": 38150, "loss": 0.1315, "lr": 4.242774118587969e-06, "epoch": 8.306684141546526, "percentage": 83.07, "elapsed_time": "0:53:22", "remaining_time": "0:10:52", "throughput": 2653.65, "total_tokens": 8498384} {"current_steps": 31695, "total_steps": 38150, "loss": 0.2773, "lr": 4.236401915816346e-06, "epoch": 8.307994757536042, "percentage": 83.08, "elapsed_time": "0:53:23", "remaining_time": "0:10:52", "throughput": 2653.71, "total_tokens": 8499872} {"current_steps": 31700, "total_steps": 38150, "loss": 0.0728, "lr": 4.230034058829932e-06, "epoch": 8.309305373525557, "percentage": 83.09, "elapsed_time": "0:53:23", "remaining_time": "0:10:51", "throughput": 2653.69, "total_tokens": 8500944} {"current_steps": 31705, "total_steps": 38150, "loss": 0.1276, "lr": 4.2236705489615e-06, "epoch": 8.310615989515073, "percentage": 83.11, "elapsed_time": "0:53:23", "remaining_time": "0:10:51", "throughput": 2653.71, "total_tokens": 8502224} {"current_steps": 31710, "total_steps": 38150, "loss": 0.1074, "lr": 4.2173113875429246e-06, "epoch": 8.311926605504587, "percentage": 83.12, "elapsed_time": "0:53:24", "remaining_time": "0:10:50", "throughput": 2653.7, "total_tokens": 8503312} {"current_steps": 31715, "total_steps": 38150, "loss": 0.1632, "lr": 4.2109565759051645e-06, "epoch": 8.313237221494102, "percentage": 83.13, "elapsed_time": "0:53:24", "remaining_time": "0:10:50", "throughput": 2653.76, "total_tokens": 8504752} {"current_steps": 31720, "total_steps": 38150, "loss": 0.1303, "lr": 4.204606115378282e-06, "epoch": 8.314547837483618, "percentage": 83.15, "elapsed_time": "0:53:25", "remaining_time": "0:10:49", "throughput": 2653.82, "total_tokens": 8506160} {"current_steps": 31725, "total_steps": 38150, "loss": 0.3745, "lr": 4.198260007291399e-06, "epoch": 8.315858453473133, "percentage": 83.16, "elapsed_time": "0:53:25", "remaining_time": "0:10:49", "throughput": 2653.9, "total_tokens": 8507616} {"current_steps": 31730, "total_steps": 38150, "loss": 0.1114, "lr": 4.191918252972754e-06, "epoch": 8.317169069462647, "percentage": 83.17, "elapsed_time": "0:53:26", "remaining_time": "0:10:48", "throughput": 2653.91, "total_tokens": 8508784} {"current_steps": 31735, "total_steps": 38150, "loss": 0.1978, "lr": 4.185580853749666e-06, "epoch": 8.318479685452163, "percentage": 83.18, "elapsed_time": "0:53:26", "remaining_time": "0:10:48", "throughput": 2653.97, "total_tokens": 8510080} {"current_steps": 31740, "total_steps": 38150, "loss": 0.1466, "lr": 4.179247810948539e-06, "epoch": 8.319790301441678, "percentage": 83.2, "elapsed_time": "0:53:26", "remaining_time": "0:10:47", "throughput": 2654.03, "total_tokens": 8511488} {"current_steps": 31745, "total_steps": 38150, "loss": 0.2534, "lr": 4.172919125894869e-06, "epoch": 8.321100917431192, "percentage": 83.21, "elapsed_time": "0:53:27", "remaining_time": "0:10:47", "throughput": 2654.1, "total_tokens": 8512944} {"current_steps": 31750, "total_steps": 38150, "loss": 0.1292, "lr": 4.166594799913237e-06, "epoch": 8.322411533420707, "percentage": 83.22, "elapsed_time": "0:53:27", "remaining_time": "0:10:46", "throughput": 2654.12, "total_tokens": 8514128} {"current_steps": 31755, "total_steps": 38150, "loss": 0.1211, "lr": 4.160274834327327e-06, "epoch": 8.323722149410223, "percentage": 83.24, "elapsed_time": "0:53:28", "remaining_time": "0:10:46", "throughput": 2654.21, "total_tokens": 8515760} {"current_steps": 31760, "total_steps": 38150, "loss": 0.2287, "lr": 4.153959230459878e-06, "epoch": 8.325032765399738, "percentage": 83.25, "elapsed_time": "0:53:28", "remaining_time": "0:10:45", "throughput": 2654.27, "total_tokens": 8517104} {"current_steps": 31765, "total_steps": 38150, "loss": 0.2092, "lr": 4.147647989632744e-06, "epoch": 8.326343381389252, "percentage": 83.26, "elapsed_time": "0:53:29", "remaining_time": "0:10:45", "throughput": 2654.28, "total_tokens": 8518256} {"current_steps": 31770, "total_steps": 38150, "loss": 0.275, "lr": 4.141341113166855e-06, "epoch": 8.327653997378768, "percentage": 83.28, "elapsed_time": "0:53:29", "remaining_time": "0:10:44", "throughput": 2654.32, "total_tokens": 8519600} {"current_steps": 31775, "total_steps": 38150, "loss": 0.1493, "lr": 4.135038602382232e-06, "epoch": 8.328964613368283, "percentage": 83.29, "elapsed_time": "0:53:30", "remaining_time": "0:10:44", "throughput": 2654.35, "total_tokens": 8520944} {"current_steps": 31780, "total_steps": 38150, "loss": 0.1155, "lr": 4.1287404585979764e-06, "epoch": 8.330275229357799, "percentage": 83.3, "elapsed_time": "0:53:30", "remaining_time": "0:10:43", "throughput": 2654.37, "total_tokens": 8522160} {"current_steps": 31785, "total_steps": 38150, "loss": 0.1982, "lr": 4.122446683132281e-06, "epoch": 8.331585845347313, "percentage": 83.32, "elapsed_time": "0:53:31", "remaining_time": "0:10:43", "throughput": 2654.46, "total_tokens": 8523808} {"current_steps": 31790, "total_steps": 38150, "loss": 0.4635, "lr": 4.116157277302418e-06, "epoch": 8.332896461336828, "percentage": 83.33, "elapsed_time": "0:53:31", "remaining_time": "0:10:42", "throughput": 2654.6, "total_tokens": 8525616} {"current_steps": 31795, "total_steps": 38150, "loss": 0.1912, "lr": 4.109872242424756e-06, "epoch": 8.334207077326344, "percentage": 83.34, "elapsed_time": "0:53:32", "remaining_time": "0:10:42", "throughput": 2654.7, "total_tokens": 8527200} {"current_steps": 31800, "total_steps": 38150, "loss": 0.2076, "lr": 4.1035915798147415e-06, "epoch": 8.33551769331586, "percentage": 83.36, "elapsed_time": "0:53:32", "remaining_time": "0:10:41", "throughput": 2654.76, "total_tokens": 8528720} {"current_steps": 31805, "total_steps": 38150, "loss": 0.1456, "lr": 4.097315290786899e-06, "epoch": 8.336828309305373, "percentage": 83.37, "elapsed_time": "0:53:33", "remaining_time": "0:10:40", "throughput": 2654.78, "total_tokens": 8529888} {"current_steps": 31810, "total_steps": 38150, "loss": 0.1191, "lr": 4.091043376654843e-06, "epoch": 8.338138925294889, "percentage": 83.38, "elapsed_time": "0:53:33", "remaining_time": "0:10:40", "throughput": 2654.85, "total_tokens": 8531360} {"current_steps": 31815, "total_steps": 38150, "loss": 0.0847, "lr": 4.084775838731286e-06, "epoch": 8.339449541284404, "percentage": 83.39, "elapsed_time": "0:53:33", "remaining_time": "0:10:39", "throughput": 2654.88, "total_tokens": 8532656} {"current_steps": 31820, "total_steps": 38150, "loss": 0.1356, "lr": 4.078512678328009e-06, "epoch": 8.34076015727392, "percentage": 83.41, "elapsed_time": "0:53:34", "remaining_time": "0:10:39", "throughput": 2654.86, "total_tokens": 8533712} {"current_steps": 31825, "total_steps": 38150, "loss": 0.114, "lr": 4.072253896755876e-06, "epoch": 8.342070773263433, "percentage": 83.42, "elapsed_time": "0:53:34", "remaining_time": "0:10:38", "throughput": 2654.91, "total_tokens": 8535008} {"current_steps": 31830, "total_steps": 38150, "loss": 0.249, "lr": 4.065999495324843e-06, "epoch": 8.343381389252949, "percentage": 83.43, "elapsed_time": "0:53:35", "remaining_time": "0:10:38", "throughput": 2654.94, "total_tokens": 8536256} {"current_steps": 31835, "total_steps": 38150, "loss": 0.135, "lr": 4.059749475343949e-06, "epoch": 8.344692005242464, "percentage": 83.45, "elapsed_time": "0:53:35", "remaining_time": "0:10:37", "throughput": 2655.0, "total_tokens": 8537680} {"current_steps": 31840, "total_steps": 38150, "loss": 0.1309, "lr": 4.053503838121306e-06, "epoch": 8.346002621231978, "percentage": 83.46, "elapsed_time": "0:53:36", "remaining_time": "0:10:37", "throughput": 2655.05, "total_tokens": 8539072} {"current_steps": 31845, "total_steps": 38150, "loss": 0.2115, "lr": 4.047262584964112e-06, "epoch": 8.347313237221494, "percentage": 83.47, "elapsed_time": "0:53:36", "remaining_time": "0:10:36", "throughput": 2655.14, "total_tokens": 8540576} {"current_steps": 31850, "total_steps": 38150, "loss": 0.2374, "lr": 4.0410257171786595e-06, "epoch": 8.34862385321101, "percentage": 83.49, "elapsed_time": "0:53:37", "remaining_time": "0:10:36", "throughput": 2655.24, "total_tokens": 8542176} {"current_steps": 31855, "total_steps": 38150, "loss": 0.2409, "lr": 4.034793236070308e-06, "epoch": 8.349934469200525, "percentage": 83.5, "elapsed_time": "0:53:37", "remaining_time": "0:10:35", "throughput": 2655.32, "total_tokens": 8543600} {"current_steps": 31860, "total_steps": 38150, "loss": 0.1613, "lr": 4.028565142943508e-06, "epoch": 8.351245085190039, "percentage": 83.51, "elapsed_time": "0:53:38", "remaining_time": "0:10:35", "throughput": 2655.39, "total_tokens": 8545072} {"current_steps": 31865, "total_steps": 38150, "loss": 0.1056, "lr": 4.022341439101782e-06, "epoch": 8.352555701179554, "percentage": 83.53, "elapsed_time": "0:53:38", "remaining_time": "0:10:34", "throughput": 2655.32, "total_tokens": 8545952} {"current_steps": 31870, "total_steps": 38150, "loss": 0.1513, "lr": 4.016122125847751e-06, "epoch": 8.35386631716907, "percentage": 83.54, "elapsed_time": "0:53:38", "remaining_time": "0:10:34", "throughput": 2655.35, "total_tokens": 8547168} {"current_steps": 31875, "total_steps": 38150, "loss": 0.1344, "lr": 4.009907204483107e-06, "epoch": 8.355176933158585, "percentage": 83.55, "elapsed_time": "0:53:39", "remaining_time": "0:10:33", "throughput": 2655.39, "total_tokens": 8548480} {"current_steps": 31880, "total_steps": 38150, "loss": 0.1594, "lr": 4.003696676308613e-06, "epoch": 8.356487549148099, "percentage": 83.56, "elapsed_time": "0:53:39", "remaining_time": "0:10:33", "throughput": 2655.47, "total_tokens": 8549904} {"current_steps": 31885, "total_steps": 38150, "loss": 0.1011, "lr": 3.997490542624124e-06, "epoch": 8.357798165137615, "percentage": 83.58, "elapsed_time": "0:53:40", "remaining_time": "0:10:32", "throughput": 2655.43, "total_tokens": 8550896} {"current_steps": 31890, "total_steps": 38150, "loss": 0.1617, "lr": 3.991288804728577e-06, "epoch": 8.35910878112713, "percentage": 83.59, "elapsed_time": "0:53:40", "remaining_time": "0:10:32", "throughput": 2655.44, "total_tokens": 8552096} {"current_steps": 31895, "total_steps": 38150, "loss": 0.2105, "lr": 3.985091463919982e-06, "epoch": 8.360419397116646, "percentage": 83.6, "elapsed_time": "0:53:41", "remaining_time": "0:10:31", "throughput": 2655.54, "total_tokens": 8553680} {"current_steps": 31900, "total_steps": 38150, "loss": 0.2486, "lr": 3.978898521495433e-06, "epoch": 8.36173001310616, "percentage": 83.62, "elapsed_time": "0:53:41", "remaining_time": "0:10:31", "throughput": 2655.79, "total_tokens": 8556080} {"current_steps": 31905, "total_steps": 38150, "loss": 0.1603, "lr": 3.972709978751099e-06, "epoch": 8.363040629095675, "percentage": 83.63, "elapsed_time": "0:53:42", "remaining_time": "0:10:30", "throughput": 2655.82, "total_tokens": 8557280} {"current_steps": 31910, "total_steps": 38150, "loss": 0.1953, "lr": 3.966525836982237e-06, "epoch": 8.36435124508519, "percentage": 83.64, "elapsed_time": "0:53:42", "remaining_time": "0:10:30", "throughput": 2655.84, "total_tokens": 8558496} {"current_steps": 31915, "total_steps": 38150, "loss": 0.1636, "lr": 3.960346097483175e-06, "epoch": 8.365661861074706, "percentage": 83.66, "elapsed_time": "0:53:42", "remaining_time": "0:10:29", "throughput": 2655.92, "total_tokens": 8560000} {"current_steps": 31920, "total_steps": 38150, "loss": 0.0994, "lr": 3.954170761547324e-06, "epoch": 8.36697247706422, "percentage": 83.67, "elapsed_time": "0:53:43", "remaining_time": "0:10:29", "throughput": 2655.92, "total_tokens": 8561120} {"current_steps": 31925, "total_steps": 38150, "loss": 0.1398, "lr": 3.947999830467159e-06, "epoch": 8.368283093053735, "percentage": 83.68, "elapsed_time": "0:53:43", "remaining_time": "0:10:28", "throughput": 2655.86, "total_tokens": 8562048} {"current_steps": 31930, "total_steps": 38150, "loss": 0.0873, "lr": 3.941833305534259e-06, "epoch": 8.36959370904325, "percentage": 83.7, "elapsed_time": "0:53:44", "remaining_time": "0:10:28", "throughput": 2655.82, "total_tokens": 8562992} {"current_steps": 31935, "total_steps": 38150, "loss": 0.1774, "lr": 3.935671188039264e-06, "epoch": 8.370904325032765, "percentage": 83.71, "elapsed_time": "0:53:44", "remaining_time": "0:10:27", "throughput": 2655.98, "total_tokens": 8564816} {"current_steps": 31940, "total_steps": 38150, "loss": 0.2096, "lr": 3.9295134792718905e-06, "epoch": 8.37221494102228, "percentage": 83.72, "elapsed_time": "0:53:45", "remaining_time": "0:10:27", "throughput": 2656.1, "total_tokens": 8566464} {"current_steps": 31945, "total_steps": 38150, "loss": 0.1592, "lr": 3.923360180520941e-06, "epoch": 8.373525557011796, "percentage": 83.74, "elapsed_time": "0:53:45", "remaining_time": "0:10:26", "throughput": 2656.12, "total_tokens": 8567744} {"current_steps": 31950, "total_steps": 38150, "loss": 0.3251, "lr": 3.917211293074285e-06, "epoch": 8.374836173001311, "percentage": 83.75, "elapsed_time": "0:53:46", "remaining_time": "0:10:26", "throughput": 2656.2, "total_tokens": 8569280} {"current_steps": 31955, "total_steps": 38150, "loss": 0.2381, "lr": 3.911066818218886e-06, "epoch": 8.376146788990825, "percentage": 83.76, "elapsed_time": "0:53:46", "remaining_time": "0:10:25", "throughput": 2656.16, "total_tokens": 8570256} {"current_steps": 31960, "total_steps": 38150, "loss": 0.2107, "lr": 3.9049267572407565e-06, "epoch": 8.37745740498034, "percentage": 83.77, "elapsed_time": "0:53:47", "remaining_time": "0:10:25", "throughput": 2656.38, "total_tokens": 8572704} {"current_steps": 31965, "total_steps": 38150, "loss": 0.1676, "lr": 3.898791111425007e-06, "epoch": 8.378768020969856, "percentage": 83.79, "elapsed_time": "0:53:47", "remaining_time": "0:10:24", "throughput": 2656.43, "total_tokens": 8574016} {"current_steps": 31970, "total_steps": 38150, "loss": 0.227, "lr": 3.892659882055819e-06, "epoch": 8.380078636959372, "percentage": 83.8, "elapsed_time": "0:53:48", "remaining_time": "0:10:24", "throughput": 2656.54, "total_tokens": 8575696} {"current_steps": 31975, "total_steps": 38150, "loss": 0.2054, "lr": 3.886533070416445e-06, "epoch": 8.381389252948885, "percentage": 83.81, "elapsed_time": "0:53:48", "remaining_time": "0:10:23", "throughput": 2656.63, "total_tokens": 8577248} {"current_steps": 31980, "total_steps": 38150, "loss": 0.1642, "lr": 3.880410677789214e-06, "epoch": 8.382699868938401, "percentage": 83.83, "elapsed_time": "0:53:49", "remaining_time": "0:10:22", "throughput": 2656.58, "total_tokens": 8578192} {"current_steps": 31985, "total_steps": 38150, "loss": 0.0693, "lr": 3.87429270545554e-06, "epoch": 8.384010484927916, "percentage": 83.84, "elapsed_time": "0:53:49", "remaining_time": "0:10:22", "throughput": 2656.6, "total_tokens": 8579488} {"current_steps": 31990, "total_steps": 38150, "loss": 0.1037, "lr": 3.868179154695909e-06, "epoch": 8.385321100917432, "percentage": 83.85, "elapsed_time": "0:53:49", "remaining_time": "0:10:21", "throughput": 2656.55, "total_tokens": 8580432} {"current_steps": 31995, "total_steps": 38150, "loss": 0.3002, "lr": 3.86207002678986e-06, "epoch": 8.386631716906946, "percentage": 83.87, "elapsed_time": "0:53:50", "remaining_time": "0:10:21", "throughput": 2656.65, "total_tokens": 8582064} {"current_steps": 32000, "total_steps": 38150, "loss": 0.2223, "lr": 3.855965323016031e-06, "epoch": 8.387942332896461, "percentage": 83.88, "elapsed_time": "0:53:50", "remaining_time": "0:10:20", "throughput": 2656.69, "total_tokens": 8583424} {"current_steps": 32005, "total_steps": 38150, "loss": 0.197, "lr": 3.8498650446521264e-06, "epoch": 8.389252948885977, "percentage": 83.89, "elapsed_time": "0:53:51", "remaining_time": "0:10:20", "throughput": 2656.79, "total_tokens": 8584992} {"current_steps": 32010, "total_steps": 38150, "loss": 0.1435, "lr": 3.843769192974925e-06, "epoch": 8.390563564875492, "percentage": 83.91, "elapsed_time": "0:53:51", "remaining_time": "0:10:19", "throughput": 2656.78, "total_tokens": 8586080} {"current_steps": 32015, "total_steps": 38150, "loss": 0.1131, "lr": 3.837677769260273e-06, "epoch": 8.391874180865006, "percentage": 83.92, "elapsed_time": "0:53:52", "remaining_time": "0:10:19", "throughput": 2656.83, "total_tokens": 8587424} {"current_steps": 32020, "total_steps": 38150, "loss": 0.081, "lr": 3.8315907747831e-06, "epoch": 8.393184796854522, "percentage": 83.93, "elapsed_time": "0:53:52", "remaining_time": "0:10:18", "throughput": 2656.85, "total_tokens": 8588720} {"current_steps": 32025, "total_steps": 38150, "loss": 0.1513, "lr": 3.825508210817402e-06, "epoch": 8.394495412844037, "percentage": 83.94, "elapsed_time": "0:53:53", "remaining_time": "0:10:18", "throughput": 2656.9, "total_tokens": 8590144} {"current_steps": 32030, "total_steps": 38150, "loss": 0.1241, "lr": 3.8194300786362465e-06, "epoch": 8.395806028833551, "percentage": 83.96, "elapsed_time": "0:53:53", "remaining_time": "0:10:17", "throughput": 2656.95, "total_tokens": 8591520} {"current_steps": 32035, "total_steps": 38150, "loss": 0.1879, "lr": 3.8133563795117816e-06, "epoch": 8.397116644823067, "percentage": 83.97, "elapsed_time": "0:53:54", "remaining_time": "0:10:17", "throughput": 2656.97, "total_tokens": 8592816} {"current_steps": 32040, "total_steps": 38150, "loss": 0.1625, "lr": 3.807287114715216e-06, "epoch": 8.398427260812582, "percentage": 83.98, "elapsed_time": "0:53:54", "remaining_time": "0:10:16", "throughput": 2656.94, "total_tokens": 8593824} {"current_steps": 32045, "total_steps": 38150, "loss": 0.2191, "lr": 3.801222285516842e-06, "epoch": 8.399737876802098, "percentage": 84.0, "elapsed_time": "0:53:54", "remaining_time": "0:10:16", "throughput": 2656.97, "total_tokens": 8595040} {"current_steps": 32050, "total_steps": 38150, "loss": 0.1912, "lr": 3.7951618931860112e-06, "epoch": 8.401048492791611, "percentage": 84.01, "elapsed_time": "0:53:55", "remaining_time": "0:10:15", "throughput": 2656.99, "total_tokens": 8596240} {"current_steps": 32055, "total_steps": 38150, "loss": 0.2315, "lr": 3.789105938991161e-06, "epoch": 8.402359108781127, "percentage": 84.02, "elapsed_time": "0:53:55", "remaining_time": "0:10:15", "throughput": 2657.01, "total_tokens": 8597424} {"current_steps": 32060, "total_steps": 38150, "loss": 0.1261, "lr": 3.7830544241997864e-06, "epoch": 8.403669724770642, "percentage": 84.04, "elapsed_time": "0:53:56", "remaining_time": "0:10:14", "throughput": 2657.0, "total_tokens": 8598512} {"current_steps": 32065, "total_steps": 38150, "loss": 0.1131, "lr": 3.7770073500784596e-06, "epoch": 8.404980340760158, "percentage": 84.05, "elapsed_time": "0:53:56", "remaining_time": "0:10:14", "throughput": 2656.98, "total_tokens": 8599568} {"current_steps": 32070, "total_steps": 38150, "loss": 0.1533, "lr": 3.7709647178928246e-06, "epoch": 8.406290956749672, "percentage": 84.06, "elapsed_time": "0:53:57", "remaining_time": "0:10:13", "throughput": 2656.99, "total_tokens": 8600752} {"current_steps": 32075, "total_steps": 38150, "loss": 0.1156, "lr": 3.7649265289076003e-06, "epoch": 8.407601572739187, "percentage": 84.08, "elapsed_time": "0:53:57", "remaining_time": "0:10:13", "throughput": 2656.92, "total_tokens": 8601632} {"current_steps": 32080, "total_steps": 38150, "loss": 0.247, "lr": 3.7588927843865556e-06, "epoch": 8.408912188728703, "percentage": 84.09, "elapsed_time": "0:53:57", "remaining_time": "0:10:12", "throughput": 2657.01, "total_tokens": 8603216} {"current_steps": 32085, "total_steps": 38150, "loss": 0.1822, "lr": 3.7528634855925475e-06, "epoch": 8.410222804718218, "percentage": 84.1, "elapsed_time": "0:53:58", "remaining_time": "0:10:12", "throughput": 2657.08, "total_tokens": 8604672} {"current_steps": 32090, "total_steps": 38150, "loss": 0.0914, "lr": 3.7468386337875028e-06, "epoch": 8.411533420707732, "percentage": 84.12, "elapsed_time": "0:53:58", "remaining_time": "0:10:11", "throughput": 2657.1, "total_tokens": 8605856} {"current_steps": 32095, "total_steps": 38150, "loss": 0.1664, "lr": 3.7408182302324014e-06, "epoch": 8.412844036697248, "percentage": 84.13, "elapsed_time": "0:53:59", "remaining_time": "0:10:11", "throughput": 2657.08, "total_tokens": 8606912} {"current_steps": 32100, "total_steps": 38150, "loss": 0.2208, "lr": 3.734802276187319e-06, "epoch": 8.414154652686763, "percentage": 84.14, "elapsed_time": "0:53:59", "remaining_time": "0:10:10", "throughput": 2657.2, "total_tokens": 8608640} {"current_steps": 32105, "total_steps": 38150, "loss": 0.1267, "lr": 3.7287907729113754e-06, "epoch": 8.415465268676279, "percentage": 84.15, "elapsed_time": "0:54:00", "remaining_time": "0:10:10", "throughput": 2657.22, "total_tokens": 8609920} {"current_steps": 32110, "total_steps": 38150, "loss": 0.1513, "lr": 3.722783721662773e-06, "epoch": 8.416775884665793, "percentage": 84.17, "elapsed_time": "0:54:00", "remaining_time": "0:10:09", "throughput": 2657.29, "total_tokens": 8611328} {"current_steps": 32115, "total_steps": 38150, "loss": 0.0929, "lr": 3.7167811236987704e-06, "epoch": 8.418086500655308, "percentage": 84.18, "elapsed_time": "0:54:01", "remaining_time": "0:10:09", "throughput": 2657.33, "total_tokens": 8612608} {"current_steps": 32120, "total_steps": 38150, "loss": 0.1942, "lr": 3.710782980275704e-06, "epoch": 8.419397116644824, "percentage": 84.19, "elapsed_time": "0:54:01", "remaining_time": "0:10:08", "throughput": 2657.38, "total_tokens": 8614016} {"current_steps": 32125, "total_steps": 38150, "loss": 0.2535, "lr": 3.704789292648975e-06, "epoch": 8.420707732634337, "percentage": 84.21, "elapsed_time": "0:54:02", "remaining_time": "0:10:08", "throughput": 2657.48, "total_tokens": 8615616} {"current_steps": 32130, "total_steps": 38150, "loss": 0.1013, "lr": 3.6988000620730516e-06, "epoch": 8.422018348623853, "percentage": 84.22, "elapsed_time": "0:54:02", "remaining_time": "0:10:07", "throughput": 2657.48, "total_tokens": 8616832} {"current_steps": 32135, "total_steps": 38150, "loss": 0.1871, "lr": 3.6928152898014684e-06, "epoch": 8.423328964613368, "percentage": 84.23, "elapsed_time": "0:54:02", "remaining_time": "0:10:07", "throughput": 2657.6, "total_tokens": 8618560} {"current_steps": 32140, "total_steps": 38150, "loss": 0.186, "lr": 3.686834977086831e-06, "epoch": 8.424639580602884, "percentage": 84.25, "elapsed_time": "0:54:03", "remaining_time": "0:10:06", "throughput": 2657.6, "total_tokens": 8619776} {"current_steps": 32145, "total_steps": 38150, "loss": 0.1753, "lr": 3.680859125180805e-06, "epoch": 8.425950196592398, "percentage": 84.26, "elapsed_time": "0:54:03", "remaining_time": "0:10:05", "throughput": 2657.63, "total_tokens": 8621008} {"current_steps": 32150, "total_steps": 38150, "loss": 0.2404, "lr": 3.674887735334126e-06, "epoch": 8.427260812581913, "percentage": 84.27, "elapsed_time": "0:54:04", "remaining_time": "0:10:05", "throughput": 2657.77, "total_tokens": 8622928} {"current_steps": 32155, "total_steps": 38150, "loss": 0.1832, "lr": 3.6689208087966e-06, "epoch": 8.428571428571429, "percentage": 84.29, "elapsed_time": "0:54:04", "remaining_time": "0:10:04", "throughput": 2657.83, "total_tokens": 8624320} {"current_steps": 32160, "total_steps": 38150, "loss": 0.2594, "lr": 3.6629583468170914e-06, "epoch": 8.429882044560944, "percentage": 84.3, "elapsed_time": "0:54:05", "remaining_time": "0:10:04", "throughput": 2657.87, "total_tokens": 8625648} {"current_steps": 32165, "total_steps": 38150, "loss": 0.1145, "lr": 3.65700035064353e-06, "epoch": 8.431192660550458, "percentage": 84.31, "elapsed_time": "0:54:05", "remaining_time": "0:10:03", "throughput": 2657.93, "total_tokens": 8627152} {"current_steps": 32170, "total_steps": 38150, "loss": 0.1474, "lr": 3.6510468215229215e-06, "epoch": 8.432503276539974, "percentage": 84.33, "elapsed_time": "0:54:06", "remaining_time": "0:10:03", "throughput": 2657.95, "total_tokens": 8628464} {"current_steps": 32175, "total_steps": 38150, "loss": 0.0663, "lr": 3.6450977607013217e-06, "epoch": 8.43381389252949, "percentage": 84.34, "elapsed_time": "0:54:06", "remaining_time": "0:10:02", "throughput": 2657.91, "total_tokens": 8629408} {"current_steps": 32180, "total_steps": 38150, "loss": 0.1639, "lr": 3.6391531694238647e-06, "epoch": 8.435124508519005, "percentage": 84.35, "elapsed_time": "0:54:07", "remaining_time": "0:10:02", "throughput": 2657.94, "total_tokens": 8630656} {"current_steps": 32185, "total_steps": 38150, "loss": 0.1493, "lr": 3.6332130489347387e-06, "epoch": 8.436435124508519, "percentage": 84.36, "elapsed_time": "0:54:07", "remaining_time": "0:10:01", "throughput": 2657.98, "total_tokens": 8631936} {"current_steps": 32190, "total_steps": 38150, "loss": 0.2351, "lr": 3.627277400477211e-06, "epoch": 8.437745740498034, "percentage": 84.38, "elapsed_time": "0:54:08", "remaining_time": "0:10:01", "throughput": 2658.1, "total_tokens": 8633584} {"current_steps": 32195, "total_steps": 38150, "loss": 0.12, "lr": 3.6213462252935844e-06, "epoch": 8.43905635648755, "percentage": 84.39, "elapsed_time": "0:54:08", "remaining_time": "0:10:00", "throughput": 2658.26, "total_tokens": 8635584} {"current_steps": 32200, "total_steps": 38150, "loss": 0.2931, "lr": 3.6154195246252575e-06, "epoch": 8.440366972477065, "percentage": 84.4, "elapsed_time": "0:54:09", "remaining_time": "0:10:00", "throughput": 2658.31, "total_tokens": 8636912} {"current_steps": 32205, "total_steps": 38150, "loss": 0.2187, "lr": 3.609497299712672e-06, "epoch": 8.441677588466579, "percentage": 84.42, "elapsed_time": "0:54:09", "remaining_time": "0:09:59", "throughput": 2658.31, "total_tokens": 8638112} {"current_steps": 32210, "total_steps": 38150, "loss": 0.1559, "lr": 3.6035795517953357e-06, "epoch": 8.442988204456094, "percentage": 84.43, "elapsed_time": "0:54:09", "remaining_time": "0:09:59", "throughput": 2658.39, "total_tokens": 8639568} {"current_steps": 32215, "total_steps": 38150, "loss": 0.1334, "lr": 3.597666282111836e-06, "epoch": 8.44429882044561, "percentage": 84.44, "elapsed_time": "0:54:10", "remaining_time": "0:09:58", "throughput": 2658.43, "total_tokens": 8640832} {"current_steps": 32220, "total_steps": 38150, "loss": 0.1827, "lr": 3.5917574918998024e-06, "epoch": 8.445609436435124, "percentage": 84.46, "elapsed_time": "0:54:10", "remaining_time": "0:09:58", "throughput": 2658.49, "total_tokens": 8642192} {"current_steps": 32225, "total_steps": 38150, "loss": 0.1324, "lr": 3.58585318239594e-06, "epoch": 8.44692005242464, "percentage": 84.47, "elapsed_time": "0:54:11", "remaining_time": "0:09:57", "throughput": 2658.48, "total_tokens": 8643328} {"current_steps": 32230, "total_steps": 38150, "loss": 0.1731, "lr": 3.579953354836002e-06, "epoch": 8.448230668414155, "percentage": 84.48, "elapsed_time": "0:54:11", "remaining_time": "0:09:57", "throughput": 2658.44, "total_tokens": 8644400} {"current_steps": 32235, "total_steps": 38150, "loss": 0.1463, "lr": 3.5740580104548145e-06, "epoch": 8.44954128440367, "percentage": 84.5, "elapsed_time": "0:54:12", "remaining_time": "0:09:56", "throughput": 2658.52, "total_tokens": 8645920} {"current_steps": 32240, "total_steps": 38150, "loss": 0.1523, "lr": 3.568167150486265e-06, "epoch": 8.450851900393184, "percentage": 84.51, "elapsed_time": "0:54:12", "remaining_time": "0:09:56", "throughput": 2658.54, "total_tokens": 8647152} {"current_steps": 32245, "total_steps": 38150, "loss": 0.079, "lr": 3.5622807761632985e-06, "epoch": 8.4521625163827, "percentage": 84.52, "elapsed_time": "0:54:13", "remaining_time": "0:09:55", "throughput": 2658.55, "total_tokens": 8648320} {"current_steps": 32250, "total_steps": 38150, "loss": 0.0532, "lr": 3.5563988887179266e-06, "epoch": 8.453473132372215, "percentage": 84.53, "elapsed_time": "0:54:13", "remaining_time": "0:09:55", "throughput": 2658.53, "total_tokens": 8649376} {"current_steps": 32255, "total_steps": 38150, "loss": 0.1382, "lr": 3.5505214893812115e-06, "epoch": 8.45478374836173, "percentage": 84.55, "elapsed_time": "0:54:13", "remaining_time": "0:09:54", "throughput": 2658.64, "total_tokens": 8651136} {"current_steps": 32260, "total_steps": 38150, "loss": 0.1626, "lr": 3.5446485793832918e-06, "epoch": 8.456094364351245, "percentage": 84.56, "elapsed_time": "0:54:14", "remaining_time": "0:09:54", "throughput": 2658.73, "total_tokens": 8652704} {"current_steps": 32265, "total_steps": 38150, "loss": 0.218, "lr": 3.5387801599533475e-06, "epoch": 8.45740498034076, "percentage": 84.57, "elapsed_time": "0:54:15", "remaining_time": "0:09:53", "throughput": 2658.93, "total_tokens": 8654976} {"current_steps": 32270, "total_steps": 38150, "loss": 0.3595, "lr": 3.5329162323196356e-06, "epoch": 8.458715596330276, "percentage": 84.59, "elapsed_time": "0:54:15", "remaining_time": "0:09:53", "throughput": 2659.03, "total_tokens": 8656640} {"current_steps": 32275, "total_steps": 38150, "loss": 0.2213, "lr": 3.527056797709466e-06, "epoch": 8.460026212319791, "percentage": 84.6, "elapsed_time": "0:54:16", "remaining_time": "0:09:52", "throughput": 2659.06, "total_tokens": 8657968} {"current_steps": 32280, "total_steps": 38150, "loss": 0.2111, "lr": 3.5212018573492047e-06, "epoch": 8.461336828309305, "percentage": 84.61, "elapsed_time": "0:54:16", "remaining_time": "0:09:52", "throughput": 2659.23, "total_tokens": 8660048} {"current_steps": 32285, "total_steps": 38150, "loss": 0.0938, "lr": 3.5153514124642822e-06, "epoch": 8.46264744429882, "percentage": 84.63, "elapsed_time": "0:54:17", "remaining_time": "0:09:51", "throughput": 2659.26, "total_tokens": 8661280} {"current_steps": 32290, "total_steps": 38150, "loss": 0.2362, "lr": 3.5095054642791862e-06, "epoch": 8.463958060288336, "percentage": 84.64, "elapsed_time": "0:54:17", "remaining_time": "0:09:51", "throughput": 2659.42, "total_tokens": 8663200} {"current_steps": 32295, "total_steps": 38150, "loss": 0.0907, "lr": 3.503664014017463e-06, "epoch": 8.46526867627785, "percentage": 84.65, "elapsed_time": "0:54:18", "remaining_time": "0:09:50", "throughput": 2659.51, "total_tokens": 8664768} {"current_steps": 32300, "total_steps": 38150, "loss": 0.1696, "lr": 3.4978270629017207e-06, "epoch": 8.466579292267365, "percentage": 84.67, "elapsed_time": "0:54:18", "remaining_time": "0:09:50", "throughput": 2659.48, "total_tokens": 8665824} {"current_steps": 32305, "total_steps": 38150, "loss": 0.2285, "lr": 3.491994612153618e-06, "epoch": 8.46788990825688, "percentage": 84.68, "elapsed_time": "0:54:18", "remaining_time": "0:09:49", "throughput": 2659.54, "total_tokens": 8667200} {"current_steps": 32310, "total_steps": 38150, "loss": 0.127, "lr": 3.4861666629938896e-06, "epoch": 8.469200524246396, "percentage": 84.69, "elapsed_time": "0:54:19", "remaining_time": "0:09:49", "throughput": 2659.62, "total_tokens": 8668640} {"current_steps": 32315, "total_steps": 38150, "loss": 0.1615, "lr": 3.4803432166422983e-06, "epoch": 8.47051114023591, "percentage": 84.71, "elapsed_time": "0:54:19", "remaining_time": "0:09:48", "throughput": 2659.6, "total_tokens": 8669696} {"current_steps": 32320, "total_steps": 38150, "loss": 0.1728, "lr": 3.474524274317689e-06, "epoch": 8.471821756225426, "percentage": 84.72, "elapsed_time": "0:54:20", "remaining_time": "0:09:48", "throughput": 2659.6, "total_tokens": 8670848} {"current_steps": 32325, "total_steps": 38150, "loss": 0.1396, "lr": 3.468709837237949e-06, "epoch": 8.473132372214941, "percentage": 84.73, "elapsed_time": "0:54:20", "remaining_time": "0:09:47", "throughput": 2659.6, "total_tokens": 8671968} {"current_steps": 32330, "total_steps": 38150, "loss": 0.173, "lr": 3.4628999066200427e-06, "epoch": 8.474442988204457, "percentage": 84.74, "elapsed_time": "0:54:21", "remaining_time": "0:09:47", "throughput": 2659.51, "total_tokens": 8672768} {"current_steps": 32335, "total_steps": 38150, "loss": 0.1275, "lr": 3.4570944836799734e-06, "epoch": 8.47575360419397, "percentage": 84.76, "elapsed_time": "0:54:21", "remaining_time": "0:09:46", "throughput": 2659.58, "total_tokens": 8674176} {"current_steps": 32340, "total_steps": 38150, "loss": 0.1883, "lr": 3.4512935696328045e-06, "epoch": 8.477064220183486, "percentage": 84.77, "elapsed_time": "0:54:21", "remaining_time": "0:09:46", "throughput": 2659.65, "total_tokens": 8675696} {"current_steps": 32345, "total_steps": 38150, "loss": 0.1476, "lr": 3.4454971656926655e-06, "epoch": 8.478374836173002, "percentage": 84.78, "elapsed_time": "0:54:22", "remaining_time": "0:09:45", "throughput": 2659.75, "total_tokens": 8677280} {"current_steps": 32350, "total_steps": 38150, "loss": 0.1065, "lr": 3.4397052730727214e-06, "epoch": 8.479685452162517, "percentage": 84.8, "elapsed_time": "0:54:22", "remaining_time": "0:09:44", "throughput": 2659.75, "total_tokens": 8678400} {"current_steps": 32355, "total_steps": 38150, "loss": 0.1753, "lr": 3.4339178929852085e-06, "epoch": 8.48099606815203, "percentage": 84.81, "elapsed_time": "0:54:23", "remaining_time": "0:09:44", "throughput": 2659.78, "total_tokens": 8679696} {"current_steps": 32360, "total_steps": 38150, "loss": 0.1876, "lr": 3.4281350266414158e-06, "epoch": 8.482306684141546, "percentage": 84.82, "elapsed_time": "0:54:23", "remaining_time": "0:09:43", "throughput": 2659.75, "total_tokens": 8680720} {"current_steps": 32365, "total_steps": 38150, "loss": 0.1912, "lr": 3.422356675251692e-06, "epoch": 8.483617300131062, "percentage": 84.84, "elapsed_time": "0:54:24", "remaining_time": "0:09:43", "throughput": 2659.81, "total_tokens": 8682160} {"current_steps": 32370, "total_steps": 38150, "loss": 0.2006, "lr": 3.4165828400254314e-06, "epoch": 8.484927916120578, "percentage": 84.85, "elapsed_time": "0:54:24", "remaining_time": "0:09:42", "throughput": 2659.9, "total_tokens": 8683728} {"current_steps": 32375, "total_steps": 38150, "loss": 0.1157, "lr": 3.4108135221710885e-06, "epoch": 8.486238532110091, "percentage": 84.86, "elapsed_time": "0:54:25", "remaining_time": "0:09:42", "throughput": 2659.86, "total_tokens": 8684704} {"current_steps": 32380, "total_steps": 38150, "loss": 0.192, "lr": 3.405048722896173e-06, "epoch": 8.487549148099607, "percentage": 84.88, "elapsed_time": "0:54:25", "remaining_time": "0:09:41", "throughput": 2659.95, "total_tokens": 8686288} {"current_steps": 32385, "total_steps": 38150, "loss": 0.1706, "lr": 3.3992884434072474e-06, "epoch": 8.488859764089122, "percentage": 84.89, "elapsed_time": "0:54:26", "remaining_time": "0:09:41", "throughput": 2659.94, "total_tokens": 8687408} {"current_steps": 32390, "total_steps": 38150, "loss": 0.144, "lr": 3.3935326849099253e-06, "epoch": 8.490170380078636, "percentage": 84.9, "elapsed_time": "0:54:26", "remaining_time": "0:09:40", "throughput": 2659.95, "total_tokens": 8688592} {"current_steps": 32395, "total_steps": 38150, "loss": 0.1593, "lr": 3.3877814486088816e-06, "epoch": 8.491480996068152, "percentage": 84.91, "elapsed_time": "0:54:26", "remaining_time": "0:09:40", "throughput": 2659.98, "total_tokens": 8689792} {"current_steps": 32400, "total_steps": 38150, "loss": 0.167, "lr": 3.382034735707834e-06, "epoch": 8.492791612057667, "percentage": 84.93, "elapsed_time": "0:54:27", "remaining_time": "0:09:39", "throughput": 2659.97, "total_tokens": 8690896} {"current_steps": 32405, "total_steps": 38150, "loss": 0.1035, "lr": 3.376292547409568e-06, "epoch": 8.494102228047183, "percentage": 84.94, "elapsed_time": "0:54:27", "remaining_time": "0:09:39", "throughput": 2659.95, "total_tokens": 8691968} {"current_steps": 32410, "total_steps": 38150, "loss": 0.208, "lr": 3.3705548849159054e-06, "epoch": 8.495412844036696, "percentage": 84.95, "elapsed_time": "0:54:28", "remaining_time": "0:09:38", "throughput": 2660.06, "total_tokens": 8693648} {"current_steps": 32415, "total_steps": 38150, "loss": 0.1951, "lr": 3.364821749427732e-06, "epoch": 8.496723460026212, "percentage": 84.97, "elapsed_time": "0:54:28", "remaining_time": "0:09:38", "throughput": 2660.14, "total_tokens": 8695056} {"current_steps": 32420, "total_steps": 38150, "loss": 0.0694, "lr": 3.3590931421449867e-06, "epoch": 8.498034076015728, "percentage": 84.98, "elapsed_time": "0:54:29", "remaining_time": "0:09:37", "throughput": 2660.18, "total_tokens": 8696368} {"current_steps": 32425, "total_steps": 38150, "loss": 0.0639, "lr": 3.3533690642666595e-06, "epoch": 8.499344692005243, "percentage": 84.99, "elapsed_time": "0:54:29", "remaining_time": "0:09:37", "throughput": 2660.17, "total_tokens": 8697472} {"current_steps": 32430, "total_steps": 38150, "loss": 0.1777, "lr": 3.347649516990778e-06, "epoch": 8.500655307994757, "percentage": 85.01, "elapsed_time": "0:54:29", "remaining_time": "0:09:36", "throughput": 2660.22, "total_tokens": 8698880} {"current_steps": 32435, "total_steps": 38150, "loss": 0.1042, "lr": 3.3419345015144406e-06, "epoch": 8.501965923984272, "percentage": 85.02, "elapsed_time": "0:54:30", "remaining_time": "0:09:36", "throughput": 2660.24, "total_tokens": 8700096} {"current_steps": 32436, "total_steps": 38150, "eval_loss": 0.8241025805473328, "epoch": 8.502228047182175, "percentage": 85.02, "elapsed_time": "0:54:47", "remaining_time": "0:09:39", "throughput": 2646.62, "total_tokens": 8700416} {"current_steps": 32440, "total_steps": 38150, "loss": 0.3265, "lr": 3.3362240190337817e-06, "epoch": 8.503276539973788, "percentage": 85.03, "elapsed_time": "0:54:49", "remaining_time": "0:09:38", "throughput": 2645.49, "total_tokens": 8701568} {"current_steps": 32445, "total_steps": 38150, "loss": 0.1729, "lr": 3.3305180707440124e-06, "epoch": 8.504587155963304, "percentage": 85.05, "elapsed_time": "0:54:49", "remaining_time": "0:09:38", "throughput": 2645.54, "total_tokens": 8702976} {"current_steps": 32450, "total_steps": 38150, "loss": 0.2445, "lr": 3.3248166578393665e-06, "epoch": 8.505897771952817, "percentage": 85.06, "elapsed_time": "0:54:50", "remaining_time": "0:09:37", "throughput": 2645.56, "total_tokens": 8704208} {"current_steps": 32455, "total_steps": 38150, "loss": 0.3193, "lr": 3.319119781513144e-06, "epoch": 8.507208387942333, "percentage": 85.07, "elapsed_time": "0:54:50", "remaining_time": "0:09:37", "throughput": 2645.58, "total_tokens": 8705440} {"current_steps": 32460, "total_steps": 38150, "loss": 0.0513, "lr": 3.313427442957695e-06, "epoch": 8.508519003931848, "percentage": 85.09, "elapsed_time": "0:54:50", "remaining_time": "0:09:36", "throughput": 2645.52, "total_tokens": 8706368} {"current_steps": 32465, "total_steps": 38150, "loss": 0.1621, "lr": 3.3077396433644046e-06, "epoch": 8.509829619921362, "percentage": 85.1, "elapsed_time": "0:54:51", "remaining_time": "0:09:36", "throughput": 2645.65, "total_tokens": 8708048} {"current_steps": 32470, "total_steps": 38150, "loss": 0.1733, "lr": 3.3020563839237267e-06, "epoch": 8.511140235910878, "percentage": 85.11, "elapsed_time": "0:54:51", "remaining_time": "0:09:35", "throughput": 2645.64, "total_tokens": 8709200} {"current_steps": 32475, "total_steps": 38150, "loss": 0.1547, "lr": 3.2963776658251537e-06, "epoch": 8.512450851900393, "percentage": 85.12, "elapsed_time": "0:54:52", "remaining_time": "0:09:35", "throughput": 2645.63, "total_tokens": 8710304} {"current_steps": 32480, "total_steps": 38150, "loss": 0.3586, "lr": 3.2907034902572382e-06, "epoch": 8.513761467889909, "percentage": 85.14, "elapsed_time": "0:54:52", "remaining_time": "0:09:34", "throughput": 2645.67, "total_tokens": 8711632} {"current_steps": 32485, "total_steps": 38150, "loss": 0.0875, "lr": 3.2850338584075686e-06, "epoch": 8.515072083879424, "percentage": 85.15, "elapsed_time": "0:54:53", "remaining_time": "0:09:34", "throughput": 2645.59, "total_tokens": 8712464} {"current_steps": 32490, "total_steps": 38150, "loss": 0.2251, "lr": 3.279368771462793e-06, "epoch": 8.516382699868938, "percentage": 85.16, "elapsed_time": "0:54:53", "remaining_time": "0:09:33", "throughput": 2645.58, "total_tokens": 8713568} {"current_steps": 32495, "total_steps": 38150, "loss": 0.2073, "lr": 3.273708230608602e-06, "epoch": 8.517693315858454, "percentage": 85.18, "elapsed_time": "0:54:54", "remaining_time": "0:09:33", "throughput": 2645.66, "total_tokens": 8715136} {"current_steps": 32500, "total_steps": 38150, "loss": 0.1126, "lr": 3.2680522370297397e-06, "epoch": 8.51900393184797, "percentage": 85.19, "elapsed_time": "0:54:54", "remaining_time": "0:09:32", "throughput": 2645.8, "total_tokens": 8717136} {"current_steps": 32505, "total_steps": 38150, "loss": 0.1323, "lr": 3.262400791909992e-06, "epoch": 8.520314547837483, "percentage": 85.2, "elapsed_time": "0:54:55", "remaining_time": "0:09:32", "throughput": 2645.85, "total_tokens": 8718544} {"current_steps": 32510, "total_steps": 38150, "loss": 0.1449, "lr": 3.256753896432202e-06, "epoch": 8.521625163826998, "percentage": 85.22, "elapsed_time": "0:54:55", "remaining_time": "0:09:31", "throughput": 2645.85, "total_tokens": 8719680} {"current_steps": 32515, "total_steps": 38150, "loss": 0.1116, "lr": 3.2511115517782494e-06, "epoch": 8.522935779816514, "percentage": 85.23, "elapsed_time": "0:54:56", "remaining_time": "0:09:31", "throughput": 2645.95, "total_tokens": 8721344} {"current_steps": 32520, "total_steps": 38150, "loss": 0.2223, "lr": 3.2454737591290695e-06, "epoch": 8.52424639580603, "percentage": 85.24, "elapsed_time": "0:54:56", "remaining_time": "0:09:30", "throughput": 2646.01, "total_tokens": 8722752} {"current_steps": 32525, "total_steps": 38150, "loss": 0.0542, "lr": 3.2398405196646443e-06, "epoch": 8.525557011795543, "percentage": 85.26, "elapsed_time": "0:54:57", "remaining_time": "0:09:30", "throughput": 2646.03, "total_tokens": 8723984} {"current_steps": 32530, "total_steps": 38150, "loss": 0.2308, "lr": 3.2342118345639993e-06, "epoch": 8.526867627785059, "percentage": 85.27, "elapsed_time": "0:54:57", "remaining_time": "0:09:29", "throughput": 2646.06, "total_tokens": 8725184} {"current_steps": 32535, "total_steps": 38150, "loss": 0.1459, "lr": 3.2285877050052093e-06, "epoch": 8.528178243774574, "percentage": 85.28, "elapsed_time": "0:54:57", "remaining_time": "0:09:29", "throughput": 2646.11, "total_tokens": 8726592} {"current_steps": 32540, "total_steps": 38150, "loss": 0.0786, "lr": 3.2229681321653966e-06, "epoch": 8.52948885976409, "percentage": 85.29, "elapsed_time": "0:54:58", "remaining_time": "0:09:28", "throughput": 2646.09, "total_tokens": 8727664} {"current_steps": 32545, "total_steps": 38150, "loss": 0.1868, "lr": 3.2173531172207283e-06, "epoch": 8.530799475753604, "percentage": 85.31, "elapsed_time": "0:54:58", "remaining_time": "0:09:28", "throughput": 2646.11, "total_tokens": 8728928} {"current_steps": 32550, "total_steps": 38150, "loss": 0.1454, "lr": 3.211742661346409e-06, "epoch": 8.53211009174312, "percentage": 85.32, "elapsed_time": "0:54:59", "remaining_time": "0:09:27", "throughput": 2646.17, "total_tokens": 8730256} {"current_steps": 32555, "total_steps": 38150, "loss": 0.1322, "lr": 3.2061367657167025e-06, "epoch": 8.533420707732635, "percentage": 85.33, "elapsed_time": "0:54:59", "remaining_time": "0:09:27", "throughput": 2646.13, "total_tokens": 8731248} {"current_steps": 32560, "total_steps": 38150, "loss": 0.1815, "lr": 3.200535431504914e-06, "epoch": 8.534731323722148, "percentage": 85.35, "elapsed_time": "0:55:00", "remaining_time": "0:09:26", "throughput": 2646.18, "total_tokens": 8732624} {"current_steps": 32565, "total_steps": 38150, "loss": 0.1275, "lr": 3.194938659883398e-06, "epoch": 8.536041939711664, "percentage": 85.36, "elapsed_time": "0:55:00", "remaining_time": "0:09:26", "throughput": 2646.17, "total_tokens": 8733728} {"current_steps": 32570, "total_steps": 38150, "loss": 0.2082, "lr": 3.189346452023542e-06, "epoch": 8.53735255570118, "percentage": 85.37, "elapsed_time": "0:55:00", "remaining_time": "0:09:25", "throughput": 2646.16, "total_tokens": 8734784} {"current_steps": 32575, "total_steps": 38150, "loss": 0.1223, "lr": 3.1837588090957853e-06, "epoch": 8.538663171690695, "percentage": 85.39, "elapsed_time": "0:55:01", "remaining_time": "0:09:25", "throughput": 2646.24, "total_tokens": 8736320} {"current_steps": 32580, "total_steps": 38150, "loss": 0.1842, "lr": 3.1781757322696224e-06, "epoch": 8.539973787680209, "percentage": 85.4, "elapsed_time": "0:55:01", "remaining_time": "0:09:24", "throughput": 2646.24, "total_tokens": 8737424} {"current_steps": 32585, "total_steps": 38150, "loss": 0.1449, "lr": 3.172597222713569e-06, "epoch": 8.541284403669724, "percentage": 85.41, "elapsed_time": "0:55:02", "remaining_time": "0:09:23", "throughput": 2646.24, "total_tokens": 8738592} {"current_steps": 32590, "total_steps": 38150, "loss": 0.1205, "lr": 3.1670232815951994e-06, "epoch": 8.54259501965924, "percentage": 85.43, "elapsed_time": "0:55:02", "remaining_time": "0:09:23", "throughput": 2646.27, "total_tokens": 8739936} {"current_steps": 32595, "total_steps": 38150, "loss": 0.2535, "lr": 3.1614539100811356e-06, "epoch": 8.543905635648755, "percentage": 85.44, "elapsed_time": "0:55:03", "remaining_time": "0:09:22", "throughput": 2646.35, "total_tokens": 8741440} {"current_steps": 32600, "total_steps": 38150, "loss": 0.2241, "lr": 3.1558891093370318e-06, "epoch": 8.54521625163827, "percentage": 85.45, "elapsed_time": "0:55:03", "remaining_time": "0:09:22", "throughput": 2646.45, "total_tokens": 8743024} {"current_steps": 32605, "total_steps": 38150, "loss": 0.128, "lr": 3.150328880527595e-06, "epoch": 8.546526867627785, "percentage": 85.47, "elapsed_time": "0:55:04", "remaining_time": "0:09:21", "throughput": 2646.45, "total_tokens": 8744160} {"current_steps": 32610, "total_steps": 38150, "loss": 0.137, "lr": 3.1447732248165633e-06, "epoch": 8.5478374836173, "percentage": 85.48, "elapsed_time": "0:55:04", "remaining_time": "0:09:21", "throughput": 2646.47, "total_tokens": 8745344} {"current_steps": 32615, "total_steps": 38150, "loss": 0.1581, "lr": 3.139222143366746e-06, "epoch": 8.549148099606816, "percentage": 85.49, "elapsed_time": "0:55:04", "remaining_time": "0:09:20", "throughput": 2646.54, "total_tokens": 8746800} {"current_steps": 32620, "total_steps": 38150, "loss": 0.1209, "lr": 3.1336756373399556e-06, "epoch": 8.55045871559633, "percentage": 85.5, "elapsed_time": "0:55:05", "remaining_time": "0:09:20", "throughput": 2646.64, "total_tokens": 8748416} {"current_steps": 32625, "total_steps": 38150, "loss": 0.1772, "lr": 3.128133707897071e-06, "epoch": 8.551769331585845, "percentage": 85.52, "elapsed_time": "0:55:05", "remaining_time": "0:09:19", "throughput": 2646.71, "total_tokens": 8749808} {"current_steps": 32630, "total_steps": 38150, "loss": 0.2522, "lr": 3.12259635619801e-06, "epoch": 8.55307994757536, "percentage": 85.53, "elapsed_time": "0:55:06", "remaining_time": "0:09:19", "throughput": 2646.73, "total_tokens": 8751008} {"current_steps": 32635, "total_steps": 38150, "loss": 0.1745, "lr": 3.1170635834017303e-06, "epoch": 8.554390563564876, "percentage": 85.54, "elapsed_time": "0:55:06", "remaining_time": "0:09:18", "throughput": 2646.79, "total_tokens": 8752416} {"current_steps": 32640, "total_steps": 38150, "loss": 0.1155, "lr": 3.1115353906662313e-06, "epoch": 8.55570117955439, "percentage": 85.56, "elapsed_time": "0:55:07", "remaining_time": "0:09:18", "throughput": 2646.76, "total_tokens": 8753456} {"current_steps": 32645, "total_steps": 38150, "loss": 0.1362, "lr": 3.1060117791485544e-06, "epoch": 8.557011795543906, "percentage": 85.57, "elapsed_time": "0:55:07", "remaining_time": "0:09:17", "throughput": 2646.79, "total_tokens": 8754768} {"current_steps": 32650, "total_steps": 38150, "loss": 0.1794, "lr": 3.1004927500047827e-06, "epoch": 8.558322411533421, "percentage": 85.58, "elapsed_time": "0:55:08", "remaining_time": "0:09:17", "throughput": 2646.86, "total_tokens": 8756160} {"current_steps": 32655, "total_steps": 38150, "loss": 0.1211, "lr": 3.0949783043900393e-06, "epoch": 8.559633027522935, "percentage": 85.6, "elapsed_time": "0:55:08", "remaining_time": "0:09:16", "throughput": 2646.81, "total_tokens": 8757088} {"current_steps": 32660, "total_steps": 38150, "loss": 0.2267, "lr": 3.0894684434584958e-06, "epoch": 8.56094364351245, "percentage": 85.61, "elapsed_time": "0:55:08", "remaining_time": "0:09:16", "throughput": 2646.87, "total_tokens": 8758464} {"current_steps": 32665, "total_steps": 38150, "loss": 0.1597, "lr": 3.083963168363341e-06, "epoch": 8.562254259501966, "percentage": 85.62, "elapsed_time": "0:55:09", "remaining_time": "0:09:15", "throughput": 2646.91, "total_tokens": 8759792} {"current_steps": 32670, "total_steps": 38150, "loss": 0.1962, "lr": 3.0784624802568192e-06, "epoch": 8.563564875491481, "percentage": 85.64, "elapsed_time": "0:55:09", "remaining_time": "0:09:15", "throughput": 2646.98, "total_tokens": 8761248} {"current_steps": 32675, "total_steps": 38150, "loss": 0.1562, "lr": 3.072966380290232e-06, "epoch": 8.564875491480995, "percentage": 85.65, "elapsed_time": "0:55:10", "remaining_time": "0:09:14", "throughput": 2647.01, "total_tokens": 8762480} {"current_steps": 32680, "total_steps": 38150, "loss": 0.2542, "lr": 3.0674748696138927e-06, "epoch": 8.56618610747051, "percentage": 85.66, "elapsed_time": "0:55:10", "remaining_time": "0:09:14", "throughput": 2647.13, "total_tokens": 8764176} {"current_steps": 32685, "total_steps": 38150, "loss": 0.2891, "lr": 3.0619879493771654e-06, "epoch": 8.567496723460026, "percentage": 85.67, "elapsed_time": "0:55:11", "remaining_time": "0:09:13", "throughput": 2647.14, "total_tokens": 8765344} {"current_steps": 32690, "total_steps": 38150, "loss": 0.0718, "lr": 3.056505620728456e-06, "epoch": 8.568807339449542, "percentage": 85.69, "elapsed_time": "0:55:11", "remaining_time": "0:09:13", "throughput": 2647.16, "total_tokens": 8766608} {"current_steps": 32695, "total_steps": 38150, "loss": 0.2521, "lr": 3.051027884815211e-06, "epoch": 8.570117955439056, "percentage": 85.7, "elapsed_time": "0:55:12", "remaining_time": "0:09:12", "throughput": 2647.32, "total_tokens": 8768576} {"current_steps": 32700, "total_steps": 38150, "loss": 0.1184, "lr": 3.0455547427838986e-06, "epoch": 8.571428571428571, "percentage": 85.71, "elapsed_time": "0:55:12", "remaining_time": "0:09:12", "throughput": 2647.32, "total_tokens": 8769712} {"current_steps": 32705, "total_steps": 38150, "loss": 0.2782, "lr": 3.0400861957800423e-06, "epoch": 8.572739187418087, "percentage": 85.73, "elapsed_time": "0:55:13", "remaining_time": "0:09:11", "throughput": 2647.5, "total_tokens": 8771792} {"current_steps": 32710, "total_steps": 38150, "loss": 0.1918, "lr": 3.034622244948204e-06, "epoch": 8.574049803407602, "percentage": 85.74, "elapsed_time": "0:55:13", "remaining_time": "0:09:11", "throughput": 2647.5, "total_tokens": 8772912} {"current_steps": 32715, "total_steps": 38150, "loss": 0.1364, "lr": 3.029162891431975e-06, "epoch": 8.575360419397116, "percentage": 85.75, "elapsed_time": "0:55:14", "remaining_time": "0:09:10", "throughput": 2647.62, "total_tokens": 8774656} {"current_steps": 32720, "total_steps": 38150, "loss": 0.1207, "lr": 3.02370813637399e-06, "epoch": 8.576671035386632, "percentage": 85.77, "elapsed_time": "0:55:14", "remaining_time": "0:09:10", "throughput": 2647.77, "total_tokens": 8776688} {"current_steps": 32725, "total_steps": 38150, "loss": 0.0862, "lr": 3.018257980915917e-06, "epoch": 8.577981651376147, "percentage": 85.78, "elapsed_time": "0:55:15", "remaining_time": "0:09:09", "throughput": 2647.73, "total_tokens": 8777680} {"current_steps": 32730, "total_steps": 38150, "loss": 0.2107, "lr": 3.0128124261984693e-06, "epoch": 8.579292267365663, "percentage": 85.79, "elapsed_time": "0:55:15", "remaining_time": "0:09:09", "throughput": 2647.69, "total_tokens": 8778656} {"current_steps": 32735, "total_steps": 38150, "loss": 0.1003, "lr": 3.007371473361398e-06, "epoch": 8.580602883355176, "percentage": 85.81, "elapsed_time": "0:55:16", "remaining_time": "0:09:08", "throughput": 2647.71, "total_tokens": 8779968} {"current_steps": 32740, "total_steps": 38150, "loss": 0.2009, "lr": 3.00193512354347e-06, "epoch": 8.581913499344692, "percentage": 85.82, "elapsed_time": "0:55:16", "remaining_time": "0:09:08", "throughput": 2647.86, "total_tokens": 8781888} {"current_steps": 32745, "total_steps": 38150, "loss": 0.1956, "lr": 2.996503377882512e-06, "epoch": 8.583224115334207, "percentage": 85.83, "elapsed_time": "0:55:17", "remaining_time": "0:09:07", "throughput": 2647.94, "total_tokens": 8783424} {"current_steps": 32750, "total_steps": 38150, "loss": 0.0765, "lr": 2.9910762375153752e-06, "epoch": 8.584534731323721, "percentage": 85.85, "elapsed_time": "0:55:17", "remaining_time": "0:09:07", "throughput": 2647.93, "total_tokens": 8784496} {"current_steps": 32755, "total_steps": 38150, "loss": 0.2852, "lr": 2.9856537035779564e-06, "epoch": 8.585845347313237, "percentage": 85.86, "elapsed_time": "0:55:17", "remaining_time": "0:09:06", "throughput": 2647.99, "total_tokens": 8785840} {"current_steps": 32760, "total_steps": 38150, "loss": 0.126, "lr": 2.980235777205179e-06, "epoch": 8.587155963302752, "percentage": 85.87, "elapsed_time": "0:55:18", "remaining_time": "0:09:05", "throughput": 2648.07, "total_tokens": 8787392} {"current_steps": 32765, "total_steps": 38150, "loss": 0.1326, "lr": 2.9748224595310042e-06, "epoch": 8.588466579292268, "percentage": 85.88, "elapsed_time": "0:55:18", "remaining_time": "0:09:05", "throughput": 2648.11, "total_tokens": 8788704} {"current_steps": 32770, "total_steps": 38150, "loss": 0.1418, "lr": 2.9694137516884353e-06, "epoch": 8.589777195281782, "percentage": 85.9, "elapsed_time": "0:55:19", "remaining_time": "0:09:04", "throughput": 2648.15, "total_tokens": 8789984} {"current_steps": 32775, "total_steps": 38150, "loss": 0.1859, "lr": 2.9640096548094992e-06, "epoch": 8.591087811271297, "percentage": 85.91, "elapsed_time": "0:55:19", "remaining_time": "0:09:04", "throughput": 2648.29, "total_tokens": 8791792} {"current_steps": 32780, "total_steps": 38150, "loss": 0.1592, "lr": 2.958610170025275e-06, "epoch": 8.592398427260813, "percentage": 85.92, "elapsed_time": "0:55:20", "remaining_time": "0:09:03", "throughput": 2648.31, "total_tokens": 8793152} {"current_steps": 32785, "total_steps": 38150, "loss": 0.1679, "lr": 2.9532152984658446e-06, "epoch": 8.593709043250328, "percentage": 85.94, "elapsed_time": "0:55:20", "remaining_time": "0:09:03", "throughput": 2648.33, "total_tokens": 8794432} {"current_steps": 32790, "total_steps": 38150, "loss": 0.0785, "lr": 2.9478250412603657e-06, "epoch": 8.595019659239842, "percentage": 85.95, "elapsed_time": "0:55:21", "remaining_time": "0:09:02", "throughput": 2648.34, "total_tokens": 8795648} {"current_steps": 32795, "total_steps": 38150, "loss": 0.0916, "lr": 2.942439399537e-06, "epoch": 8.596330275229358, "percentage": 85.96, "elapsed_time": "0:55:21", "remaining_time": "0:09:02", "throughput": 2648.31, "total_tokens": 8796640} {"current_steps": 32800, "total_steps": 38150, "loss": 0.3351, "lr": 2.9370583744229572e-06, "epoch": 8.597640891218873, "percentage": 85.98, "elapsed_time": "0:55:22", "remaining_time": "0:09:01", "throughput": 2648.3, "total_tokens": 8797744} {"current_steps": 32805, "total_steps": 38150, "loss": 0.1012, "lr": 2.931681967044475e-06, "epoch": 8.598951507208389, "percentage": 85.99, "elapsed_time": "0:55:22", "remaining_time": "0:09:01", "throughput": 2648.29, "total_tokens": 8798800} {"current_steps": 32810, "total_steps": 38150, "loss": 0.1483, "lr": 2.9263101785268254e-06, "epoch": 8.600262123197902, "percentage": 86.0, "elapsed_time": "0:55:22", "remaining_time": "0:09:00", "throughput": 2648.31, "total_tokens": 8800016} {"current_steps": 32815, "total_steps": 38150, "loss": 0.1489, "lr": 2.9209430099943204e-06, "epoch": 8.601572739187418, "percentage": 86.02, "elapsed_time": "0:55:23", "remaining_time": "0:09:00", "throughput": 2648.38, "total_tokens": 8801488} {"current_steps": 32820, "total_steps": 38150, "loss": 0.143, "lr": 2.915580462570289e-06, "epoch": 8.602883355176933, "percentage": 86.03, "elapsed_time": "0:55:23", "remaining_time": "0:08:59", "throughput": 2648.38, "total_tokens": 8802592} {"current_steps": 32825, "total_steps": 38150, "loss": 0.2114, "lr": 2.910222537377108e-06, "epoch": 8.604193971166449, "percentage": 86.04, "elapsed_time": "0:55:24", "remaining_time": "0:08:59", "throughput": 2648.42, "total_tokens": 8803872} {"current_steps": 32830, "total_steps": 38150, "loss": 0.1366, "lr": 2.904869235536181e-06, "epoch": 8.605504587155963, "percentage": 86.06, "elapsed_time": "0:55:24", "remaining_time": "0:08:58", "throughput": 2648.41, "total_tokens": 8805008} {"current_steps": 32835, "total_steps": 38150, "loss": 0.0634, "lr": 2.8995205581679452e-06, "epoch": 8.606815203145478, "percentage": 86.07, "elapsed_time": "0:55:25", "remaining_time": "0:08:58", "throughput": 2648.37, "total_tokens": 8806000} {"current_steps": 32840, "total_steps": 38150, "loss": 0.131, "lr": 2.8941765063918657e-06, "epoch": 8.608125819134994, "percentage": 86.08, "elapsed_time": "0:55:25", "remaining_time": "0:08:57", "throughput": 2648.38, "total_tokens": 8807248} {"current_steps": 32845, "total_steps": 38150, "loss": 0.1142, "lr": 2.888837081326451e-06, "epoch": 8.609436435124508, "percentage": 86.09, "elapsed_time": "0:55:25", "remaining_time": "0:08:57", "throughput": 2648.47, "total_tokens": 8808752} {"current_steps": 32850, "total_steps": 38150, "loss": 0.093, "lr": 2.8835022840892373e-06, "epoch": 8.610747051114023, "percentage": 86.11, "elapsed_time": "0:55:26", "remaining_time": "0:08:56", "throughput": 2648.53, "total_tokens": 8810096} {"current_steps": 32855, "total_steps": 38150, "loss": 0.3095, "lr": 2.8781721157967734e-06, "epoch": 8.612057667103539, "percentage": 86.12, "elapsed_time": "0:55:26", "remaining_time": "0:08:56", "throughput": 2648.68, "total_tokens": 8812144} {"current_steps": 32860, "total_steps": 38150, "loss": 0.2331, "lr": 2.872846577564664e-06, "epoch": 8.613368283093054, "percentage": 86.13, "elapsed_time": "0:55:27", "remaining_time": "0:08:55", "throughput": 2648.66, "total_tokens": 8813200} {"current_steps": 32865, "total_steps": 38150, "loss": 0.1637, "lr": 2.8675256705075343e-06, "epoch": 8.614678899082568, "percentage": 86.15, "elapsed_time": "0:55:27", "remaining_time": "0:08:55", "throughput": 2648.7, "total_tokens": 8814496} {"current_steps": 32870, "total_steps": 38150, "loss": 0.2116, "lr": 2.8622093957390377e-06, "epoch": 8.615989515072084, "percentage": 86.16, "elapsed_time": "0:55:28", "remaining_time": "0:08:54", "throughput": 2648.7, "total_tokens": 8815600} {"current_steps": 32875, "total_steps": 38150, "loss": 0.2577, "lr": 2.856897754371865e-06, "epoch": 8.617300131061599, "percentage": 86.17, "elapsed_time": "0:55:28", "remaining_time": "0:08:54", "throughput": 2648.69, "total_tokens": 8816672} {"current_steps": 32880, "total_steps": 38150, "loss": 0.1181, "lr": 2.8515907475177293e-06, "epoch": 8.618610747051115, "percentage": 86.19, "elapsed_time": "0:55:29", "remaining_time": "0:08:53", "throughput": 2648.68, "total_tokens": 8817824} {"current_steps": 32885, "total_steps": 38150, "loss": 0.1046, "lr": 2.8462883762873842e-06, "epoch": 8.619921363040628, "percentage": 86.2, "elapsed_time": "0:55:29", "remaining_time": "0:08:53", "throughput": 2648.68, "total_tokens": 8819072} {"current_steps": 32890, "total_steps": 38150, "loss": 0.0862, "lr": 2.8409906417906e-06, "epoch": 8.621231979030144, "percentage": 86.21, "elapsed_time": "0:55:30", "remaining_time": "0:08:52", "throughput": 2648.69, "total_tokens": 8820272} {"current_steps": 32895, "total_steps": 38150, "loss": 0.1378, "lr": 2.8356975451361873e-06, "epoch": 8.62254259501966, "percentage": 86.23, "elapsed_time": "0:55:30", "remaining_time": "0:08:52", "throughput": 2648.72, "total_tokens": 8821520} {"current_steps": 32900, "total_steps": 38150, "loss": 0.2127, "lr": 2.8304090874319843e-06, "epoch": 8.623853211009175, "percentage": 86.24, "elapsed_time": "0:55:30", "remaining_time": "0:08:51", "throughput": 2648.75, "total_tokens": 8822768} {"current_steps": 32905, "total_steps": 38150, "loss": 0.1673, "lr": 2.8251252697848505e-06, "epoch": 8.625163826998689, "percentage": 86.25, "elapsed_time": "0:55:31", "remaining_time": "0:08:51", "throughput": 2648.85, "total_tokens": 8824384} {"current_steps": 32910, "total_steps": 38150, "loss": 0.2669, "lr": 2.819846093300682e-06, "epoch": 8.626474442988204, "percentage": 86.26, "elapsed_time": "0:55:31", "remaining_time": "0:08:50", "throughput": 2648.88, "total_tokens": 8825712} {"current_steps": 32915, "total_steps": 38150, "loss": 0.1284, "lr": 2.814571559084403e-06, "epoch": 8.62778505897772, "percentage": 86.28, "elapsed_time": "0:55:32", "remaining_time": "0:08:49", "throughput": 2648.84, "total_tokens": 8826688} {"current_steps": 32920, "total_steps": 38150, "loss": 0.1911, "lr": 2.8093016682399636e-06, "epoch": 8.629095674967235, "percentage": 86.29, "elapsed_time": "0:55:32", "remaining_time": "0:08:49", "throughput": 2648.89, "total_tokens": 8828144} {"current_steps": 32925, "total_steps": 38150, "loss": 0.1773, "lr": 2.804036421870343e-06, "epoch": 8.63040629095675, "percentage": 86.3, "elapsed_time": "0:55:33", "remaining_time": "0:08:48", "throughput": 2649.0, "total_tokens": 8829856} {"current_steps": 32930, "total_steps": 38150, "loss": 0.1039, "lr": 2.798775821077551e-06, "epoch": 8.631716906946265, "percentage": 86.32, "elapsed_time": "0:55:33", "remaining_time": "0:08:48", "throughput": 2649.08, "total_tokens": 8831280} {"current_steps": 32935, "total_steps": 38150, "loss": 0.2078, "lr": 2.7935198669626155e-06, "epoch": 8.63302752293578, "percentage": 86.33, "elapsed_time": "0:55:34", "remaining_time": "0:08:47", "throughput": 2649.15, "total_tokens": 8832688} {"current_steps": 32940, "total_steps": 38150, "loss": 0.1128, "lr": 2.788268560625601e-06, "epoch": 8.634338138925294, "percentage": 86.34, "elapsed_time": "0:55:34", "remaining_time": "0:08:47", "throughput": 2649.17, "total_tokens": 8833952} {"current_steps": 32945, "total_steps": 38150, "loss": 0.1981, "lr": 2.7830219031655973e-06, "epoch": 8.63564875491481, "percentage": 86.36, "elapsed_time": "0:55:35", "remaining_time": "0:08:46", "throughput": 2649.25, "total_tokens": 8835504} {"current_steps": 32950, "total_steps": 38150, "loss": 0.1988, "lr": 2.777779895680721e-06, "epoch": 8.636959370904325, "percentage": 86.37, "elapsed_time": "0:55:35", "remaining_time": "0:08:46", "throughput": 2649.33, "total_tokens": 8837216} {"current_steps": 32955, "total_steps": 38150, "loss": 0.1576, "lr": 2.772542539268114e-06, "epoch": 8.63826998689384, "percentage": 86.38, "elapsed_time": "0:55:36", "remaining_time": "0:08:45", "throughput": 2649.29, "total_tokens": 8838176} {"current_steps": 32960, "total_steps": 38150, "loss": 0.1484, "lr": 2.7673098350239485e-06, "epoch": 8.639580602883354, "percentage": 86.4, "elapsed_time": "0:55:36", "remaining_time": "0:08:45", "throughput": 2649.32, "total_tokens": 8839440} {"current_steps": 32965, "total_steps": 38150, "loss": 0.1276, "lr": 2.7620817840434216e-06, "epoch": 8.64089121887287, "percentage": 86.41, "elapsed_time": "0:55:36", "remaining_time": "0:08:44", "throughput": 2649.36, "total_tokens": 8840688} {"current_steps": 32970, "total_steps": 38150, "loss": 0.185, "lr": 2.756858387420758e-06, "epoch": 8.642201834862385, "percentage": 86.42, "elapsed_time": "0:55:37", "remaining_time": "0:08:44", "throughput": 2649.33, "total_tokens": 8841680} {"current_steps": 32975, "total_steps": 38150, "loss": 0.1922, "lr": 2.7516396462491934e-06, "epoch": 8.643512450851901, "percentage": 86.44, "elapsed_time": "0:55:37", "remaining_time": "0:08:43", "throughput": 2649.39, "total_tokens": 8843120} {"current_steps": 32980, "total_steps": 38150, "loss": 0.1164, "lr": 2.7464255616210106e-06, "epoch": 8.644823066841415, "percentage": 86.45, "elapsed_time": "0:55:38", "remaining_time": "0:08:43", "throughput": 2649.5, "total_tokens": 8844752} {"current_steps": 32985, "total_steps": 38150, "loss": 0.207, "lr": 2.7412161346275057e-06, "epoch": 8.64613368283093, "percentage": 86.46, "elapsed_time": "0:55:38", "remaining_time": "0:08:42", "throughput": 2649.5, "total_tokens": 8845856} {"current_steps": 32990, "total_steps": 38150, "loss": 0.2736, "lr": 2.7360113663590036e-06, "epoch": 8.647444298820446, "percentage": 86.47, "elapsed_time": "0:55:39", "remaining_time": "0:08:42", "throughput": 2649.49, "total_tokens": 8846976} {"current_steps": 32995, "total_steps": 38150, "loss": 0.2388, "lr": 2.7308112579048555e-06, "epoch": 8.648754914809961, "percentage": 86.49, "elapsed_time": "0:55:39", "remaining_time": "0:08:41", "throughput": 2649.64, "total_tokens": 8848832} {"current_steps": 33000, "total_steps": 38150, "loss": 0.1528, "lr": 2.7256158103534298e-06, "epoch": 8.650065530799475, "percentage": 86.5, "elapsed_time": "0:55:40", "remaining_time": "0:08:41", "throughput": 2649.66, "total_tokens": 8850080} {"current_steps": 33005, "total_steps": 38150, "loss": 0.1565, "lr": 2.7204250247921308e-06, "epoch": 8.65137614678899, "percentage": 86.51, "elapsed_time": "0:55:40", "remaining_time": "0:08:40", "throughput": 2649.72, "total_tokens": 8851552} {"current_steps": 33010, "total_steps": 38150, "loss": 0.1936, "lr": 2.7152389023073766e-06, "epoch": 8.652686762778506, "percentage": 86.53, "elapsed_time": "0:55:40", "remaining_time": "0:08:40", "throughput": 2649.73, "total_tokens": 8852688} {"current_steps": 33015, "total_steps": 38150, "loss": 0.1263, "lr": 2.710057443984615e-06, "epoch": 8.653997378768022, "percentage": 86.54, "elapsed_time": "0:55:41", "remaining_time": "0:08:39", "throughput": 2649.8, "total_tokens": 8854176} {"current_steps": 33020, "total_steps": 38150, "loss": 0.1609, "lr": 2.7048806509083146e-06, "epoch": 8.655307994757536, "percentage": 86.55, "elapsed_time": "0:55:41", "remaining_time": "0:08:39", "throughput": 2649.85, "total_tokens": 8855584} {"current_steps": 33025, "total_steps": 38150, "loss": 0.2143, "lr": 2.6997085241619728e-06, "epoch": 8.656618610747051, "percentage": 86.57, "elapsed_time": "0:55:42", "remaining_time": "0:08:38", "throughput": 2649.91, "total_tokens": 8857056} {"current_steps": 33030, "total_steps": 38150, "loss": 0.2245, "lr": 2.6945410648281044e-06, "epoch": 8.657929226736567, "percentage": 86.58, "elapsed_time": "0:55:42", "remaining_time": "0:08:38", "throughput": 2649.95, "total_tokens": 8858304} {"current_steps": 33035, "total_steps": 38150, "loss": 0.1428, "lr": 2.6893782739882523e-06, "epoch": 8.65923984272608, "percentage": 86.59, "elapsed_time": "0:55:43", "remaining_time": "0:08:37", "throughput": 2650.03, "total_tokens": 8859936} {"current_steps": 33040, "total_steps": 38150, "loss": 0.1372, "lr": 2.6842201527229743e-06, "epoch": 8.660550458715596, "percentage": 86.61, "elapsed_time": "0:55:43", "remaining_time": "0:08:37", "throughput": 2650.0, "total_tokens": 8860976} {"current_steps": 33045, "total_steps": 38150, "loss": 0.0847, "lr": 2.6790667021118626e-06, "epoch": 8.661861074705111, "percentage": 86.62, "elapsed_time": "0:55:44", "remaining_time": "0:08:36", "throughput": 2649.92, "total_tokens": 8861792} {"current_steps": 33050, "total_steps": 38150, "loss": 0.3054, "lr": 2.6739179232335264e-06, "epoch": 8.663171690694627, "percentage": 86.63, "elapsed_time": "0:55:44", "remaining_time": "0:08:36", "throughput": 2649.91, "total_tokens": 8862880} {"current_steps": 33055, "total_steps": 38150, "loss": 0.2312, "lr": 2.6687738171655873e-06, "epoch": 8.66448230668414, "percentage": 86.64, "elapsed_time": "0:55:45", "remaining_time": "0:08:35", "throughput": 2649.89, "total_tokens": 8863952} {"current_steps": 33060, "total_steps": 38150, "loss": 0.2357, "lr": 2.6636343849847033e-06, "epoch": 8.665792922673656, "percentage": 86.66, "elapsed_time": "0:55:45", "remaining_time": "0:08:35", "throughput": 2650.0, "total_tokens": 8865632} {"current_steps": 33065, "total_steps": 38150, "loss": 0.1063, "lr": 2.6584996277665475e-06, "epoch": 8.667103538663172, "percentage": 86.67, "elapsed_time": "0:55:45", "remaining_time": "0:08:34", "throughput": 2650.08, "total_tokens": 8867136} {"current_steps": 33070, "total_steps": 38150, "loss": 0.1594, "lr": 2.653369546585813e-06, "epoch": 8.668414154652687, "percentage": 86.68, "elapsed_time": "0:55:46", "remaining_time": "0:08:34", "throughput": 2650.08, "total_tokens": 8868288} {"current_steps": 33075, "total_steps": 38150, "loss": 0.098, "lr": 2.6482441425162235e-06, "epoch": 8.669724770642201, "percentage": 86.7, "elapsed_time": "0:55:46", "remaining_time": "0:08:33", "throughput": 2650.11, "total_tokens": 8869584} {"current_steps": 33080, "total_steps": 38150, "loss": 0.1694, "lr": 2.6431234166305135e-06, "epoch": 8.671035386631717, "percentage": 86.71, "elapsed_time": "0:55:47", "remaining_time": "0:08:33", "throughput": 2650.21, "total_tokens": 8871216} {"current_steps": 33085, "total_steps": 38150, "loss": 0.1065, "lr": 2.6380073700004504e-06, "epoch": 8.672346002621232, "percentage": 86.72, "elapsed_time": "0:55:47", "remaining_time": "0:08:32", "throughput": 2650.16, "total_tokens": 8872160} {"current_steps": 33090, "total_steps": 38150, "loss": 0.1169, "lr": 2.6328960036967996e-06, "epoch": 8.673656618610748, "percentage": 86.74, "elapsed_time": "0:55:48", "remaining_time": "0:08:32", "throughput": 2650.26, "total_tokens": 8873792} {"current_steps": 33095, "total_steps": 38150, "loss": 0.2496, "lr": 2.627789318789367e-06, "epoch": 8.674967234600262, "percentage": 86.75, "elapsed_time": "0:55:48", "remaining_time": "0:08:31", "throughput": 2650.26, "total_tokens": 8874960} {"current_steps": 33100, "total_steps": 38150, "loss": 0.1837, "lr": 2.6226873163469752e-06, "epoch": 8.676277850589777, "percentage": 86.76, "elapsed_time": "0:55:49", "remaining_time": "0:08:30", "throughput": 2650.3, "total_tokens": 8876304} {"current_steps": 33105, "total_steps": 38150, "loss": 0.0649, "lr": 2.6175899974374614e-06, "epoch": 8.677588466579293, "percentage": 86.78, "elapsed_time": "0:55:49", "remaining_time": "0:08:30", "throughput": 2650.27, "total_tokens": 8877312} {"current_steps": 33110, "total_steps": 38150, "loss": 0.1572, "lr": 2.6124973631276888e-06, "epoch": 8.678899082568808, "percentage": 86.79, "elapsed_time": "0:55:50", "remaining_time": "0:08:29", "throughput": 2650.3, "total_tokens": 8878544} {"current_steps": 33115, "total_steps": 38150, "loss": 0.293, "lr": 2.607409414483536e-06, "epoch": 8.680209698558322, "percentage": 86.8, "elapsed_time": "0:55:50", "remaining_time": "0:08:29", "throughput": 2650.23, "total_tokens": 8879424} {"current_steps": 33120, "total_steps": 38150, "loss": 0.0961, "lr": 2.6023261525699003e-06, "epoch": 8.681520314547837, "percentage": 86.82, "elapsed_time": "0:55:50", "remaining_time": "0:08:28", "throughput": 2650.25, "total_tokens": 8880592} {"current_steps": 33125, "total_steps": 38150, "loss": 0.3356, "lr": 2.597247578450701e-06, "epoch": 8.682830930537353, "percentage": 86.83, "elapsed_time": "0:55:51", "remaining_time": "0:08:28", "throughput": 2650.36, "total_tokens": 8882272} {"current_steps": 33130, "total_steps": 38150, "loss": 0.1241, "lr": 2.592173693188876e-06, "epoch": 8.684141546526867, "percentage": 86.84, "elapsed_time": "0:55:51", "remaining_time": "0:08:27", "throughput": 2650.32, "total_tokens": 8883248} {"current_steps": 33135, "total_steps": 38150, "loss": 0.1491, "lr": 2.5871044978463764e-06, "epoch": 8.685452162516382, "percentage": 86.85, "elapsed_time": "0:55:52", "remaining_time": "0:08:27", "throughput": 2650.39, "total_tokens": 8884784} {"current_steps": 33140, "total_steps": 38150, "loss": 0.2578, "lr": 2.582039993484181e-06, "epoch": 8.686762778505898, "percentage": 86.87, "elapsed_time": "0:55:52", "remaining_time": "0:08:26", "throughput": 2650.52, "total_tokens": 8886576} {"current_steps": 33145, "total_steps": 38150, "loss": 0.1208, "lr": 2.576980181162278e-06, "epoch": 8.688073394495413, "percentage": 86.88, "elapsed_time": "0:55:53", "remaining_time": "0:08:26", "throughput": 2650.49, "total_tokens": 8887616} {"current_steps": 33150, "total_steps": 38150, "loss": 0.1706, "lr": 2.571925061939681e-06, "epoch": 8.689384010484927, "percentage": 86.89, "elapsed_time": "0:55:53", "remaining_time": "0:08:25", "throughput": 2650.58, "total_tokens": 8889232} {"current_steps": 33155, "total_steps": 38150, "loss": 0.2035, "lr": 2.566874636874414e-06, "epoch": 8.690694626474443, "percentage": 86.91, "elapsed_time": "0:55:54", "remaining_time": "0:08:25", "throughput": 2650.6, "total_tokens": 8890432} {"current_steps": 33160, "total_steps": 38150, "loss": 0.2258, "lr": 2.561828907023525e-06, "epoch": 8.692005242463958, "percentage": 86.92, "elapsed_time": "0:55:54", "remaining_time": "0:08:24", "throughput": 2650.73, "total_tokens": 8892160} {"current_steps": 33165, "total_steps": 38150, "loss": 0.148, "lr": 2.556787873443081e-06, "epoch": 8.693315858453474, "percentage": 86.93, "elapsed_time": "0:55:55", "remaining_time": "0:08:24", "throughput": 2650.75, "total_tokens": 8893360} {"current_steps": 33170, "total_steps": 38150, "loss": 0.1045, "lr": 2.5517515371881516e-06, "epoch": 8.694626474442988, "percentage": 86.95, "elapsed_time": "0:55:55", "remaining_time": "0:08:23", "throughput": 2650.87, "total_tokens": 8895104} {"current_steps": 33175, "total_steps": 38150, "loss": 0.0835, "lr": 2.5467198993128355e-06, "epoch": 8.695937090432503, "percentage": 86.96, "elapsed_time": "0:55:55", "remaining_time": "0:08:23", "throughput": 2650.89, "total_tokens": 8896304} {"current_steps": 33180, "total_steps": 38150, "loss": 0.2342, "lr": 2.541692960870251e-06, "epoch": 8.697247706422019, "percentage": 86.97, "elapsed_time": "0:55:56", "remaining_time": "0:08:22", "throughput": 2650.89, "total_tokens": 8897440} {"current_steps": 33185, "total_steps": 38150, "loss": 0.1456, "lr": 2.536670722912518e-06, "epoch": 8.698558322411534, "percentage": 86.99, "elapsed_time": "0:55:56", "remaining_time": "0:08:22", "throughput": 2650.92, "total_tokens": 8898736} {"current_steps": 33190, "total_steps": 38150, "loss": 0.1, "lr": 2.5316531864907955e-06, "epoch": 8.699868938401048, "percentage": 87.0, "elapsed_time": "0:55:57", "remaining_time": "0:08:21", "throughput": 2650.86, "total_tokens": 8899632} {"current_steps": 33195, "total_steps": 38150, "loss": 0.1566, "lr": 2.526640352655238e-06, "epoch": 8.701179554390563, "percentage": 87.01, "elapsed_time": "0:55:57", "remaining_time": "0:08:21", "throughput": 2650.87, "total_tokens": 8900848} {"current_steps": 33200, "total_steps": 38150, "loss": 0.0523, "lr": 2.5216322224550226e-06, "epoch": 8.702490170380079, "percentage": 87.02, "elapsed_time": "0:55:58", "remaining_time": "0:08:20", "throughput": 2650.83, "total_tokens": 8901808} {"current_steps": 33205, "total_steps": 38150, "loss": 0.1004, "lr": 2.51662879693835e-06, "epoch": 8.703800786369595, "percentage": 87.04, "elapsed_time": "0:55:58", "remaining_time": "0:08:20", "throughput": 2650.83, "total_tokens": 8903008} {"current_steps": 33210, "total_steps": 38150, "loss": 0.2103, "lr": 2.511630077152416e-06, "epoch": 8.705111402359108, "percentage": 87.05, "elapsed_time": "0:55:59", "remaining_time": "0:08:19", "throughput": 2650.84, "total_tokens": 8904192} {"current_steps": 33215, "total_steps": 38150, "loss": 0.198, "lr": 2.50663606414345e-06, "epoch": 8.706422018348624, "percentage": 87.06, "elapsed_time": "0:55:59", "remaining_time": "0:08:19", "throughput": 2650.91, "total_tokens": 8905696} {"current_steps": 33220, "total_steps": 38150, "loss": 0.3192, "lr": 2.501646758956691e-06, "epoch": 8.70773263433814, "percentage": 87.08, "elapsed_time": "0:55:59", "remaining_time": "0:08:18", "throughput": 2651.05, "total_tokens": 8907440} {"current_steps": 33225, "total_steps": 38150, "loss": 0.2182, "lr": 2.49666216263639e-06, "epoch": 8.709043250327653, "percentage": 87.09, "elapsed_time": "0:56:00", "remaining_time": "0:08:18", "throughput": 2651.04, "total_tokens": 8908544} {"current_steps": 33230, "total_steps": 38150, "loss": 0.1102, "lr": 2.491682276225818e-06, "epoch": 8.710353866317169, "percentage": 87.1, "elapsed_time": "0:56:00", "remaining_time": "0:08:17", "throughput": 2651.06, "total_tokens": 8909744} {"current_steps": 33235, "total_steps": 38150, "loss": 0.2193, "lr": 2.486707100767252e-06, "epoch": 8.711664482306684, "percentage": 87.12, "elapsed_time": "0:56:01", "remaining_time": "0:08:17", "throughput": 2651.1, "total_tokens": 8911040} {"current_steps": 33240, "total_steps": 38150, "loss": 0.1208, "lr": 2.4817366373019902e-06, "epoch": 8.7129750982962, "percentage": 87.13, "elapsed_time": "0:56:01", "remaining_time": "0:08:16", "throughput": 2651.07, "total_tokens": 8912144} {"current_steps": 33245, "total_steps": 38150, "loss": 0.1554, "lr": 2.4767708868703414e-06, "epoch": 8.714285714285714, "percentage": 87.14, "elapsed_time": "0:56:02", "remaining_time": "0:08:16", "throughput": 2651.08, "total_tokens": 8913296} {"current_steps": 33250, "total_steps": 38150, "loss": 0.1257, "lr": 2.4718098505116305e-06, "epoch": 8.715596330275229, "percentage": 87.16, "elapsed_time": "0:56:02", "remaining_time": "0:08:15", "throughput": 2651.09, "total_tokens": 8914464} {"current_steps": 33255, "total_steps": 38150, "loss": 0.2616, "lr": 2.4668535292641904e-06, "epoch": 8.716906946264745, "percentage": 87.17, "elapsed_time": "0:56:03", "remaining_time": "0:08:15", "throughput": 2651.2, "total_tokens": 8916016} {"current_steps": 33260, "total_steps": 38150, "loss": 0.1358, "lr": 2.4619019241653716e-06, "epoch": 8.71821756225426, "percentage": 87.18, "elapsed_time": "0:56:03", "remaining_time": "0:08:14", "throughput": 2651.25, "total_tokens": 8917328} {"current_steps": 33265, "total_steps": 38150, "loss": 0.0946, "lr": 2.4569550362515403e-06, "epoch": 8.719528178243774, "percentage": 87.2, "elapsed_time": "0:56:03", "remaining_time": "0:08:14", "throughput": 2651.38, "total_tokens": 8919232} {"current_steps": 33270, "total_steps": 38150, "loss": 0.1381, "lr": 2.452012866558065e-06, "epoch": 8.72083879423329, "percentage": 87.21, "elapsed_time": "0:56:04", "remaining_time": "0:08:13", "throughput": 2651.42, "total_tokens": 8920512} {"current_steps": 33275, "total_steps": 38150, "loss": 0.0961, "lr": 2.4470754161193406e-06, "epoch": 8.722149410222805, "percentage": 87.22, "elapsed_time": "0:56:04", "remaining_time": "0:08:12", "throughput": 2651.42, "total_tokens": 8921680} {"current_steps": 33280, "total_steps": 38150, "loss": 0.3055, "lr": 2.4421426859687597e-06, "epoch": 8.72346002621232, "percentage": 87.23, "elapsed_time": "0:56:05", "remaining_time": "0:08:12", "throughput": 2651.46, "total_tokens": 8923056} {"current_steps": 33285, "total_steps": 38150, "loss": 0.0759, "lr": 2.437214677138744e-06, "epoch": 8.724770642201834, "percentage": 87.25, "elapsed_time": "0:56:05", "remaining_time": "0:08:11", "throughput": 2651.4, "total_tokens": 8923968} {"current_steps": 33290, "total_steps": 38150, "loss": 0.1588, "lr": 2.432291390660707e-06, "epoch": 8.72608125819135, "percentage": 87.26, "elapsed_time": "0:56:06", "remaining_time": "0:08:11", "throughput": 2651.44, "total_tokens": 8925248} {"current_steps": 33295, "total_steps": 38150, "loss": 0.1407, "lr": 2.427372827565086e-06, "epoch": 8.727391874180865, "percentage": 87.27, "elapsed_time": "0:56:06", "remaining_time": "0:08:10", "throughput": 2651.42, "total_tokens": 8926320} {"current_steps": 33300, "total_steps": 38150, "loss": 0.1452, "lr": 2.4224589888813263e-06, "epoch": 8.728702490170381, "percentage": 87.29, "elapsed_time": "0:56:07", "remaining_time": "0:08:10", "throughput": 2651.48, "total_tokens": 8927840} {"current_steps": 33305, "total_steps": 38150, "loss": 0.2224, "lr": 2.4175498756378924e-06, "epoch": 8.730013106159895, "percentage": 87.3, "elapsed_time": "0:56:07", "remaining_time": "0:08:09", "throughput": 2651.48, "total_tokens": 8929024} {"current_steps": 33310, "total_steps": 38150, "loss": 0.2125, "lr": 2.41264548886225e-06, "epoch": 8.73132372214941, "percentage": 87.31, "elapsed_time": "0:56:07", "remaining_time": "0:08:09", "throughput": 2651.51, "total_tokens": 8930240} {"current_steps": 33315, "total_steps": 38150, "loss": 0.0564, "lr": 2.407745829580882e-06, "epoch": 8.732634338138926, "percentage": 87.33, "elapsed_time": "0:56:08", "remaining_time": "0:08:08", "throughput": 2651.49, "total_tokens": 8931280} {"current_steps": 33320, "total_steps": 38150, "loss": 0.142, "lr": 2.402850898819278e-06, "epoch": 8.73394495412844, "percentage": 87.34, "elapsed_time": "0:56:08", "remaining_time": "0:08:08", "throughput": 2651.51, "total_tokens": 8932480} {"current_steps": 33325, "total_steps": 38150, "loss": 0.3063, "lr": 2.397960697601931e-06, "epoch": 8.735255570117955, "percentage": 87.35, "elapsed_time": "0:56:09", "remaining_time": "0:08:07", "throughput": 2651.61, "total_tokens": 8934048} {"current_steps": 33330, "total_steps": 38150, "loss": 0.2495, "lr": 2.393075226952357e-06, "epoch": 8.73656618610747, "percentage": 87.37, "elapsed_time": "0:56:09", "remaining_time": "0:08:07", "throughput": 2651.7, "total_tokens": 8935520} {"current_steps": 33335, "total_steps": 38150, "loss": 0.1862, "lr": 2.388194487893078e-06, "epoch": 8.737876802096986, "percentage": 87.38, "elapsed_time": "0:56:10", "remaining_time": "0:08:06", "throughput": 2651.83, "total_tokens": 8937248} {"current_steps": 33340, "total_steps": 38150, "loss": 0.1755, "lr": 2.3833184814456204e-06, "epoch": 8.7391874180865, "percentage": 87.39, "elapsed_time": "0:56:10", "remaining_time": "0:08:06", "throughput": 2651.89, "total_tokens": 8938688} {"current_steps": 33345, "total_steps": 38150, "loss": 0.2125, "lr": 2.378447208630527e-06, "epoch": 8.740498034076015, "percentage": 87.4, "elapsed_time": "0:56:11", "remaining_time": "0:08:05", "throughput": 2651.96, "total_tokens": 8940176} {"current_steps": 33350, "total_steps": 38150, "loss": 0.2049, "lr": 2.373580670467343e-06, "epoch": 8.741808650065531, "percentage": 87.42, "elapsed_time": "0:56:11", "remaining_time": "0:08:05", "throughput": 2652.02, "total_tokens": 8941568} {"current_steps": 33355, "total_steps": 38150, "loss": 0.2466, "lr": 2.3687188679746315e-06, "epoch": 8.743119266055047, "percentage": 87.43, "elapsed_time": "0:56:12", "remaining_time": "0:08:04", "throughput": 2652.13, "total_tokens": 8943376} {"current_steps": 33360, "total_steps": 38150, "loss": 0.1297, "lr": 2.363861802169959e-06, "epoch": 8.74442988204456, "percentage": 87.44, "elapsed_time": "0:56:12", "remaining_time": "0:08:04", "throughput": 2652.2, "total_tokens": 8944832} {"current_steps": 33365, "total_steps": 38150, "loss": 0.2185, "lr": 2.3590094740698955e-06, "epoch": 8.745740498034076, "percentage": 87.46, "elapsed_time": "0:56:13", "remaining_time": "0:08:03", "throughput": 2652.27, "total_tokens": 8946368} {"current_steps": 33370, "total_steps": 38150, "loss": 0.1225, "lr": 2.3541618846900316e-06, "epoch": 8.747051114023591, "percentage": 87.47, "elapsed_time": "0:56:13", "remaining_time": "0:08:03", "throughput": 2652.35, "total_tokens": 8947904} {"current_steps": 33375, "total_steps": 38150, "loss": 0.1979, "lr": 2.3493190350449557e-06, "epoch": 8.748361730013107, "percentage": 87.48, "elapsed_time": "0:56:14", "remaining_time": "0:08:02", "throughput": 2652.39, "total_tokens": 8949168} {"current_steps": 33380, "total_steps": 38150, "loss": 0.2495, "lr": 2.3444809261482653e-06, "epoch": 8.74967234600262, "percentage": 87.5, "elapsed_time": "0:56:14", "remaining_time": "0:08:02", "throughput": 2652.52, "total_tokens": 8950880} {"current_steps": 33385, "total_steps": 38150, "loss": 0.2513, "lr": 2.3396475590125753e-06, "epoch": 8.750982961992136, "percentage": 87.51, "elapsed_time": "0:56:15", "remaining_time": "0:08:01", "throughput": 2652.64, "total_tokens": 8952688} {"current_steps": 33390, "total_steps": 38150, "loss": 0.233, "lr": 2.334818934649494e-06, "epoch": 8.752293577981652, "percentage": 87.52, "elapsed_time": "0:56:15", "remaining_time": "0:08:01", "throughput": 2652.74, "total_tokens": 8954448} {"current_steps": 33395, "total_steps": 38150, "loss": 0.1647, "lr": 2.3299950540696504e-06, "epoch": 8.753604193971167, "percentage": 87.54, "elapsed_time": "0:56:15", "remaining_time": "0:08:00", "throughput": 2652.81, "total_tokens": 8955872} {"current_steps": 33400, "total_steps": 38150, "loss": 0.2053, "lr": 2.325175918282674e-06, "epoch": 8.754914809960681, "percentage": 87.55, "elapsed_time": "0:56:16", "remaining_time": "0:08:00", "throughput": 2652.96, "total_tokens": 8957840} {"current_steps": 33405, "total_steps": 38150, "loss": 0.2338, "lr": 2.3203615282971934e-06, "epoch": 8.756225425950197, "percentage": 87.56, "elapsed_time": "0:56:17", "remaining_time": "0:07:59", "throughput": 2653.0, "total_tokens": 8959216} {"current_steps": 33410, "total_steps": 38150, "loss": 0.1626, "lr": 2.315551885120859e-06, "epoch": 8.757536041939712, "percentage": 87.58, "elapsed_time": "0:56:17", "remaining_time": "0:07:59", "throughput": 2653.04, "total_tokens": 8960464} {"current_steps": 33415, "total_steps": 38150, "loss": 0.185, "lr": 2.3107469897603152e-06, "epoch": 8.758846657929226, "percentage": 87.59, "elapsed_time": "0:56:17", "remaining_time": "0:07:58", "throughput": 2653.02, "total_tokens": 8961536} {"current_steps": 33420, "total_steps": 38150, "loss": 0.0823, "lr": 2.305946843221224e-06, "epoch": 8.760157273918741, "percentage": 87.6, "elapsed_time": "0:56:18", "remaining_time": "0:07:58", "throughput": 2653.04, "total_tokens": 8962720} {"current_steps": 33425, "total_steps": 38150, "loss": 0.1084, "lr": 2.3011514465082485e-06, "epoch": 8.761467889908257, "percentage": 87.61, "elapsed_time": "0:56:18", "remaining_time": "0:07:57", "throughput": 2653.05, "total_tokens": 8963888} {"current_steps": 33430, "total_steps": 38150, "loss": 0.0673, "lr": 2.2963608006250555e-06, "epoch": 8.762778505897773, "percentage": 87.63, "elapsed_time": "0:56:19", "remaining_time": "0:07:57", "throughput": 2653.05, "total_tokens": 8965008} {"current_steps": 33435, "total_steps": 38150, "loss": 0.193, "lr": 2.2915749065743176e-06, "epoch": 8.764089121887286, "percentage": 87.64, "elapsed_time": "0:56:19", "remaining_time": "0:07:56", "throughput": 2653.09, "total_tokens": 8966432} {"current_steps": 33440, "total_steps": 38150, "loss": 0.2119, "lr": 2.2867937653577173e-06, "epoch": 8.765399737876802, "percentage": 87.65, "elapsed_time": "0:56:20", "remaining_time": "0:07:56", "throughput": 2653.23, "total_tokens": 8968304} {"current_steps": 33445, "total_steps": 38150, "loss": 0.2119, "lr": 2.282017377975934e-06, "epoch": 8.766710353866317, "percentage": 87.67, "elapsed_time": "0:56:20", "remaining_time": "0:07:55", "throughput": 2653.26, "total_tokens": 8969600} {"current_steps": 33450, "total_steps": 38150, "loss": 0.1749, "lr": 2.2772457454286578e-06, "epoch": 8.768020969855833, "percentage": 87.68, "elapsed_time": "0:56:21", "remaining_time": "0:07:55", "throughput": 2653.24, "total_tokens": 8970640} {"current_steps": 33455, "total_steps": 38150, "loss": 0.1605, "lr": 2.2724788687145865e-06, "epoch": 8.769331585845347, "percentage": 87.69, "elapsed_time": "0:56:21", "remaining_time": "0:07:54", "throughput": 2653.25, "total_tokens": 8971776} {"current_steps": 33460, "total_steps": 38150, "loss": 0.164, "lr": 2.2677167488314193e-06, "epoch": 8.770642201834862, "percentage": 87.71, "elapsed_time": "0:56:21", "remaining_time": "0:07:54", "throughput": 2653.28, "total_tokens": 8973136} {"current_steps": 33465, "total_steps": 38150, "loss": 0.2087, "lr": 2.2629593867758564e-06, "epoch": 8.771952817824378, "percentage": 87.72, "elapsed_time": "0:56:22", "remaining_time": "0:07:53", "throughput": 2653.34, "total_tokens": 8974544} {"current_steps": 33470, "total_steps": 38150, "loss": 0.1193, "lr": 2.258206783543601e-06, "epoch": 8.773263433813893, "percentage": 87.73, "elapsed_time": "0:56:22", "remaining_time": "0:07:53", "throughput": 2653.33, "total_tokens": 8975632} {"current_steps": 33475, "total_steps": 38150, "loss": 0.1578, "lr": 2.253458940129383e-06, "epoch": 8.774574049803407, "percentage": 87.75, "elapsed_time": "0:56:23", "remaining_time": "0:07:52", "throughput": 2653.35, "total_tokens": 8976800} {"current_steps": 33480, "total_steps": 38150, "loss": 0.0597, "lr": 2.2487158575269006e-06, "epoch": 8.775884665792923, "percentage": 87.76, "elapsed_time": "0:56:23", "remaining_time": "0:07:51", "throughput": 2653.36, "total_tokens": 8977952} {"current_steps": 33485, "total_steps": 38150, "loss": 0.1292, "lr": 2.243977536728878e-06, "epoch": 8.777195281782438, "percentage": 87.77, "elapsed_time": "0:56:24", "remaining_time": "0:07:51", "throughput": 2653.42, "total_tokens": 8979392} {"current_steps": 33490, "total_steps": 38150, "loss": 0.1213, "lr": 2.2392439787270373e-06, "epoch": 8.778505897771954, "percentage": 87.79, "elapsed_time": "0:56:24", "remaining_time": "0:07:50", "throughput": 2653.39, "total_tokens": 8980416} {"current_steps": 33495, "total_steps": 38150, "loss": 0.1381, "lr": 2.234515184512104e-06, "epoch": 8.779816513761467, "percentage": 87.8, "elapsed_time": "0:56:24", "remaining_time": "0:07:50", "throughput": 2653.46, "total_tokens": 8981904} {"current_steps": 33500, "total_steps": 38150, "loss": 0.1437, "lr": 2.229791155073807e-06, "epoch": 8.781127129750983, "percentage": 87.81, "elapsed_time": "0:56:25", "remaining_time": "0:07:49", "throughput": 2653.6, "total_tokens": 8983696} {"current_steps": 33505, "total_steps": 38150, "loss": 0.1312, "lr": 2.225071891400879e-06, "epoch": 8.782437745740499, "percentage": 87.82, "elapsed_time": "0:56:25", "remaining_time": "0:07:49", "throughput": 2653.58, "total_tokens": 8984752} {"current_steps": 33510, "total_steps": 38150, "loss": 0.1104, "lr": 2.2203573944810514e-06, "epoch": 8.783748361730012, "percentage": 87.84, "elapsed_time": "0:56:26", "remaining_time": "0:07:48", "throughput": 2653.61, "total_tokens": 8985984} {"current_steps": 33515, "total_steps": 38150, "loss": 0.1728, "lr": 2.21564766530106e-06, "epoch": 8.785058977719528, "percentage": 87.85, "elapsed_time": "0:56:26", "remaining_time": "0:07:48", "throughput": 2653.63, "total_tokens": 8987232} {"current_steps": 33520, "total_steps": 38150, "loss": 0.177, "lr": 2.210942704846647e-06, "epoch": 8.786369593709043, "percentage": 87.86, "elapsed_time": "0:56:27", "remaining_time": "0:07:47", "throughput": 2653.73, "total_tokens": 8988912} {"current_steps": 33525, "total_steps": 38150, "loss": 0.1181, "lr": 2.2062425141025465e-06, "epoch": 8.787680209698559, "percentage": 87.88, "elapsed_time": "0:56:27", "remaining_time": "0:07:47", "throughput": 2653.76, "total_tokens": 8990144} {"current_steps": 33530, "total_steps": 38150, "loss": 0.2455, "lr": 2.2015470940525003e-06, "epoch": 8.788990825688073, "percentage": 87.89, "elapsed_time": "0:56:28", "remaining_time": "0:07:46", "throughput": 2653.8, "total_tokens": 8991568} {"current_steps": 33535, "total_steps": 38150, "loss": 0.2568, "lr": 2.1968564456792573e-06, "epoch": 8.790301441677588, "percentage": 87.9, "elapsed_time": "0:56:28", "remaining_time": "0:07:46", "throughput": 2653.88, "total_tokens": 8993072} {"current_steps": 33540, "total_steps": 38150, "loss": 0.1453, "lr": 2.1921705699645607e-06, "epoch": 8.791612057667104, "percentage": 87.92, "elapsed_time": "0:56:29", "remaining_time": "0:07:45", "throughput": 2653.91, "total_tokens": 8994336} {"current_steps": 33545, "total_steps": 38150, "loss": 0.1371, "lr": 2.187489467889153e-06, "epoch": 8.79292267365662, "percentage": 87.93, "elapsed_time": "0:56:29", "remaining_time": "0:07:45", "throughput": 2653.96, "total_tokens": 8995632} {"current_steps": 33550, "total_steps": 38150, "loss": 0.0841, "lr": 2.182813140432785e-06, "epoch": 8.794233289646133, "percentage": 87.94, "elapsed_time": "0:56:29", "remaining_time": "0:07:44", "throughput": 2653.95, "total_tokens": 8996704} {"current_steps": 33555, "total_steps": 38150, "loss": 0.1464, "lr": 2.1781415885742037e-06, "epoch": 8.795543905635649, "percentage": 87.96, "elapsed_time": "0:56:30", "remaining_time": "0:07:44", "throughput": 2654.08, "total_tokens": 8998608} {"current_steps": 33560, "total_steps": 38150, "loss": 0.1729, "lr": 2.1734748132911515e-06, "epoch": 8.796854521625164, "percentage": 87.97, "elapsed_time": "0:56:30", "remaining_time": "0:07:43", "throughput": 2654.15, "total_tokens": 8999952} {"current_steps": 33565, "total_steps": 38150, "loss": 0.1045, "lr": 2.1688128155603783e-06, "epoch": 8.79816513761468, "percentage": 87.98, "elapsed_time": "0:56:31", "remaining_time": "0:07:43", "throughput": 2654.18, "total_tokens": 9001312} {"current_steps": 33570, "total_steps": 38150, "loss": 0.09, "lr": 2.1641555963576366e-06, "epoch": 8.799475753604193, "percentage": 87.99, "elapsed_time": "0:56:31", "remaining_time": "0:07:42", "throughput": 2654.21, "total_tokens": 9002528} {"current_steps": 33575, "total_steps": 38150, "loss": 0.1261, "lr": 2.159503156657669e-06, "epoch": 8.800786369593709, "percentage": 88.01, "elapsed_time": "0:56:32", "remaining_time": "0:07:42", "throughput": 2654.22, "total_tokens": 9003776} {"current_steps": 33580, "total_steps": 38150, "loss": 0.1387, "lr": 2.1548554974342244e-06, "epoch": 8.802096985583225, "percentage": 88.02, "elapsed_time": "0:56:32", "remaining_time": "0:07:41", "throughput": 2654.19, "total_tokens": 9004768} {"current_steps": 33585, "total_steps": 38150, "loss": 0.2295, "lr": 2.15021261966005e-06, "epoch": 8.80340760157274, "percentage": 88.03, "elapsed_time": "0:56:33", "remaining_time": "0:07:41", "throughput": 2654.21, "total_tokens": 9005984} {"current_steps": 33590, "total_steps": 38150, "loss": 0.1575, "lr": 2.145574524306898e-06, "epoch": 8.804718217562254, "percentage": 88.05, "elapsed_time": "0:56:33", "remaining_time": "0:07:40", "throughput": 2654.23, "total_tokens": 9007200} {"current_steps": 33595, "total_steps": 38150, "loss": 0.1767, "lr": 2.140941212345507e-06, "epoch": 8.80602883355177, "percentage": 88.06, "elapsed_time": "0:56:34", "remaining_time": "0:07:40", "throughput": 2654.37, "total_tokens": 9009152} {"current_steps": 33600, "total_steps": 38150, "loss": 0.0769, "lr": 2.136312684745623e-06, "epoch": 8.807339449541285, "percentage": 88.07, "elapsed_time": "0:56:34", "remaining_time": "0:07:39", "throughput": 2654.6, "total_tokens": 9011744} {"current_steps": 33605, "total_steps": 38150, "loss": 0.1934, "lr": 2.1316889424759874e-06, "epoch": 8.808650065530799, "percentage": 88.09, "elapsed_time": "0:56:35", "remaining_time": "0:07:39", "throughput": 2654.7, "total_tokens": 9013424} {"current_steps": 33610, "total_steps": 38150, "loss": 0.158, "lr": 2.1270699865043405e-06, "epoch": 8.809960681520314, "percentage": 88.1, "elapsed_time": "0:56:35", "remaining_time": "0:07:38", "throughput": 2654.66, "total_tokens": 9014384} {"current_steps": 33615, "total_steps": 38150, "loss": 0.1958, "lr": 2.122455817797428e-06, "epoch": 8.81127129750983, "percentage": 88.11, "elapsed_time": "0:56:36", "remaining_time": "0:07:38", "throughput": 2654.77, "total_tokens": 9015936} {"current_steps": 33620, "total_steps": 38150, "loss": 0.1525, "lr": 2.1178464373209807e-06, "epoch": 8.812581913499345, "percentage": 88.13, "elapsed_time": "0:56:36", "remaining_time": "0:07:37", "throughput": 2654.76, "total_tokens": 9017040} {"current_steps": 33625, "total_steps": 38150, "loss": 0.3731, "lr": 2.1132418460397376e-06, "epoch": 8.813892529488859, "percentage": 88.14, "elapsed_time": "0:56:37", "remaining_time": "0:07:37", "throughput": 2654.82, "total_tokens": 9018464} {"current_steps": 33630, "total_steps": 38150, "loss": 0.1227, "lr": 2.1086420449174303e-06, "epoch": 8.815203145478375, "percentage": 88.15, "elapsed_time": "0:56:37", "remaining_time": "0:07:36", "throughput": 2654.84, "total_tokens": 9019648} {"current_steps": 33635, "total_steps": 38150, "loss": 0.2122, "lr": 2.1040470349167923e-06, "epoch": 8.81651376146789, "percentage": 88.17, "elapsed_time": "0:56:37", "remaining_time": "0:07:36", "throughput": 2654.94, "total_tokens": 9021360} {"current_steps": 33640, "total_steps": 38150, "loss": 0.1423, "lr": 2.0994568169995455e-06, "epoch": 8.817824377457406, "percentage": 88.18, "elapsed_time": "0:56:38", "remaining_time": "0:07:35", "throughput": 2654.95, "total_tokens": 9022496} {"current_steps": 33645, "total_steps": 38150, "loss": 0.1275, "lr": 2.0948713921264214e-06, "epoch": 8.81913499344692, "percentage": 88.19, "elapsed_time": "0:56:38", "remaining_time": "0:07:35", "throughput": 2654.99, "total_tokens": 9023792} {"current_steps": 33650, "total_steps": 38150, "loss": 0.1056, "lr": 2.0902907612571355e-06, "epoch": 8.820445609436435, "percentage": 88.2, "elapsed_time": "0:56:39", "remaining_time": "0:07:34", "throughput": 2655.0, "total_tokens": 9024928} {"current_steps": 33655, "total_steps": 38150, "loss": 0.2146, "lr": 2.085714925350407e-06, "epoch": 8.82175622542595, "percentage": 88.22, "elapsed_time": "0:56:39", "remaining_time": "0:07:34", "throughput": 2655.05, "total_tokens": 9026256} {"current_steps": 33660, "total_steps": 38150, "loss": 0.2702, "lr": 2.0811438853639537e-06, "epoch": 8.823066841415466, "percentage": 88.23, "elapsed_time": "0:56:40", "remaining_time": "0:07:33", "throughput": 2655.13, "total_tokens": 9027904} {"current_steps": 33665, "total_steps": 38150, "loss": 0.2164, "lr": 2.076577642254485e-06, "epoch": 8.82437745740498, "percentage": 88.24, "elapsed_time": "0:56:40", "remaining_time": "0:07:33", "throughput": 2655.17, "total_tokens": 9029168} {"current_steps": 33670, "total_steps": 38150, "loss": 0.1666, "lr": 2.072016196977708e-06, "epoch": 8.825688073394495, "percentage": 88.26, "elapsed_time": "0:56:41", "remaining_time": "0:07:32", "throughput": 2655.19, "total_tokens": 9030336} {"current_steps": 33675, "total_steps": 38150, "loss": 0.1395, "lr": 2.0674595504883265e-06, "epoch": 8.82699868938401, "percentage": 88.27, "elapsed_time": "0:56:41", "remaining_time": "0:07:32", "throughput": 2655.19, "total_tokens": 9031488} {"current_steps": 33680, "total_steps": 38150, "loss": 0.1438, "lr": 2.062907703740033e-06, "epoch": 8.828309305373526, "percentage": 88.28, "elapsed_time": "0:56:41", "remaining_time": "0:07:31", "throughput": 2655.29, "total_tokens": 9033152} {"current_steps": 33685, "total_steps": 38150, "loss": 0.1094, "lr": 2.0583606576855236e-06, "epoch": 8.82961992136304, "percentage": 88.3, "elapsed_time": "0:56:42", "remaining_time": "0:07:30", "throughput": 2655.31, "total_tokens": 9034352} {"current_steps": 33690, "total_steps": 38150, "loss": 0.1835, "lr": 2.0538184132764897e-06, "epoch": 8.830930537352556, "percentage": 88.31, "elapsed_time": "0:56:42", "remaining_time": "0:07:30", "throughput": 2655.35, "total_tokens": 9035712} {"current_steps": 33695, "total_steps": 38150, "loss": 0.1343, "lr": 2.0492809714636156e-06, "epoch": 8.832241153342071, "percentage": 88.32, "elapsed_time": "0:56:43", "remaining_time": "0:07:29", "throughput": 2655.33, "total_tokens": 9036784} {"current_steps": 33700, "total_steps": 38150, "loss": 0.1231, "lr": 2.044748333196572e-06, "epoch": 8.833551769331585, "percentage": 88.34, "elapsed_time": "0:56:43", "remaining_time": "0:07:29", "throughput": 2655.42, "total_tokens": 9038256} {"current_steps": 33705, "total_steps": 38150, "loss": 0.1329, "lr": 2.040220499424042e-06, "epoch": 8.8348623853211, "percentage": 88.35, "elapsed_time": "0:56:44", "remaining_time": "0:07:28", "throughput": 2655.48, "total_tokens": 9039712} {"current_steps": 33710, "total_steps": 38150, "loss": 0.1605, "lr": 2.0356974710936976e-06, "epoch": 8.836173001310616, "percentage": 88.36, "elapsed_time": "0:56:44", "remaining_time": "0:07:28", "throughput": 2655.59, "total_tokens": 9041440} {"current_steps": 33715, "total_steps": 38150, "loss": 0.0897, "lr": 2.0311792491521874e-06, "epoch": 8.837483617300132, "percentage": 88.37, "elapsed_time": "0:56:45", "remaining_time": "0:07:27", "throughput": 2655.56, "total_tokens": 9042448} {"current_steps": 33720, "total_steps": 38150, "loss": 0.1686, "lr": 2.0266658345451715e-06, "epoch": 8.838794233289645, "percentage": 88.39, "elapsed_time": "0:56:45", "remaining_time": "0:07:27", "throughput": 2655.6, "total_tokens": 9043824} {"current_steps": 33725, "total_steps": 38150, "loss": 0.1673, "lr": 2.022157228217303e-06, "epoch": 8.840104849279161, "percentage": 88.4, "elapsed_time": "0:56:46", "remaining_time": "0:07:26", "throughput": 2655.64, "total_tokens": 9045168} {"current_steps": 33730, "total_steps": 38150, "loss": 0.1203, "lr": 2.0176534311122263e-06, "epoch": 8.841415465268676, "percentage": 88.41, "elapsed_time": "0:56:46", "remaining_time": "0:07:26", "throughput": 2655.65, "total_tokens": 9046368} {"current_steps": 33735, "total_steps": 38150, "loss": 0.221, "lr": 2.0131544441725715e-06, "epoch": 8.842726081258192, "percentage": 88.43, "elapsed_time": "0:56:46", "remaining_time": "0:07:25", "throughput": 2655.64, "total_tokens": 9047520} {"current_steps": 33740, "total_steps": 38150, "loss": 0.1466, "lr": 2.0086602683399764e-06, "epoch": 8.844036697247706, "percentage": 88.44, "elapsed_time": "0:56:47", "remaining_time": "0:07:25", "throughput": 2655.7, "total_tokens": 9048960} {"current_steps": 33745, "total_steps": 38150, "loss": 0.0581, "lr": 2.0041709045550612e-06, "epoch": 8.845347313237221, "percentage": 88.45, "elapsed_time": "0:56:47", "remaining_time": "0:07:24", "throughput": 2655.61, "total_tokens": 9049744} {"current_steps": 33750, "total_steps": 38150, "loss": 0.2987, "lr": 1.9996863537574406e-06, "epoch": 8.846657929226737, "percentage": 88.47, "elapsed_time": "0:56:48", "remaining_time": "0:07:24", "throughput": 2655.65, "total_tokens": 9051040} {"current_steps": 33755, "total_steps": 38150, "loss": 0.0882, "lr": 1.9952066168857252e-06, "epoch": 8.847968545216252, "percentage": 88.48, "elapsed_time": "0:56:48", "remaining_time": "0:07:23", "throughput": 2655.59, "total_tokens": 9051920} {"current_steps": 33760, "total_steps": 38150, "loss": 0.5421, "lr": 1.990731694877515e-06, "epoch": 8.849279161205766, "percentage": 88.49, "elapsed_time": "0:56:49", "remaining_time": "0:07:23", "throughput": 2655.7, "total_tokens": 9053600} {"current_steps": 33765, "total_steps": 38150, "loss": 0.1842, "lr": 1.9862615886694054e-06, "epoch": 8.850589777195282, "percentage": 88.51, "elapsed_time": "0:56:49", "remaining_time": "0:07:22", "throughput": 2655.72, "total_tokens": 9054848} {"current_steps": 33770, "total_steps": 38150, "loss": 0.1591, "lr": 1.9817962991969805e-06, "epoch": 8.851900393184797, "percentage": 88.52, "elapsed_time": "0:56:49", "remaining_time": "0:07:22", "throughput": 2655.73, "total_tokens": 9056032} {"current_steps": 33775, "total_steps": 38150, "loss": 0.1981, "lr": 1.977335827394816e-06, "epoch": 8.853211009174313, "percentage": 88.53, "elapsed_time": "0:56:50", "remaining_time": "0:07:21", "throughput": 2655.74, "total_tokens": 9057216} {"current_steps": 33780, "total_steps": 38150, "loss": 0.157, "lr": 1.972880174196484e-06, "epoch": 8.854521625163827, "percentage": 88.55, "elapsed_time": "0:56:50", "remaining_time": "0:07:21", "throughput": 2655.79, "total_tokens": 9058528} {"current_steps": 33785, "total_steps": 38150, "loss": 0.143, "lr": 1.9684293405345445e-06, "epoch": 8.855832241153342, "percentage": 88.56, "elapsed_time": "0:56:51", "remaining_time": "0:07:20", "throughput": 2655.77, "total_tokens": 9059568} {"current_steps": 33790, "total_steps": 38150, "loss": 0.2382, "lr": 1.9639833273405516e-06, "epoch": 8.857142857142858, "percentage": 88.57, "elapsed_time": "0:56:51", "remaining_time": "0:07:20", "throughput": 2655.81, "total_tokens": 9060960} {"current_steps": 33795, "total_steps": 38150, "loss": 0.1327, "lr": 1.959542135545042e-06, "epoch": 8.858453473132371, "percentage": 88.58, "elapsed_time": "0:56:52", "remaining_time": "0:07:19", "throughput": 2655.92, "total_tokens": 9062576} {"current_steps": 33800, "total_steps": 38150, "loss": 0.1541, "lr": 1.9551057660775527e-06, "epoch": 8.859764089121887, "percentage": 88.6, "elapsed_time": "0:56:52", "remaining_time": "0:07:19", "throughput": 2655.99, "total_tokens": 9064096} {"current_steps": 33805, "total_steps": 38150, "loss": 0.2036, "lr": 1.950674219866608e-06, "epoch": 8.861074705111402, "percentage": 88.61, "elapsed_time": "0:56:53", "remaining_time": "0:07:18", "throughput": 2656.05, "total_tokens": 9065552} {"current_steps": 33810, "total_steps": 38150, "loss": 0.1349, "lr": 1.9462474978397204e-06, "epoch": 8.862385321100918, "percentage": 88.62, "elapsed_time": "0:56:53", "remaining_time": "0:07:18", "throughput": 2656.1, "total_tokens": 9066992} {"current_steps": 33815, "total_steps": 38150, "loss": 0.195, "lr": 1.941825600923397e-06, "epoch": 8.863695937090432, "percentage": 88.64, "elapsed_time": "0:56:54", "remaining_time": "0:07:17", "throughput": 2656.14, "total_tokens": 9068368} {"current_steps": 33820, "total_steps": 38150, "loss": 0.3037, "lr": 1.937408530043136e-06, "epoch": 8.865006553079947, "percentage": 88.65, "elapsed_time": "0:56:54", "remaining_time": "0:07:17", "throughput": 2656.21, "total_tokens": 9069840} {"current_steps": 33825, "total_steps": 38150, "loss": 0.2511, "lr": 1.9329962861234257e-06, "epoch": 8.866317169069463, "percentage": 88.66, "elapsed_time": "0:56:55", "remaining_time": "0:07:16", "throughput": 2656.26, "total_tokens": 9071248} {"current_steps": 33830, "total_steps": 38150, "loss": 0.1433, "lr": 1.9285888700877303e-06, "epoch": 8.867627785058978, "percentage": 88.68, "elapsed_time": "0:56:55", "remaining_time": "0:07:16", "throughput": 2656.32, "total_tokens": 9072800} {"current_steps": 33835, "total_steps": 38150, "loss": 0.1834, "lr": 1.92418628285852e-06, "epoch": 8.868938401048492, "percentage": 88.69, "elapsed_time": "0:56:55", "remaining_time": "0:07:15", "throughput": 2656.32, "total_tokens": 9073904} {"current_steps": 33840, "total_steps": 38150, "loss": 0.0932, "lr": 1.9197885253572497e-06, "epoch": 8.870249017038008, "percentage": 88.7, "elapsed_time": "0:56:56", "remaining_time": "0:07:15", "throughput": 2656.35, "total_tokens": 9075184} {"current_steps": 33845, "total_steps": 38150, "loss": 0.1363, "lr": 1.915395598504363e-06, "epoch": 8.871559633027523, "percentage": 88.72, "elapsed_time": "0:56:56", "remaining_time": "0:07:14", "throughput": 2656.38, "total_tokens": 9076464} {"current_steps": 33850, "total_steps": 38150, "loss": 0.2461, "lr": 1.9110075032192894e-06, "epoch": 8.872870249017039, "percentage": 88.73, "elapsed_time": "0:56:57", "remaining_time": "0:07:14", "throughput": 2656.38, "total_tokens": 9077680} {"current_steps": 33855, "total_steps": 38150, "loss": 0.0684, "lr": 1.9066242404204487e-06, "epoch": 8.874180865006553, "percentage": 88.74, "elapsed_time": "0:56:57", "remaining_time": "0:07:13", "throughput": 2656.4, "total_tokens": 9078976} {"current_steps": 33860, "total_steps": 38150, "loss": 0.1384, "lr": 1.902245811025255e-06, "epoch": 8.875491480996068, "percentage": 88.75, "elapsed_time": "0:56:58", "remaining_time": "0:07:13", "throughput": 2656.46, "total_tokens": 9080352} {"current_steps": 33865, "total_steps": 38150, "loss": 0.168, "lr": 1.8978722159501029e-06, "epoch": 8.876802096985584, "percentage": 88.77, "elapsed_time": "0:56:58", "remaining_time": "0:07:12", "throughput": 2656.47, "total_tokens": 9081552} {"current_steps": 33870, "total_steps": 38150, "loss": 0.1477, "lr": 1.8935034561103764e-06, "epoch": 8.8781127129751, "percentage": 88.78, "elapsed_time": "0:56:59", "remaining_time": "0:07:12", "throughput": 2656.49, "total_tokens": 9082752} {"current_steps": 33875, "total_steps": 38150, "loss": 0.0882, "lr": 1.889139532420453e-06, "epoch": 8.879423328964613, "percentage": 88.79, "elapsed_time": "0:56:59", "remaining_time": "0:07:11", "throughput": 2656.51, "total_tokens": 9083936} {"current_steps": 33880, "total_steps": 38150, "loss": 0.082, "lr": 1.8847804457936934e-06, "epoch": 8.880733944954128, "percentage": 88.81, "elapsed_time": "0:56:59", "remaining_time": "0:07:11", "throughput": 2656.55, "total_tokens": 9085264} {"current_steps": 33885, "total_steps": 38150, "loss": 0.0498, "lr": 1.8804261971424458e-06, "epoch": 8.882044560943644, "percentage": 88.82, "elapsed_time": "0:57:00", "remaining_time": "0:07:10", "throughput": 2656.58, "total_tokens": 9086512} {"current_steps": 33890, "total_steps": 38150, "loss": 0.0785, "lr": 1.8760767873780476e-06, "epoch": 8.883355176933158, "percentage": 88.83, "elapsed_time": "0:57:00", "remaining_time": "0:07:09", "throughput": 2656.58, "total_tokens": 9087648} {"current_steps": 33895, "total_steps": 38150, "loss": 0.2472, "lr": 1.871732217410821e-06, "epoch": 8.884665792922673, "percentage": 88.85, "elapsed_time": "0:57:01", "remaining_time": "0:07:09", "throughput": 2656.65, "total_tokens": 9089120} {"current_steps": 33900, "total_steps": 38150, "loss": 0.0793, "lr": 1.8673924881500826e-06, "epoch": 8.885976408912189, "percentage": 88.86, "elapsed_time": "0:57:01", "remaining_time": "0:07:08", "throughput": 2656.69, "total_tokens": 9090368} {"current_steps": 33905, "total_steps": 38150, "loss": 0.1235, "lr": 1.8630576005041228e-06, "epoch": 8.887287024901704, "percentage": 88.87, "elapsed_time": "0:57:02", "remaining_time": "0:07:08", "throughput": 2656.68, "total_tokens": 9091552} {"current_steps": 33910, "total_steps": 38150, "loss": 0.1123, "lr": 1.8587275553802352e-06, "epoch": 8.888597640891218, "percentage": 88.89, "elapsed_time": "0:57:02", "remaining_time": "0:07:07", "throughput": 2656.71, "total_tokens": 9092800} {"current_steps": 33915, "total_steps": 38150, "loss": 0.2486, "lr": 1.854402353684681e-06, "epoch": 8.889908256880734, "percentage": 88.9, "elapsed_time": "0:57:03", "remaining_time": "0:07:07", "throughput": 2656.83, "total_tokens": 9094512} {"current_steps": 33920, "total_steps": 38150, "loss": 0.132, "lr": 1.8500819963227223e-06, "epoch": 8.89121887287025, "percentage": 88.91, "elapsed_time": "0:57:03", "remaining_time": "0:07:06", "throughput": 2656.82, "total_tokens": 9095776} {"current_steps": 33925, "total_steps": 38150, "loss": 0.1516, "lr": 1.8457664841986023e-06, "epoch": 8.892529488859765, "percentage": 88.93, "elapsed_time": "0:57:04", "remaining_time": "0:07:06", "throughput": 2656.83, "total_tokens": 9096992} {"current_steps": 33930, "total_steps": 38150, "loss": 0.0858, "lr": 1.8414558182155456e-06, "epoch": 8.893840104849279, "percentage": 88.94, "elapsed_time": "0:57:04", "remaining_time": "0:07:05", "throughput": 2656.84, "total_tokens": 9098160} {"current_steps": 33935, "total_steps": 38150, "loss": 0.136, "lr": 1.8371499992757723e-06, "epoch": 8.895150720838794, "percentage": 88.95, "elapsed_time": "0:57:04", "remaining_time": "0:07:05", "throughput": 2656.98, "total_tokens": 9100016} {"current_steps": 33940, "total_steps": 38150, "loss": 0.1079, "lr": 1.832849028280484e-06, "epoch": 8.89646133682831, "percentage": 88.96, "elapsed_time": "0:57:05", "remaining_time": "0:07:04", "throughput": 2657.0, "total_tokens": 9101248} {"current_steps": 33945, "total_steps": 38150, "loss": 0.0433, "lr": 1.8285529061298684e-06, "epoch": 8.897771952817825, "percentage": 88.98, "elapsed_time": "0:57:05", "remaining_time": "0:07:04", "throughput": 2657.01, "total_tokens": 9102448} {"current_steps": 33950, "total_steps": 38150, "loss": 0.0644, "lr": 1.82426163372309e-06, "epoch": 8.899082568807339, "percentage": 88.99, "elapsed_time": "0:57:06", "remaining_time": "0:07:03", "throughput": 2657.02, "total_tokens": 9103568} {"current_steps": 33955, "total_steps": 38150, "loss": 0.074, "lr": 1.8199752119583052e-06, "epoch": 8.900393184796854, "percentage": 89.0, "elapsed_time": "0:57:06", "remaining_time": "0:07:03", "throughput": 2657.01, "total_tokens": 9104656} {"current_steps": 33960, "total_steps": 38150, "loss": 0.2684, "lr": 1.8156936417326576e-06, "epoch": 8.90170380078637, "percentage": 89.02, "elapsed_time": "0:57:07", "remaining_time": "0:07:02", "throughput": 2657.1, "total_tokens": 9106288} {"current_steps": 33965, "total_steps": 38150, "loss": 0.13, "lr": 1.8114169239422691e-06, "epoch": 8.903014416775886, "percentage": 89.03, "elapsed_time": "0:57:07", "remaining_time": "0:07:02", "throughput": 2657.15, "total_tokens": 9107728} {"current_steps": 33970, "total_steps": 38150, "loss": 0.1687, "lr": 1.8071450594822543e-06, "epoch": 8.9043250327654, "percentage": 89.04, "elapsed_time": "0:57:08", "remaining_time": "0:07:01", "throughput": 2657.15, "total_tokens": 9108912} {"current_steps": 33975, "total_steps": 38150, "loss": 0.0923, "lr": 1.8028780492467007e-06, "epoch": 8.905635648754915, "percentage": 89.06, "elapsed_time": "0:57:08", "remaining_time": "0:07:01", "throughput": 2657.3, "total_tokens": 9110784} {"current_steps": 33980, "total_steps": 38150, "loss": 0.2098, "lr": 1.798615894128694e-06, "epoch": 8.90694626474443, "percentage": 89.07, "elapsed_time": "0:57:09", "remaining_time": "0:07:00", "throughput": 2657.32, "total_tokens": 9112016} {"current_steps": 33985, "total_steps": 38150, "loss": 0.0852, "lr": 1.7943585950202902e-06, "epoch": 8.908256880733944, "percentage": 89.08, "elapsed_time": "0:57:09", "remaining_time": "0:07:00", "throughput": 2657.32, "total_tokens": 9113184} {"current_steps": 33990, "total_steps": 38150, "loss": 0.1739, "lr": 1.7901061528125347e-06, "epoch": 8.90956749672346, "percentage": 89.1, "elapsed_time": "0:57:09", "remaining_time": "0:06:59", "throughput": 2657.41, "total_tokens": 9114832} {"current_steps": 33995, "total_steps": 38150, "loss": 0.1433, "lr": 1.7858585683954597e-06, "epoch": 8.910878112712975, "percentage": 89.11, "elapsed_time": "0:57:10", "remaining_time": "0:06:59", "throughput": 2657.45, "total_tokens": 9116128} {"current_steps": 34000, "total_steps": 38150, "loss": 0.1198, "lr": 1.7816158426580742e-06, "epoch": 8.91218872870249, "percentage": 89.12, "elapsed_time": "0:57:10", "remaining_time": "0:06:58", "throughput": 2657.48, "total_tokens": 9117408} {"current_steps": 34005, "total_steps": 38150, "loss": 0.0869, "lr": 1.7773779764883758e-06, "epoch": 8.913499344692005, "percentage": 89.13, "elapsed_time": "0:57:11", "remaining_time": "0:06:58", "throughput": 2657.71, "total_tokens": 9120192} {"current_steps": 34010, "total_steps": 38150, "loss": 0.1751, "lr": 1.7731449707733412e-06, "epoch": 8.91480996068152, "percentage": 89.15, "elapsed_time": "0:57:12", "remaining_time": "0:06:57", "throughput": 2657.78, "total_tokens": 9121616} {"current_steps": 34015, "total_steps": 38150, "loss": 0.1349, "lr": 1.7689168263989309e-06, "epoch": 8.916120576671036, "percentage": 89.16, "elapsed_time": "0:57:12", "remaining_time": "0:06:57", "throughput": 2657.82, "total_tokens": 9122912} {"current_steps": 34020, "total_steps": 38150, "loss": 0.2221, "lr": 1.7646935442500872e-06, "epoch": 8.917431192660551, "percentage": 89.17, "elapsed_time": "0:57:12", "remaining_time": "0:06:56", "throughput": 2657.86, "total_tokens": 9124336} {"current_steps": 34025, "total_steps": 38150, "loss": 0.0936, "lr": 1.760475125210745e-06, "epoch": 8.918741808650065, "percentage": 89.19, "elapsed_time": "0:57:13", "remaining_time": "0:06:56", "throughput": 2657.85, "total_tokens": 9125472} {"current_steps": 34030, "total_steps": 38150, "loss": 0.2667, "lr": 1.7562615701637975e-06, "epoch": 8.92005242463958, "percentage": 89.2, "elapsed_time": "0:57:13", "remaining_time": "0:06:55", "throughput": 2657.84, "total_tokens": 9126560} {"current_steps": 34035, "total_steps": 38150, "loss": 0.1336, "lr": 1.7520528799911395e-06, "epoch": 8.921363040629096, "percentage": 89.21, "elapsed_time": "0:57:14", "remaining_time": "0:06:55", "throughput": 2657.84, "total_tokens": 9127776} {"current_steps": 34040, "total_steps": 38150, "loss": 0.1094, "lr": 1.7478490555736471e-06, "epoch": 8.922673656618612, "percentage": 89.23, "elapsed_time": "0:57:14", "remaining_time": "0:06:54", "throughput": 2657.92, "total_tokens": 9129248} {"current_steps": 34045, "total_steps": 38150, "loss": 0.2186, "lr": 1.7436500977911663e-06, "epoch": 8.923984272608125, "percentage": 89.24, "elapsed_time": "0:57:15", "remaining_time": "0:06:54", "throughput": 2658.03, "total_tokens": 9130896} {"current_steps": 34050, "total_steps": 38150, "loss": 0.1392, "lr": 1.7394560075225414e-06, "epoch": 8.92529488859764, "percentage": 89.25, "elapsed_time": "0:57:15", "remaining_time": "0:06:53", "throughput": 2658.0, "total_tokens": 9131936} {"current_steps": 34055, "total_steps": 38150, "loss": 0.1339, "lr": 1.7352667856455812e-06, "epoch": 8.926605504587156, "percentage": 89.27, "elapsed_time": "0:57:16", "remaining_time": "0:06:53", "throughput": 2658.03, "total_tokens": 9133168} {"current_steps": 34060, "total_steps": 38150, "loss": 0.1152, "lr": 1.7310824330370873e-06, "epoch": 8.927916120576672, "percentage": 89.28, "elapsed_time": "0:57:16", "remaining_time": "0:06:52", "throughput": 2658.02, "total_tokens": 9134272} {"current_steps": 34065, "total_steps": 38150, "loss": 0.149, "lr": 1.7269029505728313e-06, "epoch": 8.929226736566186, "percentage": 89.29, "elapsed_time": "0:57:16", "remaining_time": "0:06:52", "throughput": 2658.04, "total_tokens": 9135520} {"current_steps": 34070, "total_steps": 38150, "loss": 0.1047, "lr": 1.7227283391275772e-06, "epoch": 8.930537352555701, "percentage": 89.31, "elapsed_time": "0:57:17", "remaining_time": "0:06:51", "throughput": 2658.07, "total_tokens": 9136752} {"current_steps": 34075, "total_steps": 38150, "loss": 0.0848, "lr": 1.7185585995750598e-06, "epoch": 8.931847968545217, "percentage": 89.32, "elapsed_time": "0:57:17", "remaining_time": "0:06:51", "throughput": 2657.99, "total_tokens": 9137568} {"current_steps": 34080, "total_steps": 38150, "loss": 0.097, "lr": 1.714393732788e-06, "epoch": 8.93315858453473, "percentage": 89.33, "elapsed_time": "0:57:18", "remaining_time": "0:06:50", "throughput": 2657.99, "total_tokens": 9138688} {"current_steps": 34085, "total_steps": 38150, "loss": 0.1126, "lr": 1.710233739638098e-06, "epoch": 8.934469200524246, "percentage": 89.34, "elapsed_time": "0:57:18", "remaining_time": "0:06:50", "throughput": 2658.0, "total_tokens": 9139872} {"current_steps": 34090, "total_steps": 38150, "loss": 0.2141, "lr": 1.706078620996035e-06, "epoch": 8.935779816513762, "percentage": 89.36, "elapsed_time": "0:57:19", "remaining_time": "0:06:49", "throughput": 2658.2, "total_tokens": 9142192} {"current_steps": 34095, "total_steps": 38150, "loss": 0.2187, "lr": 1.7019283777314653e-06, "epoch": 8.937090432503277, "percentage": 89.37, "elapsed_time": "0:57:19", "remaining_time": "0:06:49", "throughput": 2658.26, "total_tokens": 9143664} {"current_steps": 34100, "total_steps": 38150, "loss": 0.1924, "lr": 1.6977830107130305e-06, "epoch": 8.938401048492791, "percentage": 89.38, "elapsed_time": "0:57:20", "remaining_time": "0:06:48", "throughput": 2658.32, "total_tokens": 9145136} {"current_steps": 34105, "total_steps": 38150, "loss": 0.1488, "lr": 1.6936425208083473e-06, "epoch": 8.939711664482306, "percentage": 89.4, "elapsed_time": "0:57:20", "remaining_time": "0:06:48", "throughput": 2658.39, "total_tokens": 9146544} {"current_steps": 34110, "total_steps": 38150, "loss": 0.1278, "lr": 1.6895069088840144e-06, "epoch": 8.941022280471822, "percentage": 89.41, "elapsed_time": "0:57:21", "remaining_time": "0:06:47", "throughput": 2658.5, "total_tokens": 9148336} {"current_steps": 34115, "total_steps": 38150, "loss": 0.3652, "lr": 1.6853761758056114e-06, "epoch": 8.942332896461338, "percentage": 89.42, "elapsed_time": "0:57:21", "remaining_time": "0:06:47", "throughput": 2658.76, "total_tokens": 9151376} {"current_steps": 34120, "total_steps": 38150, "loss": 0.1084, "lr": 1.6812503224376857e-06, "epoch": 8.943643512450851, "percentage": 89.44, "elapsed_time": "0:57:22", "remaining_time": "0:06:46", "throughput": 2658.71, "total_tokens": 9152304} {"current_steps": 34125, "total_steps": 38150, "loss": 0.2172, "lr": 1.67712934964378e-06, "epoch": 8.944954128440367, "percentage": 89.45, "elapsed_time": "0:57:22", "remaining_time": "0:06:46", "throughput": 2658.76, "total_tokens": 9153632} {"current_steps": 34130, "total_steps": 38150, "loss": 0.1976, "lr": 1.673013258286399e-06, "epoch": 8.946264744429882, "percentage": 89.46, "elapsed_time": "0:57:23", "remaining_time": "0:06:45", "throughput": 2658.8, "total_tokens": 9154928} {"current_steps": 34135, "total_steps": 38150, "loss": 0.0852, "lr": 1.668902049227039e-06, "epoch": 8.947575360419398, "percentage": 89.48, "elapsed_time": "0:57:23", "remaining_time": "0:06:45", "throughput": 2658.81, "total_tokens": 9156096} {"current_steps": 34140, "total_steps": 38150, "loss": 0.1685, "lr": 1.664795723326168e-06, "epoch": 8.948885976408912, "percentage": 89.49, "elapsed_time": "0:57:24", "remaining_time": "0:06:44", "throughput": 2658.87, "total_tokens": 9157472} {"current_steps": 34145, "total_steps": 38150, "loss": 0.2282, "lr": 1.660694281443234e-06, "epoch": 8.950196592398427, "percentage": 89.5, "elapsed_time": "0:57:24", "remaining_time": "0:06:44", "throughput": 2658.96, "total_tokens": 9159088} {"current_steps": 34150, "total_steps": 38150, "loss": 0.2231, "lr": 1.6565977244366564e-06, "epoch": 8.951507208387943, "percentage": 89.52, "elapsed_time": "0:57:25", "remaining_time": "0:06:43", "throughput": 2658.99, "total_tokens": 9160304} {"current_steps": 34155, "total_steps": 38150, "loss": 0.1491, "lr": 1.6525060531638408e-06, "epoch": 8.952817824377458, "percentage": 89.53, "elapsed_time": "0:57:25", "remaining_time": "0:06:43", "throughput": 2659.05, "total_tokens": 9161824} {"current_steps": 34160, "total_steps": 38150, "loss": 0.2412, "lr": 1.6484192684811634e-06, "epoch": 8.954128440366972, "percentage": 89.54, "elapsed_time": "0:57:25", "remaining_time": "0:06:42", "throughput": 2659.07, "total_tokens": 9163040} {"current_steps": 34165, "total_steps": 38150, "loss": 0.1549, "lr": 1.644337371243987e-06, "epoch": 8.955439056356488, "percentage": 89.55, "elapsed_time": "0:57:26", "remaining_time": "0:06:41", "throughput": 2659.11, "total_tokens": 9164352} {"current_steps": 34170, "total_steps": 38150, "loss": 0.1133, "lr": 1.6402603623066448e-06, "epoch": 8.956749672346003, "percentage": 89.57, "elapsed_time": "0:57:26", "remaining_time": "0:06:41", "throughput": 2659.12, "total_tokens": 9165488} {"current_steps": 34175, "total_steps": 38150, "loss": 0.1876, "lr": 1.6361882425224461e-06, "epoch": 8.958060288335517, "percentage": 89.58, "elapsed_time": "0:57:27", "remaining_time": "0:06:40", "throughput": 2659.22, "total_tokens": 9167280} {"current_steps": 34180, "total_steps": 38150, "loss": 0.1396, "lr": 1.6321210127436814e-06, "epoch": 8.959370904325032, "percentage": 89.59, "elapsed_time": "0:57:27", "remaining_time": "0:06:40", "throughput": 2659.28, "total_tokens": 9168736} {"current_steps": 34185, "total_steps": 38150, "loss": 0.1451, "lr": 1.6280586738216114e-06, "epoch": 8.960681520314548, "percentage": 89.61, "elapsed_time": "0:57:28", "remaining_time": "0:06:39", "throughput": 2659.26, "total_tokens": 9169776} {"current_steps": 34190, "total_steps": 38150, "loss": 0.2845, "lr": 1.6240012266064752e-06, "epoch": 8.961992136304064, "percentage": 89.62, "elapsed_time": "0:57:28", "remaining_time": "0:06:39", "throughput": 2659.2, "total_tokens": 9170752} {"current_steps": 34195, "total_steps": 38150, "loss": 0.1057, "lr": 1.619948671947491e-06, "epoch": 8.963302752293577, "percentage": 89.63, "elapsed_time": "0:57:29", "remaining_time": "0:06:38", "throughput": 2659.22, "total_tokens": 9171984} {"current_steps": 34200, "total_steps": 38150, "loss": 0.1804, "lr": 1.6159010106928523e-06, "epoch": 8.964613368283093, "percentage": 89.65, "elapsed_time": "0:57:29", "remaining_time": "0:06:38", "throughput": 2659.28, "total_tokens": 9173440} {"current_steps": 34205, "total_steps": 38150, "loss": 0.1278, "lr": 1.611858243689729e-06, "epoch": 8.965923984272608, "percentage": 89.66, "elapsed_time": "0:57:30", "remaining_time": "0:06:37", "throughput": 2659.26, "total_tokens": 9174464} {"current_steps": 34210, "total_steps": 38150, "loss": 0.2535, "lr": 1.6078203717842633e-06, "epoch": 8.967234600262124, "percentage": 89.67, "elapsed_time": "0:57:30", "remaining_time": "0:06:37", "throughput": 2659.35, "total_tokens": 9176080} {"current_steps": 34215, "total_steps": 38150, "loss": 0.1606, "lr": 1.6037873958215738e-06, "epoch": 8.968545216251638, "percentage": 89.69, "elapsed_time": "0:57:31", "remaining_time": "0:06:36", "throughput": 2659.5, "total_tokens": 9178208} {"current_steps": 34220, "total_steps": 38150, "loss": 0.1569, "lr": 1.5997593166457575e-06, "epoch": 8.969855832241153, "percentage": 89.7, "elapsed_time": "0:57:31", "remaining_time": "0:06:36", "throughput": 2659.52, "total_tokens": 9179456} {"current_steps": 34225, "total_steps": 38150, "loss": 0.1379, "lr": 1.5957361350998846e-06, "epoch": 8.971166448230669, "percentage": 89.71, "elapsed_time": "0:57:31", "remaining_time": "0:06:35", "throughput": 2659.56, "total_tokens": 9180736} {"current_steps": 34230, "total_steps": 38150, "loss": 0.1614, "lr": 1.5917178520259979e-06, "epoch": 8.972477064220184, "percentage": 89.72, "elapsed_time": "0:57:32", "remaining_time": "0:06:35", "throughput": 2659.67, "total_tokens": 9182416} {"current_steps": 34235, "total_steps": 38150, "loss": 0.1858, "lr": 1.5877044682651194e-06, "epoch": 8.973787680209698, "percentage": 89.74, "elapsed_time": "0:57:32", "remaining_time": "0:06:34", "throughput": 2659.73, "total_tokens": 9183904} {"current_steps": 34240, "total_steps": 38150, "loss": 0.2806, "lr": 1.5836959846572408e-06, "epoch": 8.975098296199214, "percentage": 89.75, "elapsed_time": "0:57:33", "remaining_time": "0:06:34", "throughput": 2659.77, "total_tokens": 9185232} {"current_steps": 34245, "total_steps": 38150, "loss": 0.1296, "lr": 1.579692402041333e-06, "epoch": 8.97640891218873, "percentage": 89.76, "elapsed_time": "0:57:33", "remaining_time": "0:06:33", "throughput": 2659.8, "total_tokens": 9186480} {"current_steps": 34250, "total_steps": 38150, "loss": 0.1603, "lr": 1.5756937212553391e-06, "epoch": 8.977719528178245, "percentage": 89.78, "elapsed_time": "0:57:34", "remaining_time": "0:06:33", "throughput": 2659.81, "total_tokens": 9187696} {"current_steps": 34255, "total_steps": 38150, "loss": 0.1569, "lr": 1.5716999431361762e-06, "epoch": 8.979030144167758, "percentage": 89.79, "elapsed_time": "0:57:34", "remaining_time": "0:06:32", "throughput": 2659.89, "total_tokens": 9189168} {"current_steps": 34260, "total_steps": 38150, "loss": 0.0895, "lr": 1.5677110685197366e-06, "epoch": 8.980340760157274, "percentage": 89.8, "elapsed_time": "0:57:35", "remaining_time": "0:06:32", "throughput": 2659.86, "total_tokens": 9190192} {"current_steps": 34265, "total_steps": 38150, "loss": 0.2296, "lr": 1.5637270982408775e-06, "epoch": 8.98165137614679, "percentage": 89.82, "elapsed_time": "0:57:35", "remaining_time": "0:06:31", "throughput": 2659.94, "total_tokens": 9191712} {"current_steps": 34270, "total_steps": 38150, "loss": 0.1993, "lr": 1.559748033133443e-06, "epoch": 8.982961992136303, "percentage": 89.83, "elapsed_time": "0:57:36", "remaining_time": "0:06:31", "throughput": 2659.97, "total_tokens": 9192944} {"current_steps": 34275, "total_steps": 38150, "loss": 0.077, "lr": 1.555773874030242e-06, "epoch": 8.984272608125819, "percentage": 89.84, "elapsed_time": "0:57:36", "remaining_time": "0:06:30", "throughput": 2659.93, "total_tokens": 9193888} {"current_steps": 34280, "total_steps": 38150, "loss": 0.1718, "lr": 1.5518046217630615e-06, "epoch": 8.985583224115334, "percentage": 89.86, "elapsed_time": "0:57:36", "remaining_time": "0:06:30", "throughput": 2659.99, "total_tokens": 9195280} {"current_steps": 34285, "total_steps": 38150, "loss": 0.1673, "lr": 1.5478402771626599e-06, "epoch": 8.98689384010485, "percentage": 89.87, "elapsed_time": "0:57:37", "remaining_time": "0:06:29", "throughput": 2659.97, "total_tokens": 9196336} {"current_steps": 34290, "total_steps": 38150, "loss": 0.1574, "lr": 1.5438808410587646e-06, "epoch": 8.988204456094364, "percentage": 89.88, "elapsed_time": "0:57:37", "remaining_time": "0:06:29", "throughput": 2660.08, "total_tokens": 9197920} {"current_steps": 34295, "total_steps": 38150, "loss": 0.1699, "lr": 1.5399263142800825e-06, "epoch": 8.98951507208388, "percentage": 89.9, "elapsed_time": "0:57:38", "remaining_time": "0:06:28", "throughput": 2660.1, "total_tokens": 9199168} {"current_steps": 34300, "total_steps": 38150, "loss": 0.1298, "lr": 1.5359766976542873e-06, "epoch": 8.990825688073395, "percentage": 89.91, "elapsed_time": "0:57:38", "remaining_time": "0:06:28", "throughput": 2660.07, "total_tokens": 9200176} {"current_steps": 34305, "total_steps": 38150, "loss": 0.1664, "lr": 1.5320319920080262e-06, "epoch": 8.99213630406291, "percentage": 89.92, "elapsed_time": "0:57:39", "remaining_time": "0:06:27", "throughput": 2660.06, "total_tokens": 9201248} {"current_steps": 34310, "total_steps": 38150, "loss": 0.0841, "lr": 1.5280921981669166e-06, "epoch": 8.993446920052424, "percentage": 89.93, "elapsed_time": "0:57:39", "remaining_time": "0:06:27", "throughput": 2659.98, "total_tokens": 9202080} {"current_steps": 34315, "total_steps": 38150, "loss": 0.2549, "lr": 1.5241573169555573e-06, "epoch": 8.99475753604194, "percentage": 89.95, "elapsed_time": "0:57:40", "remaining_time": "0:06:26", "throughput": 2660.09, "total_tokens": 9203952} {"current_steps": 34320, "total_steps": 38150, "loss": 0.3317, "lr": 1.5202273491975061e-06, "epoch": 8.996068152031455, "percentage": 89.96, "elapsed_time": "0:57:40", "remaining_time": "0:06:26", "throughput": 2660.07, "total_tokens": 9204992} {"current_steps": 34325, "total_steps": 38150, "loss": 0.118, "lr": 1.5163022957152994e-06, "epoch": 8.997378768020969, "percentage": 89.97, "elapsed_time": "0:57:40", "remaining_time": "0:06:25", "throughput": 2660.08, "total_tokens": 9206160} {"current_steps": 34330, "total_steps": 38150, "loss": 0.1719, "lr": 1.5123821573304442e-06, "epoch": 8.998689384010484, "percentage": 89.99, "elapsed_time": "0:57:41", "remaining_time": "0:06:25", "throughput": 2660.14, "total_tokens": 9207520} {"current_steps": 34335, "total_steps": 38150, "loss": 0.1442, "lr": 1.5084669348634255e-06, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:57:41", "remaining_time": "0:06:24", "throughput": 2660.01, "total_tokens": 9208488} {"current_steps": 34340, "total_steps": 38150, "loss": 0.1284, "lr": 1.5045566291336854e-06, "epoch": 9.001310615989516, "percentage": 90.01, "elapsed_time": "0:57:42", "remaining_time": "0:06:24", "throughput": 2659.87, "total_tokens": 9209608} {"current_steps": 34344, "total_steps": 38150, "eval_loss": 0.8331424593925476, "epoch": 9.002359108781127, "percentage": 90.02, "elapsed_time": "0:57:59", "remaining_time": "0:06:25", "throughput": 2647.01, "total_tokens": 9210648} {"current_steps": 34345, "total_steps": 38150, "loss": 0.231, "lr": 1.500651240959644e-06, "epoch": 9.00262123197903, "percentage": 90.03, "elapsed_time": "0:58:01", "remaining_time": "0:06:25", "throughput": 2645.66, "total_tokens": 9210792} {"current_steps": 34350, "total_steps": 38150, "loss": 0.0802, "lr": 1.4967507711586976e-06, "epoch": 9.003931847968545, "percentage": 90.04, "elapsed_time": "0:58:01", "remaining_time": "0:06:25", "throughput": 2645.64, "total_tokens": 9211864} {"current_steps": 34355, "total_steps": 38150, "loss": 0.1898, "lr": 1.4928552205472012e-06, "epoch": 9.00524246395806, "percentage": 90.05, "elapsed_time": "0:58:02", "remaining_time": "0:06:24", "throughput": 2645.68, "total_tokens": 9213288} {"current_steps": 34360, "total_steps": 38150, "loss": 0.242, "lr": 1.488964589940489e-06, "epoch": 9.006553079947576, "percentage": 90.07, "elapsed_time": "0:58:02", "remaining_time": "0:06:24", "throughput": 2645.83, "total_tokens": 9215224} {"current_steps": 34365, "total_steps": 38150, "loss": 0.1123, "lr": 1.4850788801528653e-06, "epoch": 9.00786369593709, "percentage": 90.08, "elapsed_time": "0:58:03", "remaining_time": "0:06:23", "throughput": 2645.8, "total_tokens": 9216280} {"current_steps": 34370, "total_steps": 38150, "loss": 0.0696, "lr": 1.4811980919976043e-06, "epoch": 9.009174311926605, "percentage": 90.09, "elapsed_time": "0:58:03", "remaining_time": "0:06:23", "throughput": 2645.83, "total_tokens": 9217608} {"current_steps": 34375, "total_steps": 38150, "loss": 0.1911, "lr": 1.4773222262869423e-06, "epoch": 9.01048492791612, "percentage": 90.1, "elapsed_time": "0:58:04", "remaining_time": "0:06:22", "throughput": 2645.88, "total_tokens": 9219000} {"current_steps": 34380, "total_steps": 38150, "loss": 0.1052, "lr": 1.4734512838320974e-06, "epoch": 9.011795543905636, "percentage": 90.12, "elapsed_time": "0:58:04", "remaining_time": "0:06:22", "throughput": 2645.96, "total_tokens": 9220488} {"current_steps": 34385, "total_steps": 38150, "loss": 0.1364, "lr": 1.4695852654432463e-06, "epoch": 9.01310615989515, "percentage": 90.13, "elapsed_time": "0:58:05", "remaining_time": "0:06:21", "throughput": 2645.97, "total_tokens": 9221640} {"current_steps": 34390, "total_steps": 38150, "loss": 0.1565, "lr": 1.4657241719295362e-06, "epoch": 9.014416775884666, "percentage": 90.14, "elapsed_time": "0:58:05", "remaining_time": "0:06:21", "throughput": 2646.02, "total_tokens": 9223064} {"current_steps": 34395, "total_steps": 38150, "loss": 0.1609, "lr": 1.4618680040990983e-06, "epoch": 9.015727391874181, "percentage": 90.16, "elapsed_time": "0:58:06", "remaining_time": "0:06:20", "throughput": 2646.01, "total_tokens": 9224184} {"current_steps": 34400, "total_steps": 38150, "loss": 0.1754, "lr": 1.4580167627590153e-06, "epoch": 9.017038007863697, "percentage": 90.17, "elapsed_time": "0:58:06", "remaining_time": "0:06:20", "throughput": 2646.12, "total_tokens": 9225816} {"current_steps": 34405, "total_steps": 38150, "loss": 0.0781, "lr": 1.4541704487153474e-06, "epoch": 9.01834862385321, "percentage": 90.18, "elapsed_time": "0:58:06", "remaining_time": "0:06:19", "throughput": 2646.1, "total_tokens": 9226888} {"current_steps": 34410, "total_steps": 38150, "loss": 0.18, "lr": 1.4503290627731175e-06, "epoch": 9.019659239842726, "percentage": 90.2, "elapsed_time": "0:58:07", "remaining_time": "0:06:19", "throughput": 2646.28, "total_tokens": 9229096} {"current_steps": 34415, "total_steps": 38150, "loss": 0.1263, "lr": 1.4464926057363298e-06, "epoch": 9.020969855832242, "percentage": 90.21, "elapsed_time": "0:58:07", "remaining_time": "0:06:18", "throughput": 2646.19, "total_tokens": 9229896} {"current_steps": 34420, "total_steps": 38150, "loss": 0.1241, "lr": 1.4426610784079391e-06, "epoch": 9.022280471821757, "percentage": 90.22, "elapsed_time": "0:58:08", "remaining_time": "0:06:18", "throughput": 2646.15, "total_tokens": 9230872} {"current_steps": 34425, "total_steps": 38150, "loss": 0.1738, "lr": 1.438834481589882e-06, "epoch": 9.02359108781127, "percentage": 90.24, "elapsed_time": "0:58:08", "remaining_time": "0:06:17", "throughput": 2646.22, "total_tokens": 9232296} {"current_steps": 34430, "total_steps": 38150, "loss": 0.159, "lr": 1.4350128160830562e-06, "epoch": 9.024901703800786, "percentage": 90.25, "elapsed_time": "0:58:09", "remaining_time": "0:06:17", "throughput": 2646.3, "total_tokens": 9233880} {"current_steps": 34435, "total_steps": 38150, "loss": 0.1874, "lr": 1.4311960826873305e-06, "epoch": 9.026212319790302, "percentage": 90.26, "elapsed_time": "0:58:09", "remaining_time": "0:06:16", "throughput": 2646.31, "total_tokens": 9235000} {"current_steps": 34440, "total_steps": 38150, "loss": 0.1304, "lr": 1.427384282201541e-06, "epoch": 9.027522935779816, "percentage": 90.28, "elapsed_time": "0:58:10", "remaining_time": "0:06:15", "throughput": 2646.33, "total_tokens": 9236232} {"current_steps": 34445, "total_steps": 38150, "loss": 0.1504, "lr": 1.4235774154234855e-06, "epoch": 9.028833551769331, "percentage": 90.29, "elapsed_time": "0:58:10", "remaining_time": "0:06:15", "throughput": 2646.39, "total_tokens": 9237656} {"current_steps": 34450, "total_steps": 38150, "loss": 0.1436, "lr": 1.4197754831499488e-06, "epoch": 9.030144167758847, "percentage": 90.3, "elapsed_time": "0:58:11", "remaining_time": "0:06:14", "throughput": 2646.44, "total_tokens": 9238984} {"current_steps": 34455, "total_steps": 38150, "loss": 0.1083, "lr": 1.4159784861766584e-06, "epoch": 9.031454783748362, "percentage": 90.31, "elapsed_time": "0:58:11", "remaining_time": "0:06:14", "throughput": 2646.42, "total_tokens": 9240024} {"current_steps": 34460, "total_steps": 38150, "loss": 0.1469, "lr": 1.4121864252983174e-06, "epoch": 9.032765399737876, "percentage": 90.33, "elapsed_time": "0:58:11", "remaining_time": "0:06:13", "throughput": 2646.46, "total_tokens": 9241416} {"current_steps": 34465, "total_steps": 38150, "loss": 0.1163, "lr": 1.408399301308605e-06, "epoch": 9.034076015727392, "percentage": 90.34, "elapsed_time": "0:58:12", "remaining_time": "0:06:13", "throughput": 2646.5, "total_tokens": 9242712} {"current_steps": 34470, "total_steps": 38150, "loss": 0.2262, "lr": 1.4046171150001508e-06, "epoch": 9.035386631716907, "percentage": 90.35, "elapsed_time": "0:58:12", "remaining_time": "0:06:12", "throughput": 2646.62, "total_tokens": 9244584} {"current_steps": 34475, "total_steps": 38150, "loss": 0.145, "lr": 1.4008398671645688e-06, "epoch": 9.036697247706423, "percentage": 90.37, "elapsed_time": "0:58:13", "remaining_time": "0:06:12", "throughput": 2646.67, "total_tokens": 9246040} {"current_steps": 34480, "total_steps": 38150, "loss": 0.1216, "lr": 1.3970675585924241e-06, "epoch": 9.038007863695936, "percentage": 90.38, "elapsed_time": "0:58:13", "remaining_time": "0:06:11", "throughput": 2646.61, "total_tokens": 9246936} {"current_steps": 34485, "total_steps": 38150, "loss": 0.2038, "lr": 1.3933001900732572e-06, "epoch": 9.039318479685452, "percentage": 90.39, "elapsed_time": "0:58:14", "remaining_time": "0:06:11", "throughput": 2646.6, "total_tokens": 9248104} {"current_steps": 34490, "total_steps": 38150, "loss": 0.1093, "lr": 1.3895377623955707e-06, "epoch": 9.040629095674968, "percentage": 90.41, "elapsed_time": "0:58:14", "remaining_time": "0:06:10", "throughput": 2646.69, "total_tokens": 9249848} {"current_steps": 34495, "total_steps": 38150, "loss": 0.1492, "lr": 1.3857802763468403e-06, "epoch": 9.041939711664483, "percentage": 90.42, "elapsed_time": "0:58:15", "remaining_time": "0:06:10", "throughput": 2646.73, "total_tokens": 9251144} {"current_steps": 34500, "total_steps": 38150, "loss": 0.1774, "lr": 1.3820277327134866e-06, "epoch": 9.043250327653997, "percentage": 90.43, "elapsed_time": "0:58:15", "remaining_time": "0:06:09", "throughput": 2646.76, "total_tokens": 9252472} {"current_steps": 34505, "total_steps": 38150, "loss": 0.1038, "lr": 1.3782801322809262e-06, "epoch": 9.044560943643512, "percentage": 90.45, "elapsed_time": "0:58:16", "remaining_time": "0:06:09", "throughput": 2646.75, "total_tokens": 9253576} {"current_steps": 34510, "total_steps": 38150, "loss": 0.0978, "lr": 1.374537475833515e-06, "epoch": 9.045871559633028, "percentage": 90.46, "elapsed_time": "0:58:16", "remaining_time": "0:06:08", "throughput": 2646.82, "total_tokens": 9254968} {"current_steps": 34515, "total_steps": 38150, "loss": 0.3177, "lr": 1.37079976415459e-06, "epoch": 9.047182175622543, "percentage": 90.47, "elapsed_time": "0:58:17", "remaining_time": "0:06:08", "throughput": 2646.9, "total_tokens": 9256440} {"current_steps": 34520, "total_steps": 38150, "loss": 0.102, "lr": 1.3670669980264477e-06, "epoch": 9.048492791612057, "percentage": 90.48, "elapsed_time": "0:58:17", "remaining_time": "0:06:07", "throughput": 2646.93, "total_tokens": 9257688} {"current_steps": 34525, "total_steps": 38150, "loss": 0.096, "lr": 1.3633391782303468e-06, "epoch": 9.049803407601573, "percentage": 90.5, "elapsed_time": "0:58:17", "remaining_time": "0:06:07", "throughput": 2646.89, "total_tokens": 9258664} {"current_steps": 34530, "total_steps": 38150, "loss": 0.1393, "lr": 1.3596163055465154e-06, "epoch": 9.051114023591088, "percentage": 90.51, "elapsed_time": "0:58:18", "remaining_time": "0:06:06", "throughput": 2646.99, "total_tokens": 9260344} {"current_steps": 34535, "total_steps": 38150, "loss": 0.2531, "lr": 1.3558983807541476e-06, "epoch": 9.052424639580602, "percentage": 90.52, "elapsed_time": "0:58:19", "remaining_time": "0:06:06", "throughput": 2647.22, "total_tokens": 9263144} {"current_steps": 34540, "total_steps": 38150, "loss": 0.1483, "lr": 1.3521854046313897e-06, "epoch": 9.053735255570118, "percentage": 90.54, "elapsed_time": "0:58:19", "remaining_time": "0:06:05", "throughput": 2647.18, "total_tokens": 9264136} {"current_steps": 34545, "total_steps": 38150, "loss": 0.2474, "lr": 1.3484773779553677e-06, "epoch": 9.055045871559633, "percentage": 90.55, "elapsed_time": "0:58:20", "remaining_time": "0:06:05", "throughput": 2647.4, "total_tokens": 9266360} {"current_steps": 34550, "total_steps": 38150, "loss": 0.1734, "lr": 1.3447743015021636e-06, "epoch": 9.056356487549149, "percentage": 90.56, "elapsed_time": "0:58:20", "remaining_time": "0:06:04", "throughput": 2647.41, "total_tokens": 9267624} {"current_steps": 34555, "total_steps": 38150, "loss": 0.2555, "lr": 1.3410761760468265e-06, "epoch": 9.057667103538662, "percentage": 90.58, "elapsed_time": "0:58:21", "remaining_time": "0:06:04", "throughput": 2647.48, "total_tokens": 9269112} {"current_steps": 34560, "total_steps": 38150, "loss": 0.1492, "lr": 1.3373830023633598e-06, "epoch": 9.058977719528178, "percentage": 90.59, "elapsed_time": "0:58:21", "remaining_time": "0:06:03", "throughput": 2647.53, "total_tokens": 9270440} {"current_steps": 34565, "total_steps": 38150, "loss": 0.0656, "lr": 1.3336947812247507e-06, "epoch": 9.060288335517694, "percentage": 90.6, "elapsed_time": "0:58:21", "remaining_time": "0:06:03", "throughput": 2647.56, "total_tokens": 9271704} {"current_steps": 34570, "total_steps": 38150, "loss": 0.1005, "lr": 1.3300115134029345e-06, "epoch": 9.061598951507209, "percentage": 90.62, "elapsed_time": "0:58:22", "remaining_time": "0:06:02", "throughput": 2647.58, "total_tokens": 9272984} {"current_steps": 34575, "total_steps": 38150, "loss": 0.0792, "lr": 1.3263331996688055e-06, "epoch": 9.062909567496723, "percentage": 90.63, "elapsed_time": "0:58:22", "remaining_time": "0:06:02", "throughput": 2647.65, "total_tokens": 9274488} {"current_steps": 34580, "total_steps": 38150, "loss": 0.1451, "lr": 1.3226598407922342e-06, "epoch": 9.064220183486238, "percentage": 90.64, "elapsed_time": "0:58:23", "remaining_time": "0:06:01", "throughput": 2647.8, "total_tokens": 9276504} {"current_steps": 34585, "total_steps": 38150, "loss": 0.1227, "lr": 1.318991437542047e-06, "epoch": 9.065530799475754, "percentage": 90.66, "elapsed_time": "0:58:23", "remaining_time": "0:06:01", "throughput": 2647.9, "total_tokens": 9278200} {"current_steps": 34590, "total_steps": 38150, "loss": 0.1853, "lr": 1.3153279906860355e-06, "epoch": 9.06684141546527, "percentage": 90.67, "elapsed_time": "0:58:24", "remaining_time": "0:06:00", "throughput": 2647.98, "total_tokens": 9279880} {"current_steps": 34595, "total_steps": 38150, "loss": 0.0736, "lr": 1.3116695009909474e-06, "epoch": 9.068152031454783, "percentage": 90.68, "elapsed_time": "0:58:24", "remaining_time": "0:06:00", "throughput": 2647.97, "total_tokens": 9280952} {"current_steps": 34600, "total_steps": 38150, "loss": 0.1508, "lr": 1.3080159692225063e-06, "epoch": 9.069462647444299, "percentage": 90.69, "elapsed_time": "0:58:25", "remaining_time": "0:05:59", "throughput": 2647.95, "total_tokens": 9282008} {"current_steps": 34605, "total_steps": 38150, "loss": 0.1743, "lr": 1.304367396145384e-06, "epoch": 9.070773263433814, "percentage": 90.71, "elapsed_time": "0:58:25", "remaining_time": "0:05:59", "throughput": 2647.98, "total_tokens": 9283304} {"current_steps": 34610, "total_steps": 38150, "loss": 0.1464, "lr": 1.300723782523225e-06, "epoch": 9.07208387942333, "percentage": 90.72, "elapsed_time": "0:58:26", "remaining_time": "0:05:58", "throughput": 2648.04, "total_tokens": 9284696} {"current_steps": 34615, "total_steps": 38150, "loss": 0.1031, "lr": 1.2970851291186276e-06, "epoch": 9.073394495412844, "percentage": 90.73, "elapsed_time": "0:58:26", "remaining_time": "0:05:58", "throughput": 2648.03, "total_tokens": 9285880} {"current_steps": 34620, "total_steps": 38150, "loss": 0.0628, "lr": 1.2934514366931578e-06, "epoch": 9.07470511140236, "percentage": 90.75, "elapsed_time": "0:58:27", "remaining_time": "0:05:57", "throughput": 2648.06, "total_tokens": 9287112} {"current_steps": 34625, "total_steps": 38150, "loss": 0.1496, "lr": 1.2898227060073403e-06, "epoch": 9.076015727391875, "percentage": 90.76, "elapsed_time": "0:58:27", "remaining_time": "0:05:57", "throughput": 2648.12, "total_tokens": 9288488} {"current_steps": 34630, "total_steps": 38150, "loss": 0.167, "lr": 1.2861989378206624e-06, "epoch": 9.077326343381388, "percentage": 90.77, "elapsed_time": "0:58:28", "remaining_time": "0:05:56", "throughput": 2648.16, "total_tokens": 9290072} {"current_steps": 34635, "total_steps": 38150, "loss": 0.1147, "lr": 1.2825801328915699e-06, "epoch": 9.078636959370904, "percentage": 90.79, "elapsed_time": "0:58:28", "remaining_time": "0:05:56", "throughput": 2648.15, "total_tokens": 9291160} {"current_steps": 34640, "total_steps": 38150, "loss": 0.1305, "lr": 1.2789662919774792e-06, "epoch": 9.07994757536042, "percentage": 90.8, "elapsed_time": "0:58:29", "remaining_time": "0:05:55", "throughput": 2648.16, "total_tokens": 9292408} {"current_steps": 34645, "total_steps": 38150, "loss": 0.2224, "lr": 1.2753574158347547e-06, "epoch": 9.081258191349935, "percentage": 90.81, "elapsed_time": "0:58:29", "remaining_time": "0:05:55", "throughput": 2648.3, "total_tokens": 9294296} {"current_steps": 34650, "total_steps": 38150, "loss": 0.1947, "lr": 1.271753505218734e-06, "epoch": 9.082568807339449, "percentage": 90.83, "elapsed_time": "0:58:29", "remaining_time": "0:05:54", "throughput": 2648.26, "total_tokens": 9295256} {"current_steps": 34655, "total_steps": 38150, "loss": 0.1681, "lr": 1.2681545608837026e-06, "epoch": 9.083879423328964, "percentage": 90.84, "elapsed_time": "0:58:30", "remaining_time": "0:05:54", "throughput": 2648.32, "total_tokens": 9296696} {"current_steps": 34660, "total_steps": 38150, "loss": 0.1845, "lr": 1.2645605835829132e-06, "epoch": 9.08519003931848, "percentage": 90.85, "elapsed_time": "0:58:30", "remaining_time": "0:05:53", "throughput": 2648.48, "total_tokens": 9298792} {"current_steps": 34665, "total_steps": 38150, "loss": 0.1584, "lr": 1.2609715740685869e-06, "epoch": 9.086500655307995, "percentage": 90.87, "elapsed_time": "0:58:31", "remaining_time": "0:05:53", "throughput": 2648.56, "total_tokens": 9300456} {"current_steps": 34670, "total_steps": 38150, "loss": 0.1368, "lr": 1.257387533091889e-06, "epoch": 9.08781127129751, "percentage": 90.88, "elapsed_time": "0:58:32", "remaining_time": "0:05:52", "throughput": 2648.65, "total_tokens": 9302104} {"current_steps": 34675, "total_steps": 38150, "loss": 0.1281, "lr": 1.2538084614029527e-06, "epoch": 9.089121887287025, "percentage": 90.89, "elapsed_time": "0:58:32", "remaining_time": "0:05:52", "throughput": 2648.66, "total_tokens": 9303256} {"current_steps": 34680, "total_steps": 38150, "loss": 0.1144, "lr": 1.2502343597508792e-06, "epoch": 9.09043250327654, "percentage": 90.9, "elapsed_time": "0:58:32", "remaining_time": "0:05:51", "throughput": 2648.73, "total_tokens": 9304776} {"current_steps": 34685, "total_steps": 38150, "loss": 0.4498, "lr": 1.2466652288837227e-06, "epoch": 9.091743119266056, "percentage": 90.92, "elapsed_time": "0:58:33", "remaining_time": "0:05:50", "throughput": 2648.8, "total_tokens": 9306296} {"current_steps": 34690, "total_steps": 38150, "loss": 0.2163, "lr": 1.2431010695484858e-06, "epoch": 9.09305373525557, "percentage": 90.93, "elapsed_time": "0:58:33", "remaining_time": "0:05:50", "throughput": 2648.89, "total_tokens": 9307800} {"current_steps": 34695, "total_steps": 38150, "loss": 0.1519, "lr": 1.2395418824911464e-06, "epoch": 9.094364351245085, "percentage": 90.94, "elapsed_time": "0:58:34", "remaining_time": "0:05:49", "throughput": 2648.93, "total_tokens": 9309128} {"current_steps": 34700, "total_steps": 38150, "loss": 0.1188, "lr": 1.2359876684566368e-06, "epoch": 9.0956749672346, "percentage": 90.96, "elapsed_time": "0:58:34", "remaining_time": "0:05:49", "throughput": 2648.99, "total_tokens": 9310520} {"current_steps": 34705, "total_steps": 38150, "loss": 0.1711, "lr": 1.232438428188848e-06, "epoch": 9.096985583224116, "percentage": 90.97, "elapsed_time": "0:58:35", "remaining_time": "0:05:48", "throughput": 2648.99, "total_tokens": 9311640} {"current_steps": 34710, "total_steps": 38150, "loss": 0.0791, "lr": 1.228894162430627e-06, "epoch": 9.09829619921363, "percentage": 90.98, "elapsed_time": "0:58:35", "remaining_time": "0:05:48", "throughput": 2648.94, "total_tokens": 9312568} {"current_steps": 34715, "total_steps": 38150, "loss": 0.163, "lr": 1.225354871923784e-06, "epoch": 9.099606815203146, "percentage": 91.0, "elapsed_time": "0:58:36", "remaining_time": "0:05:47", "throughput": 2649.05, "total_tokens": 9314424} {"current_steps": 34720, "total_steps": 38150, "loss": 0.1428, "lr": 1.2218205574090896e-06, "epoch": 9.100917431192661, "percentage": 91.01, "elapsed_time": "0:58:36", "remaining_time": "0:05:47", "throughput": 2649.16, "total_tokens": 9316008} {"current_steps": 34725, "total_steps": 38150, "loss": 0.0967, "lr": 1.2182912196262664e-06, "epoch": 9.102228047182175, "percentage": 91.02, "elapsed_time": "0:58:37", "remaining_time": "0:05:46", "throughput": 2649.16, "total_tokens": 9317128} {"current_steps": 34730, "total_steps": 38150, "loss": 0.1768, "lr": 1.2147668593139982e-06, "epoch": 9.10353866317169, "percentage": 91.04, "elapsed_time": "0:58:37", "remaining_time": "0:05:46", "throughput": 2649.15, "total_tokens": 9318216} {"current_steps": 34735, "total_steps": 38150, "loss": 0.1157, "lr": 1.2112474772099285e-06, "epoch": 9.104849279161206, "percentage": 91.05, "elapsed_time": "0:58:37", "remaining_time": "0:05:45", "throughput": 2649.1, "total_tokens": 9319208} {"current_steps": 34740, "total_steps": 38150, "loss": 0.0961, "lr": 1.2077330740506598e-06, "epoch": 9.106159895150721, "percentage": 91.06, "elapsed_time": "0:58:38", "remaining_time": "0:05:45", "throughput": 2649.08, "total_tokens": 9320248} {"current_steps": 34745, "total_steps": 38150, "loss": 0.1397, "lr": 1.2042236505717452e-06, "epoch": 9.107470511140235, "percentage": 91.07, "elapsed_time": "0:58:38", "remaining_time": "0:05:44", "throughput": 2649.18, "total_tokens": 9321912} {"current_steps": 34750, "total_steps": 38150, "loss": 0.0796, "lr": 1.2007192075077085e-06, "epoch": 9.10878112712975, "percentage": 91.09, "elapsed_time": "0:58:39", "remaining_time": "0:05:44", "throughput": 2649.19, "total_tokens": 9323080} {"current_steps": 34755, "total_steps": 38150, "loss": 0.1885, "lr": 1.1972197455920181e-06, "epoch": 9.110091743119266, "percentage": 91.1, "elapsed_time": "0:58:39", "remaining_time": "0:05:43", "throughput": 2649.22, "total_tokens": 9324328} {"current_steps": 34760, "total_steps": 38150, "loss": 0.0718, "lr": 1.193725265557108e-06, "epoch": 9.111402359108782, "percentage": 91.11, "elapsed_time": "0:58:40", "remaining_time": "0:05:43", "throughput": 2649.18, "total_tokens": 9325320} {"current_steps": 34765, "total_steps": 38150, "loss": 0.1501, "lr": 1.1902357681343623e-06, "epoch": 9.112712975098296, "percentage": 91.13, "elapsed_time": "0:58:40", "remaining_time": "0:05:42", "throughput": 2649.22, "total_tokens": 9326632} {"current_steps": 34770, "total_steps": 38150, "loss": 0.1596, "lr": 1.1867512540541388e-06, "epoch": 9.114023591087811, "percentage": 91.14, "elapsed_time": "0:58:40", "remaining_time": "0:05:42", "throughput": 2649.22, "total_tokens": 9327768} {"current_steps": 34775, "total_steps": 38150, "loss": 0.1639, "lr": 1.1832717240457231e-06, "epoch": 9.115334207077327, "percentage": 91.15, "elapsed_time": "0:58:41", "remaining_time": "0:05:41", "throughput": 2649.29, "total_tokens": 9329176} {"current_steps": 34780, "total_steps": 38150, "loss": 0.117, "lr": 1.1797971788373857e-06, "epoch": 9.116644823066842, "percentage": 91.17, "elapsed_time": "0:58:41", "remaining_time": "0:05:41", "throughput": 2649.32, "total_tokens": 9330504} {"current_steps": 34785, "total_steps": 38150, "loss": 0.1127, "lr": 1.1763276191563422e-06, "epoch": 9.117955439056356, "percentage": 91.18, "elapsed_time": "0:58:42", "remaining_time": "0:05:40", "throughput": 2649.35, "total_tokens": 9331768} {"current_steps": 34790, "total_steps": 38150, "loss": 0.1515, "lr": 1.1728630457287587e-06, "epoch": 9.119266055045872, "percentage": 91.19, "elapsed_time": "0:58:42", "remaining_time": "0:05:40", "throughput": 2649.34, "total_tokens": 9332824} {"current_steps": 34795, "total_steps": 38150, "loss": 0.1921, "lr": 1.1694034592797747e-06, "epoch": 9.120576671035387, "percentage": 91.21, "elapsed_time": "0:58:43", "remaining_time": "0:05:39", "throughput": 2649.47, "total_tokens": 9334616} {"current_steps": 34800, "total_steps": 38150, "loss": 0.1543, "lr": 1.1659488605334695e-06, "epoch": 9.1218872870249, "percentage": 91.22, "elapsed_time": "0:58:43", "remaining_time": "0:05:39", "throughput": 2649.5, "total_tokens": 9335864} {"current_steps": 34805, "total_steps": 38150, "loss": 0.2221, "lr": 1.1624992502128868e-06, "epoch": 9.123197903014416, "percentage": 91.23, "elapsed_time": "0:58:44", "remaining_time": "0:05:38", "throughput": 2649.57, "total_tokens": 9337336} {"current_steps": 34810, "total_steps": 38150, "loss": 0.0952, "lr": 1.159054629040024e-06, "epoch": 9.124508519003932, "percentage": 91.25, "elapsed_time": "0:58:44", "remaining_time": "0:05:38", "throughput": 2649.59, "total_tokens": 9338600} {"current_steps": 34815, "total_steps": 38150, "loss": 0.0829, "lr": 1.1556149977358295e-06, "epoch": 9.125819134993447, "percentage": 91.26, "elapsed_time": "0:58:44", "remaining_time": "0:05:37", "throughput": 2649.58, "total_tokens": 9339704} {"current_steps": 34820, "total_steps": 38150, "loss": 0.0637, "lr": 1.1521803570202188e-06, "epoch": 9.127129750982961, "percentage": 91.27, "elapsed_time": "0:58:45", "remaining_time": "0:05:37", "throughput": 2649.55, "total_tokens": 9340712} {"current_steps": 34825, "total_steps": 38150, "loss": 0.0985, "lr": 1.1487507076120507e-06, "epoch": 9.128440366972477, "percentage": 91.28, "elapsed_time": "0:58:45", "remaining_time": "0:05:36", "throughput": 2649.49, "total_tokens": 9341640} {"current_steps": 34830, "total_steps": 38150, "loss": 0.2647, "lr": 1.1453260502291507e-06, "epoch": 9.129750982961992, "percentage": 91.3, "elapsed_time": "0:58:46", "remaining_time": "0:05:36", "throughput": 2649.55, "total_tokens": 9343096} {"current_steps": 34835, "total_steps": 38150, "loss": 0.1834, "lr": 1.14190638558829e-06, "epoch": 9.131061598951508, "percentage": 91.31, "elapsed_time": "0:58:46", "remaining_time": "0:05:35", "throughput": 2649.54, "total_tokens": 9344184} {"current_steps": 34840, "total_steps": 38150, "loss": 0.1414, "lr": 1.1384917144051987e-06, "epoch": 9.132372214941022, "percentage": 91.32, "elapsed_time": "0:58:47", "remaining_time": "0:05:35", "throughput": 2649.6, "total_tokens": 9345512} {"current_steps": 34845, "total_steps": 38150, "loss": 0.1609, "lr": 1.135082037394561e-06, "epoch": 9.133682830930537, "percentage": 91.34, "elapsed_time": "0:58:47", "remaining_time": "0:05:34", "throughput": 2649.66, "total_tokens": 9346888} {"current_steps": 34850, "total_steps": 38150, "loss": 0.1729, "lr": 1.1316773552700193e-06, "epoch": 9.134993446920053, "percentage": 91.35, "elapsed_time": "0:58:48", "remaining_time": "0:05:34", "throughput": 2649.66, "total_tokens": 9348104} {"current_steps": 34855, "total_steps": 38150, "loss": 0.2714, "lr": 1.1282776687441626e-06, "epoch": 9.136304062909568, "percentage": 91.36, "elapsed_time": "0:58:48", "remaining_time": "0:05:33", "throughput": 2649.74, "total_tokens": 9349640} {"current_steps": 34860, "total_steps": 38150, "loss": 0.1335, "lr": 1.1248829785285463e-06, "epoch": 9.137614678899082, "percentage": 91.38, "elapsed_time": "0:58:48", "remaining_time": "0:05:33", "throughput": 2649.79, "total_tokens": 9350984} {"current_steps": 34865, "total_steps": 38150, "loss": 0.1795, "lr": 1.121493285333669e-06, "epoch": 9.138925294888598, "percentage": 91.39, "elapsed_time": "0:58:49", "remaining_time": "0:05:32", "throughput": 2649.8, "total_tokens": 9352200} {"current_steps": 34870, "total_steps": 38150, "loss": 0.1716, "lr": 1.1181085898689881e-06, "epoch": 9.140235910878113, "percentage": 91.4, "elapsed_time": "0:58:49", "remaining_time": "0:05:32", "throughput": 2649.84, "total_tokens": 9353656} {"current_steps": 34875, "total_steps": 38150, "loss": 0.1022, "lr": 1.1147288928429118e-06, "epoch": 9.141546526867629, "percentage": 91.42, "elapsed_time": "0:58:50", "remaining_time": "0:05:31", "throughput": 2649.89, "total_tokens": 9355032} {"current_steps": 34880, "total_steps": 38150, "loss": 0.1428, "lr": 1.1113541949628104e-06, "epoch": 9.142857142857142, "percentage": 91.43, "elapsed_time": "0:58:50", "remaining_time": "0:05:31", "throughput": 2649.9, "total_tokens": 9356248} {"current_steps": 34885, "total_steps": 38150, "loss": 0.0908, "lr": 1.1079844969350023e-06, "epoch": 9.144167758846658, "percentage": 91.44, "elapsed_time": "0:58:51", "remaining_time": "0:05:30", "throughput": 2649.9, "total_tokens": 9357480} {"current_steps": 34890, "total_steps": 38150, "loss": 0.0967, "lr": 1.104619799464754e-06, "epoch": 9.145478374836173, "percentage": 91.45, "elapsed_time": "0:58:51", "remaining_time": "0:05:29", "throughput": 2649.86, "total_tokens": 9358472} {"current_steps": 34895, "total_steps": 38150, "loss": 0.1963, "lr": 1.1012601032562935e-06, "epoch": 9.146788990825687, "percentage": 91.47, "elapsed_time": "0:58:52", "remaining_time": "0:05:29", "throughput": 2649.93, "total_tokens": 9360072} {"current_steps": 34900, "total_steps": 38150, "loss": 0.2048, "lr": 1.0979054090127978e-06, "epoch": 9.148099606815203, "percentage": 91.48, "elapsed_time": "0:58:52", "remaining_time": "0:05:28", "throughput": 2649.97, "total_tokens": 9361432} {"current_steps": 34905, "total_steps": 38150, "loss": 0.1228, "lr": 1.094555717436399e-06, "epoch": 9.149410222804718, "percentage": 91.49, "elapsed_time": "0:58:53", "remaining_time": "0:05:28", "throughput": 2649.98, "total_tokens": 9362600} {"current_steps": 34910, "total_steps": 38150, "loss": 0.1344, "lr": 1.0912110292281868e-06, "epoch": 9.150720838794234, "percentage": 91.51, "elapsed_time": "0:58:53", "remaining_time": "0:05:27", "throughput": 2650.01, "total_tokens": 9363832} {"current_steps": 34915, "total_steps": 38150, "loss": 0.1501, "lr": 1.0878713450881928e-06, "epoch": 9.152031454783748, "percentage": 91.52, "elapsed_time": "0:58:53", "remaining_time": "0:05:27", "throughput": 2650.05, "total_tokens": 9365160} {"current_steps": 34920, "total_steps": 38150, "loss": 0.538, "lr": 1.084536665715416e-06, "epoch": 9.153342070773263, "percentage": 91.53, "elapsed_time": "0:58:54", "remaining_time": "0:05:26", "throughput": 2650.09, "total_tokens": 9366504} {"current_steps": 34925, "total_steps": 38150, "loss": 0.1288, "lr": 1.0812069918077844e-06, "epoch": 9.154652686762779, "percentage": 91.55, "elapsed_time": "0:58:54", "remaining_time": "0:05:26", "throughput": 2650.11, "total_tokens": 9367768} {"current_steps": 34930, "total_steps": 38150, "loss": 0.0966, "lr": 1.0778823240622043e-06, "epoch": 9.155963302752294, "percentage": 91.56, "elapsed_time": "0:58:55", "remaining_time": "0:05:25", "throughput": 2650.1, "total_tokens": 9368872} {"current_steps": 34935, "total_steps": 38150, "loss": 0.2438, "lr": 1.0745626631745193e-06, "epoch": 9.157273918741808, "percentage": 91.57, "elapsed_time": "0:58:56", "remaining_time": "0:05:25", "throughput": 2650.33, "total_tokens": 9371912} {"current_steps": 34940, "total_steps": 38150, "loss": 0.1814, "lr": 1.0712480098395289e-06, "epoch": 9.158584534731324, "percentage": 91.59, "elapsed_time": "0:58:56", "remaining_time": "0:05:24", "throughput": 2650.42, "total_tokens": 9373624} {"current_steps": 34945, "total_steps": 38150, "loss": 0.0823, "lr": 1.0679383647509839e-06, "epoch": 9.159895150720839, "percentage": 91.6, "elapsed_time": "0:58:57", "remaining_time": "0:05:24", "throughput": 2650.45, "total_tokens": 9374984} {"current_steps": 34950, "total_steps": 38150, "loss": 0.1105, "lr": 1.0646337286015856e-06, "epoch": 9.161205766710355, "percentage": 91.61, "elapsed_time": "0:58:57", "remaining_time": "0:05:23", "throughput": 2650.4, "total_tokens": 9375880} {"current_steps": 34955, "total_steps": 38150, "loss": 0.1656, "lr": 1.0613341020829948e-06, "epoch": 9.162516382699868, "percentage": 91.63, "elapsed_time": "0:58:57", "remaining_time": "0:05:23", "throughput": 2650.42, "total_tokens": 9377112} {"current_steps": 34960, "total_steps": 38150, "loss": 0.1097, "lr": 1.0580394858858117e-06, "epoch": 9.163826998689384, "percentage": 91.64, "elapsed_time": "0:58:58", "remaining_time": "0:05:22", "throughput": 2650.39, "total_tokens": 9378120} {"current_steps": 34965, "total_steps": 38150, "loss": 0.0706, "lr": 1.054749880699593e-06, "epoch": 9.1651376146789, "percentage": 91.65, "elapsed_time": "0:58:58", "remaining_time": "0:05:22", "throughput": 2650.38, "total_tokens": 9379192} {"current_steps": 34970, "total_steps": 38150, "loss": 0.1327, "lr": 1.051465287212855e-06, "epoch": 9.166448230668415, "percentage": 91.66, "elapsed_time": "0:58:59", "remaining_time": "0:05:21", "throughput": 2650.38, "total_tokens": 9380312} {"current_steps": 34975, "total_steps": 38150, "loss": 0.1497, "lr": 1.04818570611305e-06, "epoch": 9.167758846657929, "percentage": 91.68, "elapsed_time": "0:58:59", "remaining_time": "0:05:21", "throughput": 2650.48, "total_tokens": 9381976} {"current_steps": 34980, "total_steps": 38150, "loss": 0.0621, "lr": 1.0449111380865906e-06, "epoch": 9.169069462647444, "percentage": 91.69, "elapsed_time": "0:59:00", "remaining_time": "0:05:20", "throughput": 2650.45, "total_tokens": 9383000} {"current_steps": 34985, "total_steps": 38150, "loss": 0.2581, "lr": 1.0416415838188393e-06, "epoch": 9.17038007863696, "percentage": 91.7, "elapsed_time": "0:59:00", "remaining_time": "0:05:20", "throughput": 2650.47, "total_tokens": 9384264} {"current_steps": 34990, "total_steps": 38150, "loss": 0.0427, "lr": 1.038377043994107e-06, "epoch": 9.171690694626474, "percentage": 91.72, "elapsed_time": "0:59:01", "remaining_time": "0:05:19", "throughput": 2650.52, "total_tokens": 9385640} {"current_steps": 34995, "total_steps": 38150, "loss": 0.1769, "lr": 1.0351175192956585e-06, "epoch": 9.17300131061599, "percentage": 91.73, "elapsed_time": "0:59:01", "remaining_time": "0:05:19", "throughput": 2650.59, "total_tokens": 9387160} {"current_steps": 35000, "total_steps": 38150, "loss": 0.2095, "lr": 1.0318630104057037e-06, "epoch": 9.174311926605505, "percentage": 91.74, "elapsed_time": "0:59:01", "remaining_time": "0:05:18", "throughput": 2650.58, "total_tokens": 9388248} {"current_steps": 35005, "total_steps": 38150, "loss": 0.0839, "lr": 1.0286135180054114e-06, "epoch": 9.17562254259502, "percentage": 91.76, "elapsed_time": "0:59:02", "remaining_time": "0:05:18", "throughput": 2650.59, "total_tokens": 9389480} {"current_steps": 35010, "total_steps": 38150, "loss": 0.2077, "lr": 1.0253690427748874e-06, "epoch": 9.176933158584534, "percentage": 91.77, "elapsed_time": "0:59:02", "remaining_time": "0:05:17", "throughput": 2650.65, "total_tokens": 9390856} {"current_steps": 35015, "total_steps": 38150, "loss": 0.0754, "lr": 1.0221295853931973e-06, "epoch": 9.17824377457405, "percentage": 91.78, "elapsed_time": "0:59:03", "remaining_time": "0:05:17", "throughput": 2650.74, "total_tokens": 9392488} {"current_steps": 35020, "total_steps": 38150, "loss": 0.1409, "lr": 1.0188951465383511e-06, "epoch": 9.179554390563565, "percentage": 91.8, "elapsed_time": "0:59:03", "remaining_time": "0:05:16", "throughput": 2650.83, "total_tokens": 9394072} {"current_steps": 35025, "total_steps": 38150, "loss": 0.08, "lr": 1.015665726887316e-06, "epoch": 9.18086500655308, "percentage": 91.81, "elapsed_time": "0:59:04", "remaining_time": "0:05:16", "throughput": 2650.84, "total_tokens": 9395288} {"current_steps": 35030, "total_steps": 38150, "loss": 0.1743, "lr": 1.0124413271160038e-06, "epoch": 9.182175622542594, "percentage": 91.82, "elapsed_time": "0:59:04", "remaining_time": "0:05:15", "throughput": 2650.86, "total_tokens": 9396472} {"current_steps": 35035, "total_steps": 38150, "loss": 0.1195, "lr": 1.0092219478992776e-06, "epoch": 9.18348623853211, "percentage": 91.83, "elapsed_time": "0:59:05", "remaining_time": "0:05:15", "throughput": 2650.9, "total_tokens": 9397832} {"current_steps": 35040, "total_steps": 38150, "loss": 0.1758, "lr": 1.0060075899109427e-06, "epoch": 9.184796854521625, "percentage": 91.85, "elapsed_time": "0:59:05", "remaining_time": "0:05:14", "throughput": 2650.97, "total_tokens": 9399256} {"current_steps": 35045, "total_steps": 38150, "loss": 0.1686, "lr": 1.0027982538237612e-06, "epoch": 9.186107470511141, "percentage": 91.86, "elapsed_time": "0:59:06", "remaining_time": "0:05:14", "throughput": 2651.11, "total_tokens": 9401176} {"current_steps": 35050, "total_steps": 38150, "loss": 0.1131, "lr": 9.995939403094402e-07, "epoch": 9.187418086500655, "percentage": 91.87, "elapsed_time": "0:59:06", "remaining_time": "0:05:13", "throughput": 2651.11, "total_tokens": 9402280} {"current_steps": 35055, "total_steps": 38150, "loss": 0.1472, "lr": 9.963946500386374e-07, "epoch": 9.18872870249017, "percentage": 91.89, "elapsed_time": "0:59:06", "remaining_time": "0:05:13", "throughput": 2651.09, "total_tokens": 9403352} {"current_steps": 35060, "total_steps": 38150, "loss": 0.2305, "lr": 9.932003836809616e-07, "epoch": 9.190039318479686, "percentage": 91.9, "elapsed_time": "0:59:07", "remaining_time": "0:05:12", "throughput": 2651.11, "total_tokens": 9404568} {"current_steps": 35065, "total_steps": 38150, "loss": 0.0603, "lr": 9.900111419049619e-07, "epoch": 9.191349934469201, "percentage": 91.91, "elapsed_time": "0:59:07", "remaining_time": "0:05:12", "throughput": 2651.05, "total_tokens": 9405496} {"current_steps": 35070, "total_steps": 38150, "loss": 0.126, "lr": 9.868269253781453e-07, "epoch": 9.192660550458715, "percentage": 91.93, "elapsed_time": "0:59:08", "remaining_time": "0:05:11", "throughput": 2651.12, "total_tokens": 9406904} {"current_steps": 35075, "total_steps": 38150, "loss": 0.1586, "lr": 9.836477347669626e-07, "epoch": 9.19397116644823, "percentage": 91.94, "elapsed_time": "0:59:08", "remaining_time": "0:05:11", "throughput": 2651.16, "total_tokens": 9408200} {"current_steps": 35080, "total_steps": 38150, "loss": 0.1456, "lr": 9.804735707368118e-07, "epoch": 9.195281782437746, "percentage": 91.95, "elapsed_time": "0:59:09", "remaining_time": "0:05:10", "throughput": 2651.18, "total_tokens": 9409448} {"current_steps": 35085, "total_steps": 38150, "loss": 0.1508, "lr": 9.773044339520392e-07, "epoch": 9.19659239842726, "percentage": 91.97, "elapsed_time": "0:59:09", "remaining_time": "0:05:10", "throughput": 2651.21, "total_tokens": 9410888} {"current_steps": 35090, "total_steps": 38150, "loss": 0.1031, "lr": 9.741403250759424e-07, "epoch": 9.197903014416775, "percentage": 91.98, "elapsed_time": "0:59:10", "remaining_time": "0:05:09", "throughput": 2651.18, "total_tokens": 9412008} {"current_steps": 35095, "total_steps": 38150, "loss": 0.1828, "lr": 9.709812447707606e-07, "epoch": 9.199213630406291, "percentage": 91.99, "elapsed_time": "0:59:10", "remaining_time": "0:05:09", "throughput": 2651.22, "total_tokens": 9413304} {"current_steps": 35100, "total_steps": 38150, "loss": 0.1257, "lr": 9.678271936976847e-07, "epoch": 9.200524246395807, "percentage": 92.01, "elapsed_time": "0:59:10", "remaining_time": "0:05:08", "throughput": 2651.23, "total_tokens": 9414440} {"current_steps": 35105, "total_steps": 38150, "loss": 0.1304, "lr": 9.64678172516853e-07, "epoch": 9.20183486238532, "percentage": 92.02, "elapsed_time": "0:59:11", "remaining_time": "0:05:08", "throughput": 2651.25, "total_tokens": 9415672} {"current_steps": 35110, "total_steps": 38150, "loss": 0.0989, "lr": 9.615341818873496e-07, "epoch": 9.203145478374836, "percentage": 92.03, "elapsed_time": "0:59:11", "remaining_time": "0:05:07", "throughput": 2651.27, "total_tokens": 9416872} {"current_steps": 35115, "total_steps": 38150, "loss": 0.1792, "lr": 9.583952224672094e-07, "epoch": 9.204456094364351, "percentage": 92.04, "elapsed_time": "0:59:12", "remaining_time": "0:05:07", "throughput": 2651.26, "total_tokens": 9417976} {"current_steps": 35120, "total_steps": 38150, "loss": 0.1556, "lr": 9.552612949134094e-07, "epoch": 9.205766710353867, "percentage": 92.06, "elapsed_time": "0:59:12", "remaining_time": "0:05:06", "throughput": 2651.34, "total_tokens": 9419496} {"current_steps": 35125, "total_steps": 38150, "loss": 0.1257, "lr": 9.521323998818694e-07, "epoch": 9.20707732634338, "percentage": 92.07, "elapsed_time": "0:59:13", "remaining_time": "0:05:06", "throughput": 2651.32, "total_tokens": 9420536} {"current_steps": 35130, "total_steps": 38150, "loss": 0.1689, "lr": 9.490085380274682e-07, "epoch": 9.208387942332896, "percentage": 92.08, "elapsed_time": "0:59:13", "remaining_time": "0:05:05", "throughput": 2651.44, "total_tokens": 9422248} {"current_steps": 35135, "total_steps": 38150, "loss": 0.1055, "lr": 9.45889710004022e-07, "epoch": 9.209698558322412, "percentage": 92.1, "elapsed_time": "0:59:14", "remaining_time": "0:05:04", "throughput": 2651.39, "total_tokens": 9423176} {"current_steps": 35140, "total_steps": 38150, "loss": 0.149, "lr": 9.427759164642974e-07, "epoch": 9.211009174311927, "percentage": 92.11, "elapsed_time": "0:59:14", "remaining_time": "0:05:04", "throughput": 2651.41, "total_tokens": 9424360} {"current_steps": 35145, "total_steps": 38150, "loss": 0.0628, "lr": 9.396671580600064e-07, "epoch": 9.212319790301441, "percentage": 92.12, "elapsed_time": "0:59:14", "remaining_time": "0:05:03", "throughput": 2651.39, "total_tokens": 9425384} {"current_steps": 35150, "total_steps": 38150, "loss": 0.1047, "lr": 9.36563435441809e-07, "epoch": 9.213630406290957, "percentage": 92.14, "elapsed_time": "0:59:15", "remaining_time": "0:05:03", "throughput": 2651.51, "total_tokens": 9427304} {"current_steps": 35155, "total_steps": 38150, "loss": 0.1065, "lr": 9.334647492593051e-07, "epoch": 9.214941022280472, "percentage": 92.15, "elapsed_time": "0:59:15", "remaining_time": "0:05:02", "throughput": 2651.52, "total_tokens": 9428472} {"current_steps": 35160, "total_steps": 38150, "loss": 0.2303, "lr": 9.303711001610454e-07, "epoch": 9.216251638269988, "percentage": 92.16, "elapsed_time": "0:59:16", "remaining_time": "0:05:02", "throughput": 2651.52, "total_tokens": 9429576} {"current_steps": 35165, "total_steps": 38150, "loss": 0.0546, "lr": 9.27282488794523e-07, "epoch": 9.217562254259501, "percentage": 92.18, "elapsed_time": "0:59:16", "remaining_time": "0:05:01", "throughput": 2651.47, "total_tokens": 9430504} {"current_steps": 35170, "total_steps": 38150, "loss": 0.1498, "lr": 9.24198915806182e-07, "epoch": 9.218872870249017, "percentage": 92.19, "elapsed_time": "0:59:17", "remaining_time": "0:05:01", "throughput": 2651.6, "total_tokens": 9432408} {"current_steps": 35175, "total_steps": 38150, "loss": 0.1078, "lr": 9.211203818414088e-07, "epoch": 9.220183486238533, "percentage": 92.2, "elapsed_time": "0:59:17", "remaining_time": "0:05:00", "throughput": 2651.61, "total_tokens": 9433592} {"current_steps": 35180, "total_steps": 38150, "loss": 0.1081, "lr": 9.180468875445352e-07, "epoch": 9.221494102228046, "percentage": 92.21, "elapsed_time": "0:59:18", "remaining_time": "0:05:00", "throughput": 2651.6, "total_tokens": 9434648} {"current_steps": 35185, "total_steps": 38150, "loss": 0.1067, "lr": 9.149784335588357e-07, "epoch": 9.222804718217562, "percentage": 92.23, "elapsed_time": "0:59:18", "remaining_time": "0:04:59", "throughput": 2651.66, "total_tokens": 9436152} {"current_steps": 35190, "total_steps": 38150, "loss": 0.0968, "lr": 9.119150205265326e-07, "epoch": 9.224115334207077, "percentage": 92.24, "elapsed_time": "0:59:19", "remaining_time": "0:04:59", "throughput": 2651.67, "total_tokens": 9437336} {"current_steps": 35195, "total_steps": 38150, "loss": 0.1056, "lr": 9.088566490888017e-07, "epoch": 9.225425950196593, "percentage": 92.25, "elapsed_time": "0:59:19", "remaining_time": "0:04:58", "throughput": 2651.72, "total_tokens": 9438728} {"current_steps": 35200, "total_steps": 38150, "loss": 0.1774, "lr": 9.058033198857424e-07, "epoch": 9.226736566186107, "percentage": 92.27, "elapsed_time": "0:59:19", "remaining_time": "0:04:58", "throughput": 2651.78, "total_tokens": 9440216} {"current_steps": 35205, "total_steps": 38150, "loss": 0.1298, "lr": 9.027550335564184e-07, "epoch": 9.228047182175622, "percentage": 92.28, "elapsed_time": "0:59:20", "remaining_time": "0:04:57", "throughput": 2651.74, "total_tokens": 9441208} {"current_steps": 35210, "total_steps": 38150, "loss": 0.1399, "lr": 8.997117907388275e-07, "epoch": 9.229357798165138, "percentage": 92.29, "elapsed_time": "0:59:20", "remaining_time": "0:04:57", "throughput": 2651.7, "total_tokens": 9442152} {"current_steps": 35215, "total_steps": 38150, "loss": 0.1252, "lr": 8.966735920699187e-07, "epoch": 9.230668414154653, "percentage": 92.31, "elapsed_time": "0:59:21", "remaining_time": "0:04:56", "throughput": 2651.76, "total_tokens": 9443528} {"current_steps": 35220, "total_steps": 38150, "loss": 0.0955, "lr": 8.936404381855806e-07, "epoch": 9.231979030144167, "percentage": 92.32, "elapsed_time": "0:59:21", "remaining_time": "0:04:56", "throughput": 2651.72, "total_tokens": 9444488} {"current_steps": 35225, "total_steps": 38150, "loss": 0.1082, "lr": 8.906123297206442e-07, "epoch": 9.233289646133683, "percentage": 92.33, "elapsed_time": "0:59:22", "remaining_time": "0:04:55", "throughput": 2651.74, "total_tokens": 9445720} {"current_steps": 35230, "total_steps": 38150, "loss": 0.13, "lr": 8.875892673088887e-07, "epoch": 9.234600262123198, "percentage": 92.35, "elapsed_time": "0:59:22", "remaining_time": "0:04:55", "throughput": 2651.78, "total_tokens": 9447064} {"current_steps": 35235, "total_steps": 38150, "loss": 0.1754, "lr": 8.845712515830385e-07, "epoch": 9.235910878112714, "percentage": 92.36, "elapsed_time": "0:59:22", "remaining_time": "0:04:54", "throughput": 2651.81, "total_tokens": 9448392} {"current_steps": 35240, "total_steps": 38150, "loss": 0.1675, "lr": 8.815582831747576e-07, "epoch": 9.237221494102227, "percentage": 92.37, "elapsed_time": "0:59:23", "remaining_time": "0:04:54", "throughput": 2651.89, "total_tokens": 9449912} {"current_steps": 35245, "total_steps": 38150, "loss": 0.2947, "lr": 8.785503627146501e-07, "epoch": 9.238532110091743, "percentage": 92.39, "elapsed_time": "0:59:23", "remaining_time": "0:04:53", "throughput": 2651.99, "total_tokens": 9451560} {"current_steps": 35250, "total_steps": 38150, "loss": 0.1788, "lr": 8.755474908322764e-07, "epoch": 9.239842726081259, "percentage": 92.4, "elapsed_time": "0:59:24", "remaining_time": "0:04:53", "throughput": 2652.03, "total_tokens": 9452984} {"current_steps": 35255, "total_steps": 38150, "loss": 0.2581, "lr": 8.725496681561279e-07, "epoch": 9.241153342070774, "percentage": 92.41, "elapsed_time": "0:59:24", "remaining_time": "0:04:52", "throughput": 2652.12, "total_tokens": 9454568} {"current_steps": 35260, "total_steps": 38150, "loss": 0.1898, "lr": 8.695568953136446e-07, "epoch": 9.242463958060288, "percentage": 92.42, "elapsed_time": "0:59:25", "remaining_time": "0:04:52", "throughput": 2652.17, "total_tokens": 9455880} {"current_steps": 35265, "total_steps": 38150, "loss": 0.1789, "lr": 8.665691729312115e-07, "epoch": 9.243774574049803, "percentage": 92.44, "elapsed_time": "0:59:25", "remaining_time": "0:04:51", "throughput": 2652.28, "total_tokens": 9457624} {"current_steps": 35270, "total_steps": 38150, "loss": 0.092, "lr": 8.635865016341477e-07, "epoch": 9.245085190039319, "percentage": 92.45, "elapsed_time": "0:59:26", "remaining_time": "0:04:51", "throughput": 2652.39, "total_tokens": 9459352} {"current_steps": 35275, "total_steps": 38150, "loss": 0.0666, "lr": 8.606088820467318e-07, "epoch": 9.246395806028833, "percentage": 92.46, "elapsed_time": "0:59:26", "remaining_time": "0:04:50", "throughput": 2652.35, "total_tokens": 9460328} {"current_steps": 35280, "total_steps": 38150, "loss": 0.2873, "lr": 8.576363147921596e-07, "epoch": 9.247706422018348, "percentage": 92.48, "elapsed_time": "0:59:27", "remaining_time": "0:04:50", "throughput": 2652.42, "total_tokens": 9461880} {"current_steps": 35285, "total_steps": 38150, "loss": 0.0687, "lr": 8.546688004925946e-07, "epoch": 9.249017038007864, "percentage": 92.49, "elapsed_time": "0:59:27", "remaining_time": "0:04:49", "throughput": 2652.48, "total_tokens": 9463336} {"current_steps": 35290, "total_steps": 38150, "loss": 0.1179, "lr": 8.517063397691288e-07, "epoch": 9.25032765399738, "percentage": 92.5, "elapsed_time": "0:59:28", "remaining_time": "0:04:49", "throughput": 2652.62, "total_tokens": 9465400} {"current_steps": 35295, "total_steps": 38150, "loss": 0.1947, "lr": 8.487489332418025e-07, "epoch": 9.251638269986893, "percentage": 92.52, "elapsed_time": "0:59:28", "remaining_time": "0:04:48", "throughput": 2652.72, "total_tokens": 9467048} {"current_steps": 35300, "total_steps": 38150, "loss": 0.0981, "lr": 8.457965815295926e-07, "epoch": 9.252948885976409, "percentage": 92.53, "elapsed_time": "0:59:29", "remaining_time": "0:04:48", "throughput": 2652.71, "total_tokens": 9468104} {"current_steps": 35305, "total_steps": 38150, "loss": 0.165, "lr": 8.428492852504216e-07, "epoch": 9.254259501965924, "percentage": 92.54, "elapsed_time": "0:59:29", "remaining_time": "0:04:47", "throughput": 2652.68, "total_tokens": 9469128} {"current_steps": 35310, "total_steps": 38150, "loss": 0.1127, "lr": 8.399070450211599e-07, "epoch": 9.25557011795544, "percentage": 92.56, "elapsed_time": "0:59:30", "remaining_time": "0:04:47", "throughput": 2652.64, "total_tokens": 9470088} {"current_steps": 35315, "total_steps": 38150, "loss": 0.1181, "lr": 8.369698614576038e-07, "epoch": 9.256880733944953, "percentage": 92.57, "elapsed_time": "0:59:30", "remaining_time": "0:04:46", "throughput": 2652.64, "total_tokens": 9471208} {"current_steps": 35320, "total_steps": 38150, "loss": 0.3653, "lr": 8.340377351745088e-07, "epoch": 9.258191349934469, "percentage": 92.58, "elapsed_time": "0:59:30", "remaining_time": "0:04:46", "throughput": 2652.71, "total_tokens": 9472728} {"current_steps": 35325, "total_steps": 38150, "loss": 0.082, "lr": 8.311106667855562e-07, "epoch": 9.259501965923985, "percentage": 92.6, "elapsed_time": "0:59:31", "remaining_time": "0:04:45", "throughput": 2652.73, "total_tokens": 9474008} {"current_steps": 35330, "total_steps": 38150, "loss": 0.1496, "lr": 8.281886569033836e-07, "epoch": 9.2608125819135, "percentage": 92.61, "elapsed_time": "0:59:31", "remaining_time": "0:04:45", "throughput": 2652.82, "total_tokens": 9475528} {"current_steps": 35335, "total_steps": 38150, "loss": 0.3915, "lr": 8.252717061395576e-07, "epoch": 9.262123197903014, "percentage": 92.62, "elapsed_time": "0:59:32", "remaining_time": "0:04:44", "throughput": 2652.86, "total_tokens": 9476856} {"current_steps": 35340, "total_steps": 38150, "loss": 0.0898, "lr": 8.223598151045952e-07, "epoch": 9.26343381389253, "percentage": 92.63, "elapsed_time": "0:59:32", "remaining_time": "0:04:44", "throughput": 2652.84, "total_tokens": 9477880} {"current_steps": 35345, "total_steps": 38150, "loss": 0.201, "lr": 8.194529844079451e-07, "epoch": 9.264744429882045, "percentage": 92.65, "elapsed_time": "0:59:33", "remaining_time": "0:04:43", "throughput": 2652.9, "total_tokens": 9479304} {"current_steps": 35350, "total_steps": 38150, "loss": 0.1295, "lr": 8.16551214658004e-07, "epoch": 9.26605504587156, "percentage": 92.66, "elapsed_time": "0:59:33", "remaining_time": "0:04:43", "throughput": 2652.87, "total_tokens": 9480280} {"current_steps": 35355, "total_steps": 38150, "loss": 0.1772, "lr": 8.136545064621137e-07, "epoch": 9.267365661861074, "percentage": 92.67, "elapsed_time": "0:59:34", "remaining_time": "0:04:42", "throughput": 2652.89, "total_tokens": 9481496} {"current_steps": 35360, "total_steps": 38150, "loss": 0.1155, "lr": 8.107628604265366e-07, "epoch": 9.26867627785059, "percentage": 92.69, "elapsed_time": "0:59:34", "remaining_time": "0:04:42", "throughput": 2653.0, "total_tokens": 9483144} {"current_steps": 35365, "total_steps": 38150, "loss": 0.1251, "lr": 8.078762771564996e-07, "epoch": 9.269986893840105, "percentage": 92.7, "elapsed_time": "0:59:34", "remaining_time": "0:04:41", "throughput": 2653.07, "total_tokens": 9484616} {"current_steps": 35370, "total_steps": 38150, "loss": 0.1106, "lr": 8.049947572561584e-07, "epoch": 9.271297509829619, "percentage": 92.71, "elapsed_time": "0:59:35", "remaining_time": "0:04:41", "throughput": 2653.08, "total_tokens": 9485800} {"current_steps": 35375, "total_steps": 38150, "loss": 0.1116, "lr": 8.021183013286082e-07, "epoch": 9.272608125819135, "percentage": 92.73, "elapsed_time": "0:59:35", "remaining_time": "0:04:40", "throughput": 2653.09, "total_tokens": 9486984} {"current_steps": 35380, "total_steps": 38150, "loss": 0.2669, "lr": 7.99246909975887e-07, "epoch": 9.27391874180865, "percentage": 92.74, "elapsed_time": "0:59:36", "remaining_time": "0:04:40", "throughput": 2653.17, "total_tokens": 9488632} {"current_steps": 35385, "total_steps": 38150, "loss": 0.2114, "lr": 7.963805837989724e-07, "epoch": 9.275229357798166, "percentage": 92.75, "elapsed_time": "0:59:36", "remaining_time": "0:04:39", "throughput": 2653.2, "total_tokens": 9489880} {"current_steps": 35390, "total_steps": 38150, "loss": 0.1272, "lr": 7.935193233977845e-07, "epoch": 9.27653997378768, "percentage": 92.77, "elapsed_time": "0:59:37", "remaining_time": "0:04:38", "throughput": 2653.21, "total_tokens": 9491032} {"current_steps": 35395, "total_steps": 38150, "loss": 0.1159, "lr": 7.906631293711719e-07, "epoch": 9.277850589777195, "percentage": 92.78, "elapsed_time": "0:59:37", "remaining_time": "0:04:38", "throughput": 2653.28, "total_tokens": 9492520} {"current_steps": 35400, "total_steps": 38150, "loss": 0.1288, "lr": 7.878120023169344e-07, "epoch": 9.27916120576671, "percentage": 92.79, "elapsed_time": "0:59:38", "remaining_time": "0:04:37", "throughput": 2653.35, "total_tokens": 9494040} {"current_steps": 35405, "total_steps": 38150, "loss": 0.1083, "lr": 7.849659428318113e-07, "epoch": 9.280471821756226, "percentage": 92.8, "elapsed_time": "0:59:38", "remaining_time": "0:04:37", "throughput": 2653.32, "total_tokens": 9495048} {"current_steps": 35410, "total_steps": 38150, "loss": 0.175, "lr": 7.821249515114787e-07, "epoch": 9.28178243774574, "percentage": 92.82, "elapsed_time": "0:59:39", "remaining_time": "0:04:36", "throughput": 2653.42, "total_tokens": 9496776} {"current_steps": 35415, "total_steps": 38150, "loss": 0.2621, "lr": 7.792890289505444e-07, "epoch": 9.283093053735255, "percentage": 92.83, "elapsed_time": "0:59:39", "remaining_time": "0:04:36", "throughput": 2653.45, "total_tokens": 9498040} {"current_steps": 35420, "total_steps": 38150, "loss": 0.0796, "lr": 7.764581757425642e-07, "epoch": 9.284403669724771, "percentage": 92.84, "elapsed_time": "0:59:40", "remaining_time": "0:04:35", "throughput": 2653.49, "total_tokens": 9499608} {"current_steps": 35425, "total_steps": 38150, "loss": 0.2254, "lr": 7.736323924800365e-07, "epoch": 9.285714285714286, "percentage": 92.86, "elapsed_time": "0:59:40", "remaining_time": "0:04:35", "throughput": 2653.55, "total_tokens": 9500984} {"current_steps": 35430, "total_steps": 38150, "loss": 0.0969, "lr": 7.708116797543907e-07, "epoch": 9.2870249017038, "percentage": 92.87, "elapsed_time": "0:59:40", "remaining_time": "0:04:34", "throughput": 2653.57, "total_tokens": 9502184} {"current_steps": 35435, "total_steps": 38150, "loss": 0.2242, "lr": 7.679960381559936e-07, "epoch": 9.288335517693316, "percentage": 92.88, "elapsed_time": "0:59:41", "remaining_time": "0:04:34", "throughput": 2653.64, "total_tokens": 9503624} {"current_steps": 35440, "total_steps": 38150, "loss": 0.1514, "lr": 7.651854682741572e-07, "epoch": 9.289646133682831, "percentage": 92.9, "elapsed_time": "0:59:41", "remaining_time": "0:04:33", "throughput": 2653.72, "total_tokens": 9505176} {"current_steps": 35445, "total_steps": 38150, "loss": 0.1911, "lr": 7.623799706971274e-07, "epoch": 9.290956749672347, "percentage": 92.91, "elapsed_time": "0:59:42", "remaining_time": "0:04:33", "throughput": 2653.76, "total_tokens": 9506504} {"current_steps": 35450, "total_steps": 38150, "loss": 0.1069, "lr": 7.595795460120903e-07, "epoch": 9.29226736566186, "percentage": 92.92, "elapsed_time": "0:59:42", "remaining_time": "0:04:32", "throughput": 2653.72, "total_tokens": 9507448} {"current_steps": 35455, "total_steps": 38150, "loss": 0.1609, "lr": 7.567841948051685e-07, "epoch": 9.293577981651376, "percentage": 92.94, "elapsed_time": "0:59:43", "remaining_time": "0:04:32", "throughput": 2653.73, "total_tokens": 9508760} {"current_steps": 35460, "total_steps": 38150, "loss": 0.1565, "lr": 7.539939176614247e-07, "epoch": 9.294888597640892, "percentage": 92.95, "elapsed_time": "0:59:43", "remaining_time": "0:04:31", "throughput": 2653.77, "total_tokens": 9510072} {"current_steps": 35465, "total_steps": 38150, "loss": 0.1081, "lr": 7.512087151648639e-07, "epoch": 9.296199213630405, "percentage": 92.96, "elapsed_time": "0:59:44", "remaining_time": "0:04:31", "throughput": 2653.78, "total_tokens": 9511288} {"current_steps": 35470, "total_steps": 38150, "loss": 0.2059, "lr": 7.484285878984171e-07, "epoch": 9.297509829619921, "percentage": 92.98, "elapsed_time": "0:59:44", "remaining_time": "0:04:30", "throughput": 2653.78, "total_tokens": 9512408} {"current_steps": 35475, "total_steps": 38150, "loss": 0.1389, "lr": 7.45653536443966e-07, "epoch": 9.298820445609437, "percentage": 92.99, "elapsed_time": "0:59:44", "remaining_time": "0:04:30", "throughput": 2653.83, "total_tokens": 9513752} {"current_steps": 35480, "total_steps": 38150, "loss": 0.1961, "lr": 7.428835613823182e-07, "epoch": 9.300131061598952, "percentage": 93.0, "elapsed_time": "0:59:45", "remaining_time": "0:04:29", "throughput": 2653.84, "total_tokens": 9515000} {"current_steps": 35485, "total_steps": 38150, "loss": 0.1216, "lr": 7.401186632932294e-07, "epoch": 9.301441677588466, "percentage": 93.01, "elapsed_time": "0:59:45", "remaining_time": "0:04:29", "throughput": 2653.83, "total_tokens": 9516136} {"current_steps": 35490, "total_steps": 38150, "loss": 0.1386, "lr": 7.373588427553869e-07, "epoch": 9.302752293577981, "percentage": 93.03, "elapsed_time": "0:59:46", "remaining_time": "0:04:28", "throughput": 2653.84, "total_tokens": 9517288} {"current_steps": 35495, "total_steps": 38150, "loss": 0.1347, "lr": 7.346041003464172e-07, "epoch": 9.304062909567497, "percentage": 93.04, "elapsed_time": "0:59:46", "remaining_time": "0:04:28", "throughput": 2653.87, "total_tokens": 9518536} {"current_steps": 35500, "total_steps": 38150, "loss": 0.1185, "lr": 7.318544366428814e-07, "epoch": 9.305373525557012, "percentage": 93.05, "elapsed_time": "0:59:47", "remaining_time": "0:04:27", "throughput": 2653.85, "total_tokens": 9519608} {"current_steps": 35505, "total_steps": 38150, "loss": 0.1363, "lr": 7.291098522202777e-07, "epoch": 9.306684141546526, "percentage": 93.07, "elapsed_time": "0:59:47", "remaining_time": "0:04:27", "throughput": 2653.86, "total_tokens": 9520808} {"current_steps": 35510, "total_steps": 38150, "loss": 0.1473, "lr": 7.263703476530492e-07, "epoch": 9.307994757536042, "percentage": 93.08, "elapsed_time": "0:59:47", "remaining_time": "0:04:26", "throughput": 2653.88, "total_tokens": 9522008} {"current_steps": 35515, "total_steps": 38150, "loss": 0.1772, "lr": 7.236359235145624e-07, "epoch": 9.309305373525557, "percentage": 93.09, "elapsed_time": "0:59:48", "remaining_time": "0:04:26", "throughput": 2653.9, "total_tokens": 9523288} {"current_steps": 35520, "total_steps": 38150, "loss": 0.1577, "lr": 7.209065803771315e-07, "epoch": 9.310615989515073, "percentage": 93.11, "elapsed_time": "0:59:48", "remaining_time": "0:04:25", "throughput": 2654.01, "total_tokens": 9525064} {"current_steps": 35525, "total_steps": 38150, "loss": 0.18, "lr": 7.181823188120024e-07, "epoch": 9.311926605504587, "percentage": 93.12, "elapsed_time": "0:59:49", "remaining_time": "0:04:25", "throughput": 2653.99, "total_tokens": 9526120} {"current_steps": 35530, "total_steps": 38150, "loss": 0.1684, "lr": 7.154631393893552e-07, "epoch": 9.313237221494102, "percentage": 93.13, "elapsed_time": "0:59:49", "remaining_time": "0:04:24", "throughput": 2654.04, "total_tokens": 9527512} {"current_steps": 35535, "total_steps": 38150, "loss": 0.2159, "lr": 7.127490426783123e-07, "epoch": 9.314547837483618, "percentage": 93.15, "elapsed_time": "0:59:50", "remaining_time": "0:04:24", "throughput": 2654.03, "total_tokens": 9528600} {"current_steps": 35540, "total_steps": 38150, "loss": 0.2346, "lr": 7.100400292469333e-07, "epoch": 9.315858453473133, "percentage": 93.16, "elapsed_time": "0:59:50", "remaining_time": "0:04:23", "throughput": 2654.05, "total_tokens": 9529800} {"current_steps": 35545, "total_steps": 38150, "loss": 0.1045, "lr": 7.073360996622064e-07, "epoch": 9.317169069462647, "percentage": 93.17, "elapsed_time": "0:59:51", "remaining_time": "0:04:23", "throughput": 2654.06, "total_tokens": 9530968} {"current_steps": 35550, "total_steps": 38150, "loss": 0.0818, "lr": 7.046372544900592e-07, "epoch": 9.318479685452163, "percentage": 93.18, "elapsed_time": "0:59:51", "remaining_time": "0:04:22", "throughput": 2654.09, "total_tokens": 9532168} {"current_steps": 35555, "total_steps": 38150, "loss": 0.1851, "lr": 7.01943494295354e-07, "epoch": 9.319790301441678, "percentage": 93.2, "elapsed_time": "0:59:51", "remaining_time": "0:04:22", "throughput": 2654.16, "total_tokens": 9533640} {"current_steps": 35560, "total_steps": 38150, "loss": 0.0855, "lr": 6.992548196418924e-07, "epoch": 9.321100917431192, "percentage": 93.21, "elapsed_time": "0:59:52", "remaining_time": "0:04:21", "throughput": 2654.13, "total_tokens": 9534632} {"current_steps": 35565, "total_steps": 38150, "loss": 0.1165, "lr": 6.965712310924078e-07, "epoch": 9.322411533420707, "percentage": 93.22, "elapsed_time": "0:59:52", "remaining_time": "0:04:21", "throughput": 2654.19, "total_tokens": 9536040} {"current_steps": 35570, "total_steps": 38150, "loss": 0.0897, "lr": 6.9389272920857e-07, "epoch": 9.323722149410223, "percentage": 93.24, "elapsed_time": "0:59:53", "remaining_time": "0:04:20", "throughput": 2654.2, "total_tokens": 9537192} {"current_steps": 35575, "total_steps": 38150, "loss": 0.0836, "lr": 6.912193145509893e-07, "epoch": 9.325032765399738, "percentage": 93.25, "elapsed_time": "0:59:53", "remaining_time": "0:04:20", "throughput": 2654.26, "total_tokens": 9538680} {"current_steps": 35580, "total_steps": 38150, "loss": 0.0952, "lr": 6.885509876792012e-07, "epoch": 9.326343381389252, "percentage": 93.26, "elapsed_time": "0:59:54", "remaining_time": "0:04:19", "throughput": 2654.22, "total_tokens": 9539656} {"current_steps": 35585, "total_steps": 38150, "loss": 0.137, "lr": 6.858877491516869e-07, "epoch": 9.327653997378768, "percentage": 93.28, "elapsed_time": "0:59:54", "remaining_time": "0:04:19", "throughput": 2654.26, "total_tokens": 9540968} {"current_steps": 35590, "total_steps": 38150, "loss": 0.1904, "lr": 6.832295995258531e-07, "epoch": 9.328964613368283, "percentage": 93.29, "elapsed_time": "0:59:55", "remaining_time": "0:04:18", "throughput": 2654.28, "total_tokens": 9542248} {"current_steps": 35595, "total_steps": 38150, "loss": 0.1583, "lr": 6.805765393580493e-07, "epoch": 9.330275229357799, "percentage": 93.3, "elapsed_time": "0:59:55", "remaining_time": "0:04:18", "throughput": 2654.29, "total_tokens": 9543416} {"current_steps": 35600, "total_steps": 38150, "loss": 0.1955, "lr": 6.779285692035536e-07, "epoch": 9.331585845347313, "percentage": 93.32, "elapsed_time": "0:59:55", "remaining_time": "0:04:17", "throughput": 2654.42, "total_tokens": 9545272} {"current_steps": 35605, "total_steps": 38150, "loss": 0.1872, "lr": 6.752856896165866e-07, "epoch": 9.332896461336828, "percentage": 93.33, "elapsed_time": "0:59:56", "remaining_time": "0:04:17", "throughput": 2654.43, "total_tokens": 9546488} {"current_steps": 35610, "total_steps": 38150, "loss": 0.0797, "lr": 6.726479011502917e-07, "epoch": 9.334207077326344, "percentage": 93.34, "elapsed_time": "0:59:56", "remaining_time": "0:04:16", "throughput": 2654.39, "total_tokens": 9547496} {"current_steps": 35615, "total_steps": 38150, "loss": 0.1209, "lr": 6.700152043567554e-07, "epoch": 9.33551769331586, "percentage": 93.36, "elapsed_time": "0:59:57", "remaining_time": "0:04:16", "throughput": 2654.43, "total_tokens": 9548856} {"current_steps": 35620, "total_steps": 38150, "loss": 0.1153, "lr": 6.673875997870005e-07, "epoch": 9.336828309305373, "percentage": 93.37, "elapsed_time": "0:59:57", "remaining_time": "0:04:15", "throughput": 2654.46, "total_tokens": 9550280} {"current_steps": 35625, "total_steps": 38150, "loss": 0.2011, "lr": 6.64765087990979e-07, "epoch": 9.338138925294889, "percentage": 93.38, "elapsed_time": "0:59:58", "remaining_time": "0:04:15", "throughput": 2654.56, "total_tokens": 9551864} {"current_steps": 35630, "total_steps": 38150, "loss": 0.1104, "lr": 6.621476695175738e-07, "epoch": 9.339449541284404, "percentage": 93.39, "elapsed_time": "0:59:58", "remaining_time": "0:04:14", "throughput": 2654.58, "total_tokens": 9553032} {"current_steps": 35635, "total_steps": 38150, "loss": 0.2465, "lr": 6.595353449146108e-07, "epoch": 9.34076015727392, "percentage": 93.41, "elapsed_time": "0:59:59", "remaining_time": "0:04:14", "throughput": 2654.66, "total_tokens": 9554520} {"current_steps": 35640, "total_steps": 38150, "loss": 0.2601, "lr": 6.569281147288414e-07, "epoch": 9.342070773263433, "percentage": 93.42, "elapsed_time": "0:59:59", "remaining_time": "0:04:13", "throughput": 2654.8, "total_tokens": 9556424} {"current_steps": 35645, "total_steps": 38150, "loss": 0.1902, "lr": 6.54325979505957e-07, "epoch": 9.343381389252949, "percentage": 93.43, "elapsed_time": "1:00:00", "remaining_time": "0:04:13", "throughput": 2654.95, "total_tokens": 9558392} {"current_steps": 35650, "total_steps": 38150, "loss": 0.1527, "lr": 6.517289397905746e-07, "epoch": 9.344692005242464, "percentage": 93.45, "elapsed_time": "1:00:00", "remaining_time": "0:04:12", "throughput": 2654.98, "total_tokens": 9559704} {"current_steps": 35655, "total_steps": 38150, "loss": 0.2386, "lr": 6.491369961262566e-07, "epoch": 9.346002621231978, "percentage": 93.46, "elapsed_time": "1:00:01", "remaining_time": "0:04:11", "throughput": 2655.07, "total_tokens": 9561288} {"current_steps": 35660, "total_steps": 38150, "loss": 0.241, "lr": 6.465501490554914e-07, "epoch": 9.347313237221494, "percentage": 93.47, "elapsed_time": "1:00:01", "remaining_time": "0:04:11", "throughput": 2655.08, "total_tokens": 9562440} {"current_steps": 35665, "total_steps": 38150, "loss": 0.1107, "lr": 6.439683991197043e-07, "epoch": 9.34862385321101, "percentage": 93.49, "elapsed_time": "1:00:02", "remaining_time": "0:04:10", "throughput": 2655.13, "total_tokens": 9563880} {"current_steps": 35670, "total_steps": 38150, "loss": 0.1941, "lr": 6.413917468592434e-07, "epoch": 9.349934469200525, "percentage": 93.5, "elapsed_time": "1:00:02", "remaining_time": "0:04:10", "throughput": 2655.14, "total_tokens": 9565032} {"current_steps": 35675, "total_steps": 38150, "loss": 0.0785, "lr": 6.388201928134025e-07, "epoch": 9.351245085190039, "percentage": 93.51, "elapsed_time": "1:00:02", "remaining_time": "0:04:09", "throughput": 2655.1, "total_tokens": 9566008} {"current_steps": 35680, "total_steps": 38150, "loss": 0.2356, "lr": 6.362537375204009e-07, "epoch": 9.352555701179554, "percentage": 93.53, "elapsed_time": "1:00:03", "remaining_time": "0:04:09", "throughput": 2655.15, "total_tokens": 9567336} {"current_steps": 35685, "total_steps": 38150, "loss": 0.1099, "lr": 6.336923815173951e-07, "epoch": 9.35386631716907, "percentage": 93.54, "elapsed_time": "1:00:03", "remaining_time": "0:04:08", "throughput": 2655.12, "total_tokens": 9568312} {"current_steps": 35690, "total_steps": 38150, "loss": 0.1895, "lr": 6.31136125340473e-07, "epoch": 9.355176933158585, "percentage": 93.55, "elapsed_time": "1:00:04", "remaining_time": "0:04:08", "throughput": 2655.18, "total_tokens": 9569816} {"current_steps": 35695, "total_steps": 38150, "loss": 0.1158, "lr": 6.285849695246537e-07, "epoch": 9.356487549148099, "percentage": 93.56, "elapsed_time": "1:00:04", "remaining_time": "0:04:07", "throughput": 2655.23, "total_tokens": 9571224} {"current_steps": 35700, "total_steps": 38150, "loss": 0.1519, "lr": 6.260389146038881e-07, "epoch": 9.357798165137615, "percentage": 93.58, "elapsed_time": "1:00:05", "remaining_time": "0:04:07", "throughput": 2655.24, "total_tokens": 9572360} {"current_steps": 35705, "total_steps": 38150, "loss": 0.1364, "lr": 6.234979611110637e-07, "epoch": 9.35910878112713, "percentage": 93.59, "elapsed_time": "1:00:05", "remaining_time": "0:04:06", "throughput": 2655.26, "total_tokens": 9573656} {"current_steps": 35710, "total_steps": 38150, "loss": 0.0783, "lr": 6.209621095779993e-07, "epoch": 9.360419397116646, "percentage": 93.6, "elapsed_time": "1:00:05", "remaining_time": "0:04:06", "throughput": 2655.26, "total_tokens": 9574776} {"current_steps": 35715, "total_steps": 38150, "loss": 0.1446, "lr": 6.184313605354375e-07, "epoch": 9.36173001310616, "percentage": 93.62, "elapsed_time": "1:00:06", "remaining_time": "0:04:05", "throughput": 2655.32, "total_tokens": 9576248} {"current_steps": 35720, "total_steps": 38150, "loss": 0.1809, "lr": 6.159057145130653e-07, "epoch": 9.363040629095675, "percentage": 93.63, "elapsed_time": "1:00:06", "remaining_time": "0:04:05", "throughput": 2655.34, "total_tokens": 9577432} {"current_steps": 35725, "total_steps": 38150, "loss": 0.0355, "lr": 6.133851720394962e-07, "epoch": 9.36435124508519, "percentage": 93.64, "elapsed_time": "1:00:07", "remaining_time": "0:04:04", "throughput": 2655.33, "total_tokens": 9578552} {"current_steps": 35730, "total_steps": 38150, "loss": 0.2607, "lr": 6.10869733642272e-07, "epoch": 9.365661861074706, "percentage": 93.66, "elapsed_time": "1:00:07", "remaining_time": "0:04:04", "throughput": 2655.4, "total_tokens": 9580024} {"current_steps": 35735, "total_steps": 38150, "loss": 0.122, "lr": 6.083593998478715e-07, "epoch": 9.36697247706422, "percentage": 93.67, "elapsed_time": "1:00:08", "remaining_time": "0:04:03", "throughput": 2655.46, "total_tokens": 9581496} {"current_steps": 35740, "total_steps": 38150, "loss": 0.1386, "lr": 6.058541711817023e-07, "epoch": 9.368283093053735, "percentage": 93.68, "elapsed_time": "1:00:08", "remaining_time": "0:04:03", "throughput": 2655.42, "total_tokens": 9582440} {"current_steps": 35745, "total_steps": 38150, "loss": 0.0965, "lr": 6.033540481681088e-07, "epoch": 9.36959370904325, "percentage": 93.7, "elapsed_time": "1:00:09", "remaining_time": "0:04:02", "throughput": 2655.47, "total_tokens": 9583896} {"current_steps": 35750, "total_steps": 38150, "loss": 0.1616, "lr": 6.008590313303586e-07, "epoch": 9.370904325032765, "percentage": 93.71, "elapsed_time": "1:00:09", "remaining_time": "0:04:02", "throughput": 2655.51, "total_tokens": 9585304} {"current_steps": 35755, "total_steps": 38150, "loss": 0.1953, "lr": 5.983691211906506e-07, "epoch": 9.37221494102228, "percentage": 93.72, "elapsed_time": "1:00:10", "remaining_time": "0:04:01", "throughput": 2655.52, "total_tokens": 9586488} {"current_steps": 35760, "total_steps": 38150, "loss": 0.1861, "lr": 5.958843182701263e-07, "epoch": 9.373525557011796, "percentage": 93.74, "elapsed_time": "1:00:10", "remaining_time": "0:04:01", "throughput": 2655.56, "total_tokens": 9587880} {"current_steps": 35765, "total_steps": 38150, "loss": 0.1416, "lr": 5.934046230888418e-07, "epoch": 9.374836173001311, "percentage": 93.75, "elapsed_time": "1:00:10", "remaining_time": "0:04:00", "throughput": 2655.54, "total_tokens": 9588920} {"current_steps": 35770, "total_steps": 38150, "loss": 0.1225, "lr": 5.909300361658015e-07, "epoch": 9.376146788990825, "percentage": 93.76, "elapsed_time": "1:00:11", "remaining_time": "0:04:00", "throughput": 2655.53, "total_tokens": 9589976} {"current_steps": 35775, "total_steps": 38150, "loss": 0.1095, "lr": 5.8846055801893e-07, "epoch": 9.37745740498034, "percentage": 93.77, "elapsed_time": "1:00:11", "remaining_time": "0:03:59", "throughput": 2655.62, "total_tokens": 9591704} {"current_steps": 35780, "total_steps": 38150, "loss": 0.1983, "lr": 5.859961891650861e-07, "epoch": 9.378768020969856, "percentage": 93.79, "elapsed_time": "1:00:12", "remaining_time": "0:03:59", "throughput": 2655.64, "total_tokens": 9593000} {"current_steps": 35785, "total_steps": 38150, "loss": 0.1489, "lr": 5.835369301200516e-07, "epoch": 9.380078636959372, "percentage": 93.8, "elapsed_time": "1:00:12", "remaining_time": "0:03:58", "throughput": 2655.69, "total_tokens": 9594440} {"current_steps": 35790, "total_steps": 38150, "loss": 0.0991, "lr": 5.810827813985509e-07, "epoch": 9.381389252948885, "percentage": 93.81, "elapsed_time": "1:00:13", "remaining_time": "0:03:58", "throughput": 2655.69, "total_tokens": 9595672} {"current_steps": 35795, "total_steps": 38150, "loss": 0.143, "lr": 5.786337435142314e-07, "epoch": 9.382699868938401, "percentage": 93.83, "elapsed_time": "1:00:13", "remaining_time": "0:03:57", "throughput": 2655.76, "total_tokens": 9597112} {"current_steps": 35800, "total_steps": 38150, "loss": 0.0599, "lr": 5.761898169796721e-07, "epoch": 9.384010484927916, "percentage": 93.84, "elapsed_time": "1:00:14", "remaining_time": "0:03:57", "throughput": 2655.81, "total_tokens": 9598456} {"current_steps": 35805, "total_steps": 38150, "loss": 0.2225, "lr": 5.73751002306383e-07, "epoch": 9.385321100917432, "percentage": 93.85, "elapsed_time": "1:00:14", "remaining_time": "0:03:56", "throughput": 2655.81, "total_tokens": 9599608} {"current_steps": 35810, "total_steps": 38150, "loss": 0.1287, "lr": 5.713173000048033e-07, "epoch": 9.386631716906946, "percentage": 93.87, "elapsed_time": "1:00:15", "remaining_time": "0:03:56", "throughput": 2655.86, "total_tokens": 9601000} {"current_steps": 35815, "total_steps": 38150, "loss": 0.1385, "lr": 5.688887105843032e-07, "epoch": 9.387942332896461, "percentage": 93.88, "elapsed_time": "1:00:15", "remaining_time": "0:03:55", "throughput": 2655.88, "total_tokens": 9602232} {"current_steps": 35820, "total_steps": 38150, "loss": 0.1199, "lr": 5.664652345531846e-07, "epoch": 9.389252948885977, "percentage": 93.89, "elapsed_time": "1:00:15", "remaining_time": "0:03:55", "throughput": 2655.88, "total_tokens": 9603400} {"current_steps": 35825, "total_steps": 38150, "loss": 0.1621, "lr": 5.640468724186721e-07, "epoch": 9.390563564875492, "percentage": 93.91, "elapsed_time": "1:00:16", "remaining_time": "0:03:54", "throughput": 2655.89, "total_tokens": 9604648} {"current_steps": 35830, "total_steps": 38150, "loss": 0.0855, "lr": 5.616336246869275e-07, "epoch": 9.391874180865006, "percentage": 93.92, "elapsed_time": "1:00:16", "remaining_time": "0:03:54", "throughput": 2655.95, "total_tokens": 9606008} {"current_steps": 35835, "total_steps": 38150, "loss": 0.2174, "lr": 5.592254918630385e-07, "epoch": 9.393184796854522, "percentage": 93.93, "elapsed_time": "1:00:17", "remaining_time": "0:03:53", "throughput": 2655.97, "total_tokens": 9607304} {"current_steps": 35840, "total_steps": 38150, "loss": 0.175, "lr": 5.568224744510242e-07, "epoch": 9.394495412844037, "percentage": 93.94, "elapsed_time": "1:00:17", "remaining_time": "0:03:53", "throughput": 2655.96, "total_tokens": 9608360} {"current_steps": 35845, "total_steps": 38150, "loss": 0.1677, "lr": 5.544245729538322e-07, "epoch": 9.395806028833551, "percentage": 93.96, "elapsed_time": "1:00:18", "remaining_time": "0:03:52", "throughput": 2656.02, "total_tokens": 9609720} {"current_steps": 35850, "total_steps": 38150, "loss": 0.1027, "lr": 5.520317878733389e-07, "epoch": 9.397116644823067, "percentage": 93.97, "elapsed_time": "1:00:18", "remaining_time": "0:03:52", "throughput": 2655.94, "total_tokens": 9610536} {"current_steps": 35855, "total_steps": 38150, "loss": 0.1582, "lr": 5.496441197103463e-07, "epoch": 9.398427260812582, "percentage": 93.98, "elapsed_time": "1:00:18", "remaining_time": "0:03:51", "throughput": 2655.97, "total_tokens": 9611832} {"current_steps": 35860, "total_steps": 38150, "loss": 0.1514, "lr": 5.472615689645965e-07, "epoch": 9.399737876802098, "percentage": 94.0, "elapsed_time": "1:00:19", "remaining_time": "0:03:51", "throughput": 2656.06, "total_tokens": 9613416} {"current_steps": 35865, "total_steps": 38150, "loss": 0.1241, "lr": 5.44884136134749e-07, "epoch": 9.401048492791611, "percentage": 94.01, "elapsed_time": "1:00:19", "remaining_time": "0:03:50", "throughput": 2656.0, "total_tokens": 9614296} {"current_steps": 35870, "total_steps": 38150, "loss": 0.0316, "lr": 5.425118217183945e-07, "epoch": 9.402359108781127, "percentage": 94.02, "elapsed_time": "1:00:20", "remaining_time": "0:03:50", "throughput": 2655.94, "total_tokens": 9615176} {"current_steps": 35875, "total_steps": 38150, "loss": 0.1291, "lr": 5.40144626212058e-07, "epoch": 9.403669724770642, "percentage": 94.04, "elapsed_time": "1:00:20", "remaining_time": "0:03:49", "throughput": 2655.96, "total_tokens": 9616472} {"current_steps": 35880, "total_steps": 38150, "loss": 0.1182, "lr": 5.377825501111849e-07, "epoch": 9.404980340760158, "percentage": 94.05, "elapsed_time": "1:00:21", "remaining_time": "0:03:49", "throughput": 2656.0, "total_tokens": 9617784} {"current_steps": 35885, "total_steps": 38150, "loss": 0.1363, "lr": 5.354255939101576e-07, "epoch": 9.406290956749672, "percentage": 94.06, "elapsed_time": "1:00:21", "remaining_time": "0:03:48", "throughput": 2656.07, "total_tokens": 9619272} {"current_steps": 35890, "total_steps": 38150, "loss": 0.1398, "lr": 5.330737581022843e-07, "epoch": 9.407601572739187, "percentage": 94.08, "elapsed_time": "1:00:22", "remaining_time": "0:03:48", "throughput": 2656.09, "total_tokens": 9620472} {"current_steps": 35895, "total_steps": 38150, "loss": 0.1369, "lr": 5.307270431797962e-07, "epoch": 9.408912188728703, "percentage": 94.09, "elapsed_time": "1:00:22", "remaining_time": "0:03:47", "throughput": 2656.15, "total_tokens": 9622040} {"current_steps": 35900, "total_steps": 38150, "loss": 0.2029, "lr": 5.283854496338586e-07, "epoch": 9.410222804718218, "percentage": 94.1, "elapsed_time": "1:00:22", "remaining_time": "0:03:47", "throughput": 2656.18, "total_tokens": 9623304} {"current_steps": 35905, "total_steps": 38150, "loss": 0.103, "lr": 5.26048977954563e-07, "epoch": 9.411533420707732, "percentage": 94.12, "elapsed_time": "1:00:23", "remaining_time": "0:03:46", "throughput": 2656.26, "total_tokens": 9624936} {"current_steps": 35910, "total_steps": 38150, "loss": 0.1052, "lr": 5.237176286309292e-07, "epoch": 9.412844036697248, "percentage": 94.13, "elapsed_time": "1:00:24", "remaining_time": "0:03:46", "throughput": 2656.39, "total_tokens": 9626952} {"current_steps": 35915, "total_steps": 38150, "loss": 0.2003, "lr": 5.213914021509031e-07, "epoch": 9.414154652686763, "percentage": 94.14, "elapsed_time": "1:00:24", "remaining_time": "0:03:45", "throughput": 2656.41, "total_tokens": 9628200} {"current_steps": 35920, "total_steps": 38150, "loss": 0.1197, "lr": 5.190702990013618e-07, "epoch": 9.415465268676279, "percentage": 94.15, "elapsed_time": "1:00:24", "remaining_time": "0:03:45", "throughput": 2656.44, "total_tokens": 9629432} {"current_steps": 35925, "total_steps": 38150, "loss": 0.0686, "lr": 5.167543196681058e-07, "epoch": 9.416775884665793, "percentage": 94.17, "elapsed_time": "1:00:25", "remaining_time": "0:03:44", "throughput": 2656.5, "total_tokens": 9630824} {"current_steps": 35930, "total_steps": 38150, "loss": 0.1751, "lr": 5.144434646358665e-07, "epoch": 9.418086500655308, "percentage": 94.18, "elapsed_time": "1:00:25", "remaining_time": "0:03:44", "throughput": 2656.52, "total_tokens": 9632104} {"current_steps": 35935, "total_steps": 38150, "loss": 0.1148, "lr": 5.121377343883016e-07, "epoch": 9.419397116644824, "percentage": 94.19, "elapsed_time": "1:00:26", "remaining_time": "0:03:43", "throughput": 2656.6, "total_tokens": 9633704} {"current_steps": 35940, "total_steps": 38150, "loss": 0.0739, "lr": 5.098371294080001e-07, "epoch": 9.420707732634337, "percentage": 94.21, "elapsed_time": "1:00:26", "remaining_time": "0:03:43", "throughput": 2656.62, "total_tokens": 9634968} {"current_steps": 35945, "total_steps": 38150, "loss": 0.3134, "lr": 5.075416501764685e-07, "epoch": 9.422018348623853, "percentage": 94.22, "elapsed_time": "1:00:27", "remaining_time": "0:03:42", "throughput": 2656.66, "total_tokens": 9636392} {"current_steps": 35950, "total_steps": 38150, "loss": 0.1515, "lr": 5.052512971741529e-07, "epoch": 9.423328964613368, "percentage": 94.23, "elapsed_time": "1:00:27", "remaining_time": "0:03:42", "throughput": 2656.63, "total_tokens": 9637400} {"current_steps": 35955, "total_steps": 38150, "loss": 0.187, "lr": 5.029660708804146e-07, "epoch": 9.424639580602884, "percentage": 94.25, "elapsed_time": "1:00:28", "remaining_time": "0:03:41", "throughput": 2656.7, "total_tokens": 9638952} {"current_steps": 35960, "total_steps": 38150, "loss": 0.1651, "lr": 5.006859717735512e-07, "epoch": 9.425950196592398, "percentage": 94.26, "elapsed_time": "1:00:28", "remaining_time": "0:03:40", "throughput": 2656.73, "total_tokens": 9640232} {"current_steps": 35965, "total_steps": 38150, "loss": 0.1407, "lr": 4.984110003307812e-07, "epoch": 9.427260812581913, "percentage": 94.27, "elapsed_time": "1:00:29", "remaining_time": "0:03:40", "throughput": 2656.74, "total_tokens": 9641384} {"current_steps": 35970, "total_steps": 38150, "loss": 0.0737, "lr": 4.961411570282543e-07, "epoch": 9.428571428571429, "percentage": 94.29, "elapsed_time": "1:00:29", "remaining_time": "0:03:39", "throughput": 2656.86, "total_tokens": 9643128} {"current_steps": 35975, "total_steps": 38150, "loss": 0.0803, "lr": 4.938764423410458e-07, "epoch": 9.429882044560944, "percentage": 94.3, "elapsed_time": "1:00:29", "remaining_time": "0:03:39", "throughput": 2656.88, "total_tokens": 9644312} {"current_steps": 35980, "total_steps": 38150, "loss": 0.1394, "lr": 4.916168567431544e-07, "epoch": 9.431192660550458, "percentage": 94.31, "elapsed_time": "1:00:30", "remaining_time": "0:03:38", "throughput": 2656.89, "total_tokens": 9645544} {"current_steps": 35985, "total_steps": 38150, "loss": 0.1623, "lr": 4.893624007075048e-07, "epoch": 9.432503276539974, "percentage": 94.33, "elapsed_time": "1:00:30", "remaining_time": "0:03:38", "throughput": 2656.94, "total_tokens": 9646888} {"current_steps": 35990, "total_steps": 38150, "loss": 0.1533, "lr": 4.871130747059554e-07, "epoch": 9.43381389252949, "percentage": 94.34, "elapsed_time": "1:00:31", "remaining_time": "0:03:37", "throughput": 2657.0, "total_tokens": 9648360} {"current_steps": 35995, "total_steps": 38150, "loss": 0.18, "lr": 4.848688792092798e-07, "epoch": 9.435124508519005, "percentage": 94.35, "elapsed_time": "1:00:31", "remaining_time": "0:03:37", "throughput": 2657.03, "total_tokens": 9649608} {"current_steps": 36000, "total_steps": 38150, "loss": 0.2426, "lr": 4.826298146871938e-07, "epoch": 9.436435124508519, "percentage": 94.36, "elapsed_time": "1:00:32", "remaining_time": "0:03:36", "throughput": 2657.06, "total_tokens": 9650840} {"current_steps": 36005, "total_steps": 38150, "loss": 0.1293, "lr": 4.803958816083254e-07, "epoch": 9.437745740498034, "percentage": 94.38, "elapsed_time": "1:00:32", "remaining_time": "0:03:36", "throughput": 2657.05, "total_tokens": 9651928} {"current_steps": 36010, "total_steps": 38150, "loss": 0.185, "lr": 4.781670804402283e-07, "epoch": 9.43905635648755, "percentage": 94.39, "elapsed_time": "1:00:33", "remaining_time": "0:03:35", "throughput": 2657.08, "total_tokens": 9653192} {"current_steps": 36015, "total_steps": 38150, "loss": 0.1001, "lr": 4.75943411649396e-07, "epoch": 9.440366972477065, "percentage": 94.4, "elapsed_time": "1:00:33", "remaining_time": "0:03:35", "throughput": 2657.03, "total_tokens": 9654152} {"current_steps": 36020, "total_steps": 38150, "loss": 0.1797, "lr": 4.7372487570123135e-07, "epoch": 9.441677588466579, "percentage": 94.42, "elapsed_time": "1:00:33", "remaining_time": "0:03:34", "throughput": 2657.09, "total_tokens": 9655656} {"current_steps": 36025, "total_steps": 38150, "loss": 0.1283, "lr": 4.7151147306007117e-07, "epoch": 9.442988204456094, "percentage": 94.43, "elapsed_time": "1:00:34", "remaining_time": "0:03:34", "throughput": 2657.09, "total_tokens": 9656792} {"current_steps": 36030, "total_steps": 38150, "loss": 0.1466, "lr": 4.6930320418917817e-07, "epoch": 9.44429882044561, "percentage": 94.44, "elapsed_time": "1:00:34", "remaining_time": "0:03:33", "throughput": 2657.1, "total_tokens": 9657928} {"current_steps": 36035, "total_steps": 38150, "loss": 0.1225, "lr": 4.6710006955073826e-07, "epoch": 9.445609436435124, "percentage": 94.46, "elapsed_time": "1:00:35", "remaining_time": "0:03:33", "throughput": 2657.09, "total_tokens": 9659032} {"current_steps": 36040, "total_steps": 38150, "loss": 0.1422, "lr": 4.649020696058659e-07, "epoch": 9.44692005242464, "percentage": 94.47, "elapsed_time": "1:00:35", "remaining_time": "0:03:32", "throughput": 2657.09, "total_tokens": 9660200} {"current_steps": 36045, "total_steps": 38150, "loss": 0.0701, "lr": 4.627092048145959e-07, "epoch": 9.448230668414155, "percentage": 94.48, "elapsed_time": "1:00:36", "remaining_time": "0:03:32", "throughput": 2657.11, "total_tokens": 9661432} {"current_steps": 36050, "total_steps": 38150, "loss": 0.2109, "lr": 4.6052147563589167e-07, "epoch": 9.44954128440367, "percentage": 94.5, "elapsed_time": "1:00:36", "remaining_time": "0:03:31", "throughput": 2657.14, "total_tokens": 9662776} {"current_steps": 36055, "total_steps": 38150, "loss": 0.1157, "lr": 4.583388825276397e-07, "epoch": 9.450851900393184, "percentage": 94.51, "elapsed_time": "1:00:36", "remaining_time": "0:03:31", "throughput": 2657.12, "total_tokens": 9663896} {"current_steps": 36060, "total_steps": 38150, "loss": 0.0654, "lr": 4.561614259466579e-07, "epoch": 9.4521625163827, "percentage": 94.52, "elapsed_time": "1:00:37", "remaining_time": "0:03:30", "throughput": 2657.14, "total_tokens": 9665144} {"current_steps": 36065, "total_steps": 38150, "loss": 0.2837, "lr": 4.53989106348679e-07, "epoch": 9.453473132372215, "percentage": 94.53, "elapsed_time": "1:00:37", "remaining_time": "0:03:30", "throughput": 2657.22, "total_tokens": 9666616} {"current_steps": 36070, "total_steps": 38150, "loss": 0.0818, "lr": 4.518219241883698e-07, "epoch": 9.45478374836173, "percentage": 94.55, "elapsed_time": "1:00:38", "remaining_time": "0:03:29", "throughput": 2657.22, "total_tokens": 9667768} {"current_steps": 36075, "total_steps": 38150, "loss": 0.0897, "lr": 4.4965987991931466e-07, "epoch": 9.456094364351245, "percentage": 94.56, "elapsed_time": "1:00:38", "remaining_time": "0:03:29", "throughput": 2657.28, "total_tokens": 9669192} {"current_steps": 36080, "total_steps": 38150, "loss": 0.1121, "lr": 4.475029739940295e-07, "epoch": 9.45740498034076, "percentage": 94.57, "elapsed_time": "1:00:39", "remaining_time": "0:03:28", "throughput": 2657.29, "total_tokens": 9670392} {"current_steps": 36085, "total_steps": 38150, "loss": 0.15, "lr": 4.4535120686394484e-07, "epoch": 9.458715596330276, "percentage": 94.59, "elapsed_time": "1:00:39", "remaining_time": "0:03:28", "throughput": 2657.31, "total_tokens": 9671656} {"current_steps": 36090, "total_steps": 38150, "loss": 0.0589, "lr": 4.4320457897942815e-07, "epoch": 9.460026212319791, "percentage": 94.6, "elapsed_time": "1:00:40", "remaining_time": "0:03:27", "throughput": 2657.29, "total_tokens": 9672696} {"current_steps": 36095, "total_steps": 38150, "loss": 0.1427, "lr": 4.410630907897617e-07, "epoch": 9.461336828309305, "percentage": 94.61, "elapsed_time": "1:00:40", "remaining_time": "0:03:27", "throughput": 2657.35, "total_tokens": 9674152} {"current_steps": 36100, "total_steps": 38150, "loss": 0.0785, "lr": 4.389267427431565e-07, "epoch": 9.46264744429882, "percentage": 94.63, "elapsed_time": "1:00:40", "remaining_time": "0:03:26", "throughput": 2657.35, "total_tokens": 9675272} {"current_steps": 36105, "total_steps": 38150, "loss": 0.1514, "lr": 4.367955352867437e-07, "epoch": 9.463958060288336, "percentage": 94.64, "elapsed_time": "1:00:41", "remaining_time": "0:03:26", "throughput": 2657.4, "total_tokens": 9676600} {"current_steps": 36110, "total_steps": 38150, "loss": 0.1248, "lr": 4.346694688665831e-07, "epoch": 9.46526867627785, "percentage": 94.65, "elapsed_time": "1:00:41", "remaining_time": "0:03:25", "throughput": 2657.38, "total_tokens": 9677656} {"current_steps": 36115, "total_steps": 38150, "loss": 0.0945, "lr": 4.325485439276578e-07, "epoch": 9.466579292267365, "percentage": 94.67, "elapsed_time": "1:00:42", "remaining_time": "0:03:25", "throughput": 2657.36, "total_tokens": 9678696} {"current_steps": 36120, "total_steps": 38150, "loss": 0.1146, "lr": 4.304327609138736e-07, "epoch": 9.46788990825688, "percentage": 94.68, "elapsed_time": "1:00:42", "remaining_time": "0:03:24", "throughput": 2657.44, "total_tokens": 9680280} {"current_steps": 36125, "total_steps": 38150, "loss": 0.1548, "lr": 4.2832212026805986e-07, "epoch": 9.469200524246396, "percentage": 94.69, "elapsed_time": "1:00:43", "remaining_time": "0:03:24", "throughput": 2657.45, "total_tokens": 9681432} {"current_steps": 36130, "total_steps": 38150, "loss": 0.1637, "lr": 4.262166224319686e-07, "epoch": 9.47051114023591, "percentage": 94.71, "elapsed_time": "1:00:43", "remaining_time": "0:03:23", "throughput": 2657.46, "total_tokens": 9682744} {"current_steps": 36135, "total_steps": 38150, "loss": 0.2583, "lr": 4.2411626784628065e-07, "epoch": 9.471821756225426, "percentage": 94.72, "elapsed_time": "1:00:44", "remaining_time": "0:03:23", "throughput": 2657.75, "total_tokens": 9686088} {"current_steps": 36140, "total_steps": 38150, "loss": 0.1337, "lr": 4.220210569505917e-07, "epoch": 9.473132372214941, "percentage": 94.73, "elapsed_time": "1:00:44", "remaining_time": "0:03:22", "throughput": 2657.76, "total_tokens": 9687240} {"current_steps": 36145, "total_steps": 38150, "loss": 0.1393, "lr": 4.199309901834286e-07, "epoch": 9.474442988204457, "percentage": 94.74, "elapsed_time": "1:00:45", "remaining_time": "0:03:22", "throughput": 2657.77, "total_tokens": 9688440} {"current_steps": 36150, "total_steps": 38150, "loss": 0.209, "lr": 4.178460679822388e-07, "epoch": 9.47575360419397, "percentage": 94.76, "elapsed_time": "1:00:45", "remaining_time": "0:03:21", "throughput": 2657.83, "total_tokens": 9690136} {"current_steps": 36155, "total_steps": 38150, "loss": 0.1014, "lr": 4.157662907833898e-07, "epoch": 9.477064220183486, "percentage": 94.77, "elapsed_time": "1:00:46", "remaining_time": "0:03:21", "throughput": 2657.85, "total_tokens": 9691352} {"current_steps": 36160, "total_steps": 38150, "loss": 0.216, "lr": 4.1369165902218065e-07, "epoch": 9.478374836173002, "percentage": 94.78, "elapsed_time": "1:00:46", "remaining_time": "0:03:20", "throughput": 2657.91, "total_tokens": 9692760} {"current_steps": 36165, "total_steps": 38150, "loss": 0.1958, "lr": 4.1162217313282236e-07, "epoch": 9.479685452162517, "percentage": 94.8, "elapsed_time": "1:00:47", "remaining_time": "0:03:20", "throughput": 2657.95, "total_tokens": 9694024} {"current_steps": 36170, "total_steps": 38150, "loss": 0.1257, "lr": 4.0955783354846013e-07, "epoch": 9.48099606815203, "percentage": 94.81, "elapsed_time": "1:00:47", "remaining_time": "0:03:19", "throughput": 2657.96, "total_tokens": 9695192} {"current_steps": 36175, "total_steps": 38150, "loss": 0.1843, "lr": 4.0749864070115387e-07, "epoch": 9.482306684141546, "percentage": 94.82, "elapsed_time": "1:00:48", "remaining_time": "0:03:19", "throughput": 2657.99, "total_tokens": 9696536} {"current_steps": 36180, "total_steps": 38150, "loss": 0.0827, "lr": 4.0544459502188934e-07, "epoch": 9.483617300131062, "percentage": 94.84, "elapsed_time": "1:00:48", "remaining_time": "0:03:18", "throughput": 2658.02, "total_tokens": 9697928} {"current_steps": 36185, "total_steps": 38150, "loss": 0.1736, "lr": 4.0339569694057554e-07, "epoch": 9.484927916120578, "percentage": 94.85, "elapsed_time": "1:00:48", "remaining_time": "0:03:18", "throughput": 2658.07, "total_tokens": 9699272} {"current_steps": 36190, "total_steps": 38150, "loss": 0.1764, "lr": 4.013519468860416e-07, "epoch": 9.486238532110091, "percentage": 94.86, "elapsed_time": "1:00:49", "remaining_time": "0:03:17", "throughput": 2658.17, "total_tokens": 9700968} {"current_steps": 36195, "total_steps": 38150, "loss": 0.1999, "lr": 3.993133452860426e-07, "epoch": 9.487549148099607, "percentage": 94.88, "elapsed_time": "1:00:49", "remaining_time": "0:03:17", "throughput": 2658.22, "total_tokens": 9702344} {"current_steps": 36200, "total_steps": 38150, "loss": 0.1226, "lr": 3.9727989256725384e-07, "epoch": 9.488859764089122, "percentage": 94.89, "elapsed_time": "1:00:50", "remaining_time": "0:03:16", "throughput": 2658.19, "total_tokens": 9703352} {"current_steps": 36205, "total_steps": 38150, "loss": 0.1424, "lr": 3.9525158915527383e-07, "epoch": 9.490170380078636, "percentage": 94.9, "elapsed_time": "1:00:50", "remaining_time": "0:03:16", "throughput": 2658.27, "total_tokens": 9704840} {"current_steps": 36210, "total_steps": 38150, "loss": 0.1238, "lr": 3.932284354746213e-07, "epoch": 9.491480996068152, "percentage": 94.91, "elapsed_time": "1:00:51", "remaining_time": "0:03:15", "throughput": 2658.31, "total_tokens": 9706248} {"current_steps": 36215, "total_steps": 38150, "loss": 0.113, "lr": 3.9121043194874365e-07, "epoch": 9.492791612057667, "percentage": 94.93, "elapsed_time": "1:00:51", "remaining_time": "0:03:15", "throughput": 2658.31, "total_tokens": 9707384} {"current_steps": 36220, "total_steps": 38150, "loss": 0.0964, "lr": 3.8919757899999743e-07, "epoch": 9.494102228047183, "percentage": 94.94, "elapsed_time": "1:00:52", "remaining_time": "0:03:14", "throughput": 2658.41, "total_tokens": 9709208} {"current_steps": 36225, "total_steps": 38150, "loss": 0.1366, "lr": 3.8718987704967345e-07, "epoch": 9.495412844036696, "percentage": 94.95, "elapsed_time": "1:00:52", "remaining_time": "0:03:14", "throughput": 2658.42, "total_tokens": 9710392} {"current_steps": 36230, "total_steps": 38150, "loss": 0.198, "lr": 3.8518732651798284e-07, "epoch": 9.496723460026212, "percentage": 94.97, "elapsed_time": "1:00:53", "remaining_time": "0:03:13", "throughput": 2658.45, "total_tokens": 9711624} {"current_steps": 36235, "total_steps": 38150, "loss": 0.1174, "lr": 3.8318992782405414e-07, "epoch": 9.498034076015728, "percentage": 94.98, "elapsed_time": "1:00:53", "remaining_time": "0:03:13", "throughput": 2658.43, "total_tokens": 9712680} {"current_steps": 36240, "total_steps": 38150, "loss": 0.0921, "lr": 3.811976813859364e-07, "epoch": 9.499344692005243, "percentage": 94.99, "elapsed_time": "1:00:53", "remaining_time": "0:03:12", "throughput": 2658.47, "total_tokens": 9714008} {"current_steps": 36245, "total_steps": 38150, "loss": 0.1541, "lr": 3.792105876206098e-07, "epoch": 9.500655307994757, "percentage": 95.01, "elapsed_time": "1:00:54", "remaining_time": "0:03:12", "throughput": 2658.48, "total_tokens": 9715176} {"current_steps": 36250, "total_steps": 38150, "loss": 0.1177, "lr": 3.7722864694396397e-07, "epoch": 9.501965923984272, "percentage": 95.02, "elapsed_time": "1:00:54", "remaining_time": "0:03:11", "throughput": 2658.47, "total_tokens": 9716296} {"current_steps": 36252, "total_steps": 38150, "eval_loss": 0.8772965669631958, "epoch": 9.502490170380078, "percentage": 95.02, "elapsed_time": "1:01:11", "remaining_time": "0:03:12", "throughput": 2646.31, "total_tokens": 9716920} {"current_steps": 36255, "total_steps": 38150, "loss": 0.1199, "lr": 3.7525185977081713e-07, "epoch": 9.503276539973788, "percentage": 95.03, "elapsed_time": "1:01:13", "remaining_time": "0:03:12", "throughput": 2645.41, "total_tokens": 9719064} {"current_steps": 36260, "total_steps": 38150, "loss": 0.1425, "lr": 3.7328022651490767e-07, "epoch": 9.504587155963304, "percentage": 95.05, "elapsed_time": "1:01:14", "remaining_time": "0:03:11", "throughput": 2645.46, "total_tokens": 9720472} {"current_steps": 36265, "total_steps": 38150, "loss": 0.1215, "lr": 3.7131374758889446e-07, "epoch": 9.505897771952817, "percentage": 95.06, "elapsed_time": "1:01:14", "remaining_time": "0:03:11", "throughput": 2645.51, "total_tokens": 9721896} {"current_steps": 36270, "total_steps": 38150, "loss": 0.1738, "lr": 3.693524234043594e-07, "epoch": 9.507208387942333, "percentage": 95.07, "elapsed_time": "1:01:15", "remaining_time": "0:03:10", "throughput": 2645.59, "total_tokens": 9723480} {"current_steps": 36275, "total_steps": 38150, "loss": 0.1459, "lr": 3.6739625437180457e-07, "epoch": 9.508519003931848, "percentage": 95.09, "elapsed_time": "1:01:15", "remaining_time": "0:03:09", "throughput": 2645.7, "total_tokens": 9725224} {"current_steps": 36280, "total_steps": 38150, "loss": 0.3996, "lr": 3.654452409006498e-07, "epoch": 9.509829619921362, "percentage": 95.1, "elapsed_time": "1:01:16", "remaining_time": "0:03:09", "throughput": 2645.73, "total_tokens": 9726520} {"current_steps": 36285, "total_steps": 38150, "loss": 0.0894, "lr": 3.634993833992434e-07, "epoch": 9.511140235910878, "percentage": 95.11, "elapsed_time": "1:01:16", "remaining_time": "0:03:08", "throughput": 2645.66, "total_tokens": 9727352} {"current_steps": 36290, "total_steps": 38150, "loss": 0.0975, "lr": 3.615586822748457e-07, "epoch": 9.512450851900393, "percentage": 95.12, "elapsed_time": "1:01:17", "remaining_time": "0:03:08", "throughput": 2645.72, "total_tokens": 9728760} {"current_steps": 36295, "total_steps": 38150, "loss": 0.0946, "lr": 3.596231379336429e-07, "epoch": 9.513761467889909, "percentage": 95.14, "elapsed_time": "1:01:17", "remaining_time": "0:03:07", "throughput": 2645.81, "total_tokens": 9730360} {"current_steps": 36300, "total_steps": 38150, "loss": 0.1334, "lr": 3.5769275078074425e-07, "epoch": 9.515072083879424, "percentage": 95.15, "elapsed_time": "1:01:18", "remaining_time": "0:03:07", "throughput": 2645.84, "total_tokens": 9731688} {"current_steps": 36305, "total_steps": 38150, "loss": 0.2273, "lr": 3.5576752122017385e-07, "epoch": 9.516382699868938, "percentage": 95.16, "elapsed_time": "1:01:18", "remaining_time": "0:03:06", "throughput": 2645.9, "total_tokens": 9733160} {"current_steps": 36310, "total_steps": 38150, "loss": 0.0992, "lr": 3.5384744965487883e-07, "epoch": 9.517693315858454, "percentage": 95.18, "elapsed_time": "1:01:19", "remaining_time": "0:03:06", "throughput": 2645.97, "total_tokens": 9734760} {"current_steps": 36315, "total_steps": 38150, "loss": 0.0892, "lr": 3.519325364867265e-07, "epoch": 9.51900393184797, "percentage": 95.19, "elapsed_time": "1:01:19", "remaining_time": "0:03:05", "throughput": 2645.99, "total_tokens": 9735960} {"current_steps": 36320, "total_steps": 38150, "loss": 0.1743, "lr": 3.5002278211650476e-07, "epoch": 9.520314547837483, "percentage": 95.2, "elapsed_time": "1:01:19", "remaining_time": "0:03:05", "throughput": 2646.05, "total_tokens": 9737416} {"current_steps": 36325, "total_steps": 38150, "loss": 0.1689, "lr": 3.4811818694392706e-07, "epoch": 9.521625163826998, "percentage": 95.22, "elapsed_time": "1:01:20", "remaining_time": "0:03:04", "throughput": 2646.11, "total_tokens": 9738888} {"current_steps": 36330, "total_steps": 38150, "loss": 0.0643, "lr": 3.462187513676135e-07, "epoch": 9.522935779816514, "percentage": 95.23, "elapsed_time": "1:01:20", "remaining_time": "0:03:04", "throughput": 2646.08, "total_tokens": 9739880} {"current_steps": 36335, "total_steps": 38150, "loss": 0.0937, "lr": 3.4432447578511826e-07, "epoch": 9.52424639580603, "percentage": 95.24, "elapsed_time": "1:01:21", "remaining_time": "0:03:03", "throughput": 2646.14, "total_tokens": 9741336} {"current_steps": 36340, "total_steps": 38150, "loss": 0.1941, "lr": 3.4243536059291035e-07, "epoch": 9.525557011795543, "percentage": 95.26, "elapsed_time": "1:01:21", "remaining_time": "0:03:03", "throughput": 2646.2, "total_tokens": 9742776} {"current_steps": 36345, "total_steps": 38150, "loss": 0.0908, "lr": 3.405514061863735e-07, "epoch": 9.526867627785059, "percentage": 95.27, "elapsed_time": "1:01:22", "remaining_time": "0:03:02", "throughput": 2646.24, "total_tokens": 9744072} {"current_steps": 36350, "total_steps": 38150, "loss": 0.2079, "lr": 3.3867261295982e-07, "epoch": 9.528178243774574, "percentage": 95.28, "elapsed_time": "1:01:22", "remaining_time": "0:03:02", "throughput": 2646.28, "total_tokens": 9745384} {"current_steps": 36355, "total_steps": 38150, "loss": 0.2697, "lr": 3.36798981306477e-07, "epoch": 9.52948885976409, "percentage": 95.29, "elapsed_time": "1:01:23", "remaining_time": "0:03:01", "throughput": 2646.44, "total_tokens": 9747400} {"current_steps": 36360, "total_steps": 38150, "loss": 0.1744, "lr": 3.3493051161849477e-07, "epoch": 9.530799475753604, "percentage": 95.31, "elapsed_time": "1:01:23", "remaining_time": "0:03:01", "throughput": 2646.53, "total_tokens": 9749032} {"current_steps": 36365, "total_steps": 38150, "loss": 0.195, "lr": 3.330672042869354e-07, "epoch": 9.53211009174312, "percentage": 95.32, "elapsed_time": "1:01:24", "remaining_time": "0:03:00", "throughput": 2646.6, "total_tokens": 9750648} {"current_steps": 36370, "total_steps": 38150, "loss": 0.1156, "lr": 3.312090597017925e-07, "epoch": 9.533420707732635, "percentage": 95.33, "elapsed_time": "1:01:24", "remaining_time": "0:03:00", "throughput": 2646.67, "total_tokens": 9752392} {"current_steps": 36375, "total_steps": 38150, "loss": 0.1068, "lr": 3.2935607825196614e-07, "epoch": 9.534731323722148, "percentage": 95.35, "elapsed_time": "1:01:25", "remaining_time": "0:02:59", "throughput": 2646.77, "total_tokens": 9754152} {"current_steps": 36380, "total_steps": 38150, "loss": 0.0785, "lr": 3.275082603252877e-07, "epoch": 9.536041939711664, "percentage": 95.36, "elapsed_time": "1:01:25", "remaining_time": "0:02:59", "throughput": 2646.74, "total_tokens": 9755128} {"current_steps": 36385, "total_steps": 38150, "loss": 0.0825, "lr": 3.2566560630849784e-07, "epoch": 9.53735255570118, "percentage": 95.37, "elapsed_time": "1:01:26", "remaining_time": "0:02:58", "throughput": 2646.76, "total_tokens": 9756408} {"current_steps": 36390, "total_steps": 38150, "loss": 0.1829, "lr": 3.2382811658726033e-07, "epoch": 9.538663171690695, "percentage": 95.39, "elapsed_time": "1:01:26", "remaining_time": "0:02:58", "throughput": 2646.74, "total_tokens": 9757432} {"current_steps": 36395, "total_steps": 38150, "loss": 0.0727, "lr": 3.219957915461619e-07, "epoch": 9.539973787680209, "percentage": 95.4, "elapsed_time": "1:01:27", "remaining_time": "0:02:57", "throughput": 2646.79, "total_tokens": 9758856} {"current_steps": 36400, "total_steps": 38150, "loss": 0.1351, "lr": 3.201686315687041e-07, "epoch": 9.541284403669724, "percentage": 95.41, "elapsed_time": "1:01:27", "remaining_time": "0:02:57", "throughput": 2646.98, "total_tokens": 9761496} {"current_steps": 36405, "total_steps": 38150, "loss": 0.145, "lr": 3.183466370373117e-07, "epoch": 9.54259501965924, "percentage": 95.43, "elapsed_time": "1:01:28", "remaining_time": "0:02:56", "throughput": 2646.98, "total_tokens": 9762616} {"current_steps": 36410, "total_steps": 38150, "loss": 0.1571, "lr": 3.1652980833331846e-07, "epoch": 9.543905635648755, "percentage": 95.44, "elapsed_time": "1:01:28", "remaining_time": "0:02:56", "throughput": 2647.0, "total_tokens": 9763864} {"current_steps": 36415, "total_steps": 38150, "loss": 0.1474, "lr": 3.147181458369897e-07, "epoch": 9.54521625163827, "percentage": 95.45, "elapsed_time": "1:01:29", "remaining_time": "0:02:55", "throughput": 2647.0, "total_tokens": 9764968} {"current_steps": 36420, "total_steps": 38150, "loss": 0.1954, "lr": 3.12911649927497e-07, "epoch": 9.546526867627785, "percentage": 95.47, "elapsed_time": "1:01:29", "remaining_time": "0:02:55", "throughput": 2647.06, "total_tokens": 9766424} {"current_steps": 36425, "total_steps": 38150, "loss": 0.0972, "lr": 3.111103209829408e-07, "epoch": 9.5478374836173, "percentage": 95.48, "elapsed_time": "1:01:30", "remaining_time": "0:02:54", "throughput": 2647.13, "total_tokens": 9767912} {"current_steps": 36430, "total_steps": 38150, "loss": 0.1082, "lr": 3.0931415938033336e-07, "epoch": 9.549148099606816, "percentage": 95.49, "elapsed_time": "1:01:30", "remaining_time": "0:02:54", "throughput": 2647.09, "total_tokens": 9768904} {"current_steps": 36435, "total_steps": 38150, "loss": 0.1571, "lr": 3.075231654956129e-07, "epoch": 9.55045871559633, "percentage": 95.5, "elapsed_time": "1:01:30", "remaining_time": "0:02:53", "throughput": 2647.18, "total_tokens": 9770552} {"current_steps": 36440, "total_steps": 38150, "loss": 0.2277, "lr": 3.0573733970362674e-07, "epoch": 9.551769331585845, "percentage": 95.52, "elapsed_time": "1:01:31", "remaining_time": "0:02:53", "throughput": 2647.19, "total_tokens": 9771704} {"current_steps": 36445, "total_steps": 38150, "loss": 0.1817, "lr": 3.0395668237814813e-07, "epoch": 9.55307994757536, "percentage": 95.53, "elapsed_time": "1:01:31", "remaining_time": "0:02:52", "throughput": 2647.29, "total_tokens": 9773320} {"current_steps": 36450, "total_steps": 38150, "loss": 0.1473, "lr": 3.0218119389186503e-07, "epoch": 9.554390563564876, "percentage": 95.54, "elapsed_time": "1:01:32", "remaining_time": "0:02:52", "throughput": 2647.28, "total_tokens": 9774424} {"current_steps": 36455, "total_steps": 38150, "loss": 0.0602, "lr": 3.0041087461638304e-07, "epoch": 9.55570117955439, "percentage": 95.56, "elapsed_time": "1:01:32", "remaining_time": "0:02:51", "throughput": 2647.23, "total_tokens": 9775336} {"current_steps": 36460, "total_steps": 38150, "loss": 0.2043, "lr": 2.986457249222252e-07, "epoch": 9.557011795543906, "percentage": 95.57, "elapsed_time": "1:01:33", "remaining_time": "0:02:51", "throughput": 2647.27, "total_tokens": 9776680} {"current_steps": 36465, "total_steps": 38150, "loss": 0.1639, "lr": 2.968857451788404e-07, "epoch": 9.558322411533421, "percentage": 95.58, "elapsed_time": "1:01:33", "remaining_time": "0:02:50", "throughput": 2647.33, "total_tokens": 9778088} {"current_steps": 36470, "total_steps": 38150, "loss": 0.1169, "lr": 2.951309357545812e-07, "epoch": 9.559633027522935, "percentage": 95.6, "elapsed_time": "1:01:34", "remaining_time": "0:02:50", "throughput": 2647.44, "total_tokens": 9779752} {"current_steps": 36475, "total_steps": 38150, "loss": 0.1098, "lr": 2.9338129701673434e-07, "epoch": 9.56094364351245, "percentage": 95.61, "elapsed_time": "1:01:34", "remaining_time": "0:02:49", "throughput": 2647.52, "total_tokens": 9781368} {"current_steps": 36480, "total_steps": 38150, "loss": 0.0593, "lr": 2.916368293314903e-07, "epoch": 9.562254259501966, "percentage": 95.62, "elapsed_time": "1:01:34", "remaining_time": "0:02:49", "throughput": 2647.54, "total_tokens": 9782600} {"current_steps": 36485, "total_steps": 38150, "loss": 0.157, "lr": 2.898975330639653e-07, "epoch": 9.563564875491481, "percentage": 95.64, "elapsed_time": "1:01:35", "remaining_time": "0:02:48", "throughput": 2647.61, "total_tokens": 9784184} {"current_steps": 36490, "total_steps": 38150, "loss": 0.1182, "lr": 2.8816340857819034e-07, "epoch": 9.564875491480995, "percentage": 95.65, "elapsed_time": "1:01:35", "remaining_time": "0:02:48", "throughput": 2647.67, "total_tokens": 9785672} {"current_steps": 36495, "total_steps": 38150, "loss": 0.1804, "lr": 2.8643445623711684e-07, "epoch": 9.56618610747051, "percentage": 95.66, "elapsed_time": "1:01:36", "remaining_time": "0:02:47", "throughput": 2647.71, "total_tokens": 9786952} {"current_steps": 36500, "total_steps": 38150, "loss": 0.0912, "lr": 2.847106764026081e-07, "epoch": 9.567496723460026, "percentage": 95.67, "elapsed_time": "1:01:36", "remaining_time": "0:02:47", "throughput": 2647.7, "total_tokens": 9788040} {"current_steps": 36505, "total_steps": 38150, "loss": 0.1348, "lr": 2.8299206943545044e-07, "epoch": 9.568807339449542, "percentage": 95.69, "elapsed_time": "1:01:37", "remaining_time": "0:02:46", "throughput": 2647.7, "total_tokens": 9789144} {"current_steps": 36510, "total_steps": 38150, "loss": 0.0902, "lr": 2.812786356953451e-07, "epoch": 9.570117955439056, "percentage": 95.7, "elapsed_time": "1:01:37", "remaining_time": "0:02:46", "throughput": 2647.68, "total_tokens": 9790168} {"current_steps": 36515, "total_steps": 38150, "loss": 0.1586, "lr": 2.795703755409107e-07, "epoch": 9.571428571428571, "percentage": 95.71, "elapsed_time": "1:01:38", "remaining_time": "0:02:45", "throughput": 2647.73, "total_tokens": 9791672} {"current_steps": 36520, "total_steps": 38150, "loss": 0.1582, "lr": 2.7786728932968354e-07, "epoch": 9.572739187418087, "percentage": 95.73, "elapsed_time": "1:01:38", "remaining_time": "0:02:45", "throughput": 2647.79, "total_tokens": 9793048} {"current_steps": 36525, "total_steps": 38150, "loss": 0.1955, "lr": 2.761693774181173e-07, "epoch": 9.574049803407602, "percentage": 95.74, "elapsed_time": "1:01:39", "remaining_time": "0:02:44", "throughput": 2647.87, "total_tokens": 9794648} {"current_steps": 36530, "total_steps": 38150, "loss": 0.0856, "lr": 2.7447664016157783e-07, "epoch": 9.575360419397116, "percentage": 95.75, "elapsed_time": "1:01:39", "remaining_time": "0:02:44", "throughput": 2647.91, "total_tokens": 9795928} {"current_steps": 36535, "total_steps": 38150, "loss": 0.1835, "lr": 2.727890779143566e-07, "epoch": 9.576671035386632, "percentage": 95.77, "elapsed_time": "1:01:39", "remaining_time": "0:02:43", "throughput": 2647.92, "total_tokens": 9797064} {"current_steps": 36540, "total_steps": 38150, "loss": 0.1122, "lr": 2.7110669102965723e-07, "epoch": 9.577981651376147, "percentage": 95.78, "elapsed_time": "1:01:40", "remaining_time": "0:02:43", "throughput": 2647.9, "total_tokens": 9798120} {"current_steps": 36545, "total_steps": 38150, "loss": 0.1762, "lr": 2.694294798595981e-07, "epoch": 9.579292267365663, "percentage": 95.79, "elapsed_time": "1:01:40", "remaining_time": "0:02:42", "throughput": 2647.9, "total_tokens": 9799336} {"current_steps": 36550, "total_steps": 38150, "loss": 0.1489, "lr": 2.677574447552178e-07, "epoch": 9.580602883355176, "percentage": 95.81, "elapsed_time": "1:01:41", "remaining_time": "0:02:42", "throughput": 2647.93, "total_tokens": 9800664} {"current_steps": 36555, "total_steps": 38150, "loss": 0.0675, "lr": 2.660905860664697e-07, "epoch": 9.581913499344692, "percentage": 95.82, "elapsed_time": "1:01:41", "remaining_time": "0:02:41", "throughput": 2647.89, "total_tokens": 9801656} {"current_steps": 36560, "total_steps": 38150, "loss": 0.1212, "lr": 2.6442890414222487e-07, "epoch": 9.583224115334207, "percentage": 95.83, "elapsed_time": "1:01:42", "remaining_time": "0:02:41", "throughput": 2648.0, "total_tokens": 9803416} {"current_steps": 36565, "total_steps": 38150, "loss": 0.1392, "lr": 2.6277239933027163e-07, "epoch": 9.584534731323721, "percentage": 95.85, "elapsed_time": "1:01:42", "remaining_time": "0:02:40", "throughput": 2648.01, "total_tokens": 9804568} {"current_steps": 36570, "total_steps": 38150, "loss": 0.0681, "lr": 2.611210719773133e-07, "epoch": 9.585845347313237, "percentage": 95.86, "elapsed_time": "1:01:43", "remaining_time": "0:02:39", "throughput": 2647.97, "total_tokens": 9805528} {"current_steps": 36575, "total_steps": 38150, "loss": 0.0709, "lr": 2.5947492242896776e-07, "epoch": 9.587155963302752, "percentage": 95.87, "elapsed_time": "1:01:43", "remaining_time": "0:02:39", "throughput": 2647.96, "total_tokens": 9806616} {"current_steps": 36580, "total_steps": 38150, "loss": 0.178, "lr": 2.5783395102977057e-07, "epoch": 9.588466579292268, "percentage": 95.88, "elapsed_time": "1:01:43", "remaining_time": "0:02:38", "throughput": 2648.01, "total_tokens": 9807944} {"current_steps": 36585, "total_steps": 38150, "loss": 0.1877, "lr": 2.5619815812318037e-07, "epoch": 9.589777195281782, "percentage": 95.9, "elapsed_time": "1:01:44", "remaining_time": "0:02:38", "throughput": 2648.05, "total_tokens": 9809272} {"current_steps": 36590, "total_steps": 38150, "loss": 0.1827, "lr": 2.5456754405155934e-07, "epoch": 9.591087811271297, "percentage": 95.91, "elapsed_time": "1:01:44", "remaining_time": "0:02:37", "throughput": 2648.15, "total_tokens": 9811080} {"current_steps": 36595, "total_steps": 38150, "loss": 0.1156, "lr": 2.5294210915619564e-07, "epoch": 9.592398427260813, "percentage": 95.92, "elapsed_time": "1:01:45", "remaining_time": "0:02:37", "throughput": 2648.09, "total_tokens": 9811960} {"current_steps": 36600, "total_steps": 38150, "loss": 0.0805, "lr": 2.5132185377728656e-07, "epoch": 9.593709043250328, "percentage": 95.94, "elapsed_time": "1:01:45", "remaining_time": "0:02:36", "throughput": 2648.08, "total_tokens": 9813048} {"current_steps": 36605, "total_steps": 38150, "loss": 0.0964, "lr": 2.497067782539553e-07, "epoch": 9.595019659239842, "percentage": 95.95, "elapsed_time": "1:01:46", "remaining_time": "0:02:36", "throughput": 2648.08, "total_tokens": 9814168} {"current_steps": 36610, "total_steps": 38150, "loss": 0.0759, "lr": 2.480968829242286e-07, "epoch": 9.596330275229358, "percentage": 95.96, "elapsed_time": "1:01:46", "remaining_time": "0:02:35", "throughput": 2648.09, "total_tokens": 9815416} {"current_steps": 36615, "total_steps": 38150, "loss": 0.129, "lr": 2.4649216812505373e-07, "epoch": 9.597640891218873, "percentage": 95.98, "elapsed_time": "1:01:47", "remaining_time": "0:02:35", "throughput": 2648.11, "total_tokens": 9816632} {"current_steps": 36620, "total_steps": 38150, "loss": 0.0692, "lr": 2.448926341923008e-07, "epoch": 9.598951507208389, "percentage": 95.99, "elapsed_time": "1:01:47", "remaining_time": "0:02:34", "throughput": 2648.1, "total_tokens": 9817736} {"current_steps": 36625, "total_steps": 38150, "loss": 0.1438, "lr": 2.4329828146074095e-07, "epoch": 9.600262123197902, "percentage": 96.0, "elapsed_time": "1:01:47", "remaining_time": "0:02:34", "throughput": 2648.19, "total_tokens": 9819432} {"current_steps": 36630, "total_steps": 38150, "loss": 0.1348, "lr": 2.417091102640795e-07, "epoch": 9.601572739187418, "percentage": 96.02, "elapsed_time": "1:01:48", "remaining_time": "0:02:33", "throughput": 2648.29, "total_tokens": 9821096} {"current_steps": 36635, "total_steps": 38150, "loss": 0.2069, "lr": 2.401251209349198e-07, "epoch": 9.602883355176933, "percentage": 96.03, "elapsed_time": "1:01:48", "remaining_time": "0:02:33", "throughput": 2648.35, "total_tokens": 9822584} {"current_steps": 36640, "total_steps": 38150, "loss": 0.1228, "lr": 2.385463138047911e-07, "epoch": 9.604193971166449, "percentage": 96.04, "elapsed_time": "1:01:49", "remaining_time": "0:02:32", "throughput": 2648.36, "total_tokens": 9823720} {"current_steps": 36645, "total_steps": 38150, "loss": 0.1411, "lr": 2.3697268920413462e-07, "epoch": 9.605504587155963, "percentage": 96.06, "elapsed_time": "1:01:49", "remaining_time": "0:02:32", "throughput": 2648.4, "total_tokens": 9824984} {"current_steps": 36650, "total_steps": 38150, "loss": 0.3382, "lr": 2.3540424746230916e-07, "epoch": 9.606815203145478, "percentage": 96.07, "elapsed_time": "1:01:50", "remaining_time": "0:02:31", "throughput": 2648.4, "total_tokens": 9826152} {"current_steps": 36655, "total_steps": 38150, "loss": 0.0945, "lr": 2.3384098890758267e-07, "epoch": 9.608125819134994, "percentage": 96.08, "elapsed_time": "1:01:50", "remaining_time": "0:02:31", "throughput": 2648.39, "total_tokens": 9827224} {"current_steps": 36660, "total_steps": 38150, "loss": 0.0874, "lr": 2.322829138671434e-07, "epoch": 9.609436435124508, "percentage": 96.09, "elapsed_time": "1:01:51", "remaining_time": "0:02:30", "throughput": 2648.42, "total_tokens": 9828472} {"current_steps": 36665, "total_steps": 38150, "loss": 0.1032, "lr": 2.3073002266709443e-07, "epoch": 9.610747051114023, "percentage": 96.11, "elapsed_time": "1:01:51", "remaining_time": "0:02:30", "throughput": 2648.43, "total_tokens": 9829704} {"current_steps": 36670, "total_steps": 38150, "loss": 0.0851, "lr": 2.2918231563245629e-07, "epoch": 9.612057667103539, "percentage": 96.12, "elapsed_time": "1:01:52", "remaining_time": "0:02:29", "throughput": 2648.49, "total_tokens": 9831224} {"current_steps": 36675, "total_steps": 38150, "loss": 0.1299, "lr": 2.2763979308715877e-07, "epoch": 9.613368283093054, "percentage": 96.13, "elapsed_time": "1:01:52", "remaining_time": "0:02:29", "throughput": 2648.56, "total_tokens": 9832744} {"current_steps": 36680, "total_steps": 38150, "loss": 0.1377, "lr": 2.2610245535404638e-07, "epoch": 9.614678899082568, "percentage": 96.15, "elapsed_time": "1:01:52", "remaining_time": "0:02:28", "throughput": 2648.56, "total_tokens": 9833960} {"current_steps": 36685, "total_steps": 38150, "loss": 0.156, "lr": 2.2457030275488676e-07, "epoch": 9.615989515072084, "percentage": 96.16, "elapsed_time": "1:01:53", "remaining_time": "0:02:28", "throughput": 2648.69, "total_tokens": 9835960} {"current_steps": 36690, "total_steps": 38150, "loss": 0.1339, "lr": 2.2304333561035396e-07, "epoch": 9.617300131061599, "percentage": 96.17, "elapsed_time": "1:01:53", "remaining_time": "0:02:27", "throughput": 2648.66, "total_tokens": 9836936} {"current_steps": 36695, "total_steps": 38150, "loss": 0.1013, "lr": 2.2152155424003952e-07, "epoch": 9.618610747051115, "percentage": 96.19, "elapsed_time": "1:01:54", "remaining_time": "0:02:27", "throughput": 2648.72, "total_tokens": 9838296} {"current_steps": 36700, "total_steps": 38150, "loss": 0.3366, "lr": 2.2000495896244976e-07, "epoch": 9.619921363040628, "percentage": 96.2, "elapsed_time": "1:01:54", "remaining_time": "0:02:26", "throughput": 2648.81, "total_tokens": 9839912} {"current_steps": 36705, "total_steps": 38150, "loss": 0.1301, "lr": 2.1849355009500582e-07, "epoch": 9.621231979030144, "percentage": 96.21, "elapsed_time": "1:01:55", "remaining_time": "0:02:26", "throughput": 2648.82, "total_tokens": 9841096} {"current_steps": 36710, "total_steps": 38150, "loss": 0.0969, "lr": 2.1698732795404074e-07, "epoch": 9.62254259501966, "percentage": 96.23, "elapsed_time": "1:01:55", "remaining_time": "0:02:25", "throughput": 2648.88, "total_tokens": 9842600} {"current_steps": 36715, "total_steps": 38150, "loss": 0.0826, "lr": 2.1548629285480792e-07, "epoch": 9.623853211009175, "percentage": 96.24, "elapsed_time": "1:01:56", "remaining_time": "0:02:25", "throughput": 2649.0, "total_tokens": 9844456} {"current_steps": 36720, "total_steps": 38150, "loss": 0.0845, "lr": 2.1399044511146993e-07, "epoch": 9.625163826998689, "percentage": 96.25, "elapsed_time": "1:01:56", "remaining_time": "0:02:24", "throughput": 2649.06, "total_tokens": 9845944} {"current_steps": 36725, "total_steps": 38150, "loss": 0.1206, "lr": 2.124997850371041e-07, "epoch": 9.626474442988204, "percentage": 96.26, "elapsed_time": "1:01:57", "remaining_time": "0:02:24", "throughput": 2649.13, "total_tokens": 9847400} {"current_steps": 36730, "total_steps": 38150, "loss": 0.1642, "lr": 2.1101431294370533e-07, "epoch": 9.62778505897772, "percentage": 96.28, "elapsed_time": "1:01:57", "remaining_time": "0:02:23", "throughput": 2649.11, "total_tokens": 9848440} {"current_steps": 36735, "total_steps": 38150, "loss": 0.1629, "lr": 2.0953402914217768e-07, "epoch": 9.629095674967235, "percentage": 96.29, "elapsed_time": "1:01:58", "remaining_time": "0:02:23", "throughput": 2649.15, "total_tokens": 9849816} {"current_steps": 36740, "total_steps": 38150, "loss": 0.1517, "lr": 2.0805893394234e-07, "epoch": 9.63040629095675, "percentage": 96.3, "elapsed_time": "1:01:58", "remaining_time": "0:02:22", "throughput": 2649.22, "total_tokens": 9851304} {"current_steps": 36745, "total_steps": 38150, "loss": 0.1043, "lr": 2.065890276529342e-07, "epoch": 9.631716906946265, "percentage": 96.32, "elapsed_time": "1:01:58", "remaining_time": "0:02:22", "throughput": 2649.26, "total_tokens": 9852568} {"current_steps": 36750, "total_steps": 38150, "loss": 0.1554, "lr": 2.051243105816031e-07, "epoch": 9.63302752293578, "percentage": 96.33, "elapsed_time": "1:01:59", "remaining_time": "0:02:21", "throughput": 2649.33, "total_tokens": 9854056} {"current_steps": 36755, "total_steps": 38150, "loss": 0.082, "lr": 2.0366478303491255e-07, "epoch": 9.634338138925294, "percentage": 96.34, "elapsed_time": "1:01:59", "remaining_time": "0:02:21", "throughput": 2649.34, "total_tokens": 9855240} {"current_steps": 36760, "total_steps": 38150, "loss": 0.1635, "lr": 2.0221044531834043e-07, "epoch": 9.63564875491481, "percentage": 96.36, "elapsed_time": "1:02:00", "remaining_time": "0:02:20", "throughput": 2649.4, "total_tokens": 9856760} {"current_steps": 36765, "total_steps": 38150, "loss": 0.1282, "lr": 2.0076129773627105e-07, "epoch": 9.636959370904325, "percentage": 96.37, "elapsed_time": "1:02:00", "remaining_time": "0:02:20", "throughput": 2649.47, "total_tokens": 9858360} {"current_steps": 36770, "total_steps": 38150, "loss": 0.1528, "lr": 1.9931734059201457e-07, "epoch": 9.63826998689384, "percentage": 96.38, "elapsed_time": "1:02:01", "remaining_time": "0:02:19", "throughput": 2649.51, "total_tokens": 9859624} {"current_steps": 36775, "total_steps": 38150, "loss": 0.0667, "lr": 1.9787857418778478e-07, "epoch": 9.639580602883354, "percentage": 96.4, "elapsed_time": "1:02:01", "remaining_time": "0:02:19", "throughput": 2649.53, "total_tokens": 9860856} {"current_steps": 36780, "total_steps": 38150, "loss": 0.1241, "lr": 1.9644499882471578e-07, "epoch": 9.64089121887287, "percentage": 96.41, "elapsed_time": "1:02:02", "remaining_time": "0:02:18", "throughput": 2649.59, "total_tokens": 9862296} {"current_steps": 36785, "total_steps": 38150, "loss": 0.1271, "lr": 1.9501661480285095e-07, "epoch": 9.642201834862385, "percentage": 96.42, "elapsed_time": "1:02:02", "remaining_time": "0:02:18", "throughput": 2649.67, "total_tokens": 9863784} {"current_steps": 36790, "total_steps": 38150, "loss": 0.1759, "lr": 1.935934224211483e-07, "epoch": 9.643512450851901, "percentage": 96.44, "elapsed_time": "1:02:03", "remaining_time": "0:02:17", "throughput": 2649.74, "total_tokens": 9865288} {"current_steps": 36795, "total_steps": 38150, "loss": 0.0839, "lr": 1.9217542197748074e-07, "epoch": 9.644823066841415, "percentage": 96.45, "elapsed_time": "1:02:03", "remaining_time": "0:02:17", "throughput": 2649.75, "total_tokens": 9866504} {"current_steps": 36800, "total_steps": 38150, "loss": 0.1614, "lr": 1.9076261376863303e-07, "epoch": 9.64613368283093, "percentage": 96.46, "elapsed_time": "1:02:03", "remaining_time": "0:02:16", "throughput": 2649.72, "total_tokens": 9867480} {"current_steps": 36805, "total_steps": 38150, "loss": 0.1588, "lr": 1.8935499809030476e-07, "epoch": 9.647444298820446, "percentage": 96.47, "elapsed_time": "1:02:04", "remaining_time": "0:02:16", "throughput": 2649.84, "total_tokens": 9869256} {"current_steps": 36810, "total_steps": 38150, "loss": 0.1095, "lr": 1.8795257523710197e-07, "epoch": 9.648754914809961, "percentage": 96.49, "elapsed_time": "1:02:05", "remaining_time": "0:02:15", "throughput": 2649.96, "total_tokens": 9871160} {"current_steps": 36815, "total_steps": 38150, "loss": 0.1181, "lr": 1.8655534550255648e-07, "epoch": 9.650065530799475, "percentage": 96.5, "elapsed_time": "1:02:05", "remaining_time": "0:02:15", "throughput": 2650.01, "total_tokens": 9872504} {"current_steps": 36820, "total_steps": 38150, "loss": 0.0975, "lr": 1.8516330917910108e-07, "epoch": 9.65137614678899, "percentage": 96.51, "elapsed_time": "1:02:05", "remaining_time": "0:02:14", "throughput": 2650.07, "total_tokens": 9873928} {"current_steps": 36825, "total_steps": 38150, "loss": 0.1904, "lr": 1.8377646655808877e-07, "epoch": 9.652686762778506, "percentage": 96.53, "elapsed_time": "1:02:06", "remaining_time": "0:02:14", "throughput": 2650.13, "total_tokens": 9875368} {"current_steps": 36830, "total_steps": 38150, "loss": 0.1047, "lr": 1.8239481792978464e-07, "epoch": 9.653997378768022, "percentage": 96.54, "elapsed_time": "1:02:06", "remaining_time": "0:02:13", "throughput": 2650.15, "total_tokens": 9876584} {"current_steps": 36835, "total_steps": 38150, "loss": 0.1226, "lr": 1.8101836358336287e-07, "epoch": 9.655307994757536, "percentage": 96.55, "elapsed_time": "1:02:07", "remaining_time": "0:02:13", "throughput": 2650.3, "total_tokens": 9878584} {"current_steps": 36840, "total_steps": 38150, "loss": 0.1224, "lr": 1.7964710380691251e-07, "epoch": 9.656618610747051, "percentage": 96.57, "elapsed_time": "1:02:07", "remaining_time": "0:02:12", "throughput": 2650.24, "total_tokens": 9879432} {"current_steps": 36845, "total_steps": 38150, "loss": 0.1134, "lr": 1.782810388874373e-07, "epoch": 9.657929226736567, "percentage": 96.58, "elapsed_time": "1:02:08", "remaining_time": "0:02:12", "throughput": 2650.27, "total_tokens": 9880744} {"current_steps": 36850, "total_steps": 38150, "loss": 0.1709, "lr": 1.7692016911085295e-07, "epoch": 9.65923984272608, "percentage": 96.59, "elapsed_time": "1:02:08", "remaining_time": "0:02:11", "throughput": 2650.33, "total_tokens": 9882280} {"current_steps": 36855, "total_steps": 38150, "loss": 0.2123, "lr": 1.7556449476198445e-07, "epoch": 9.660550458715596, "percentage": 96.61, "elapsed_time": "1:02:09", "remaining_time": "0:02:11", "throughput": 2650.41, "total_tokens": 9883816} {"current_steps": 36860, "total_steps": 38150, "loss": 0.1901, "lr": 1.7421401612457423e-07, "epoch": 9.661861074705111, "percentage": 96.62, "elapsed_time": "1:02:09", "remaining_time": "0:02:10", "throughput": 2650.51, "total_tokens": 9885512} {"current_steps": 36865, "total_steps": 38150, "loss": 0.085, "lr": 1.7286873348127676e-07, "epoch": 9.663171690694627, "percentage": 96.63, "elapsed_time": "1:02:10", "remaining_time": "0:02:10", "throughput": 2650.51, "total_tokens": 9886600} {"current_steps": 36870, "total_steps": 38150, "loss": 0.1106, "lr": 1.715286471136529e-07, "epoch": 9.66448230668414, "percentage": 96.64, "elapsed_time": "1:02:10", "remaining_time": "0:02:09", "throughput": 2650.48, "total_tokens": 9887592} {"current_steps": 36875, "total_steps": 38150, "loss": 0.1021, "lr": 1.7019375730218667e-07, "epoch": 9.665792922673656, "percentage": 96.66, "elapsed_time": "1:02:10", "remaining_time": "0:02:09", "throughput": 2650.43, "total_tokens": 9888504} {"current_steps": 36880, "total_steps": 38150, "loss": 0.164, "lr": 1.688640643262629e-07, "epoch": 9.667103538663172, "percentage": 96.67, "elapsed_time": "1:02:11", "remaining_time": "0:02:08", "throughput": 2650.45, "total_tokens": 9889688} {"current_steps": 36885, "total_steps": 38150, "loss": 0.2311, "lr": 1.6753956846418395e-07, "epoch": 9.668414154652687, "percentage": 96.68, "elapsed_time": "1:02:11", "remaining_time": "0:02:07", "throughput": 2650.53, "total_tokens": 9891304} {"current_steps": 36890, "total_steps": 38150, "loss": 0.104, "lr": 1.6622026999316697e-07, "epoch": 9.669724770642201, "percentage": 96.7, "elapsed_time": "1:02:12", "remaining_time": "0:02:07", "throughput": 2650.65, "total_tokens": 9893064} {"current_steps": 36895, "total_steps": 38150, "loss": 0.1408, "lr": 1.6490616918933554e-07, "epoch": 9.671035386631717, "percentage": 96.71, "elapsed_time": "1:02:12", "remaining_time": "0:02:06", "throughput": 2650.74, "total_tokens": 9894680} {"current_steps": 36900, "total_steps": 38150, "loss": 0.1382, "lr": 1.6359726632773353e-07, "epoch": 9.672346002621232, "percentage": 96.72, "elapsed_time": "1:02:13", "remaining_time": "0:02:06", "throughput": 2650.77, "total_tokens": 9896056} {"current_steps": 36905, "total_steps": 38150, "loss": 0.1903, "lr": 1.6229356168231125e-07, "epoch": 9.673656618610748, "percentage": 96.74, "elapsed_time": "1:02:13", "remaining_time": "0:02:05", "throughput": 2650.82, "total_tokens": 9897448} {"current_steps": 36910, "total_steps": 38150, "loss": 0.1601, "lr": 1.609950555259282e-07, "epoch": 9.674967234600262, "percentage": 96.75, "elapsed_time": "1:02:14", "remaining_time": "0:02:05", "throughput": 2650.92, "total_tokens": 9899128} {"current_steps": 36915, "total_steps": 38150, "loss": 0.1448, "lr": 1.5970174813036144e-07, "epoch": 9.676277850589777, "percentage": 96.76, "elapsed_time": "1:02:14", "remaining_time": "0:02:04", "throughput": 2650.98, "total_tokens": 9900552} {"current_steps": 36920, "total_steps": 38150, "loss": 0.1916, "lr": 1.5841363976629998e-07, "epoch": 9.677588466579293, "percentage": 96.78, "elapsed_time": "1:02:15", "remaining_time": "0:02:04", "throughput": 2651.0, "total_tokens": 9901784} {"current_steps": 36925, "total_steps": 38150, "loss": 0.1158, "lr": 1.5713073070333927e-07, "epoch": 9.678899082568808, "percentage": 96.79, "elapsed_time": "1:02:15", "remaining_time": "0:02:03", "throughput": 2650.99, "total_tokens": 9902968} {"current_steps": 36930, "total_steps": 38150, "loss": 0.1522, "lr": 1.5585302120998956e-07, "epoch": 9.680209698558322, "percentage": 96.8, "elapsed_time": "1:02:16", "remaining_time": "0:02:03", "throughput": 2651.06, "total_tokens": 9904472} {"current_steps": 36935, "total_steps": 38150, "loss": 0.1691, "lr": 1.545805115536786e-07, "epoch": 9.681520314547837, "percentage": 96.82, "elapsed_time": "1:02:16", "remaining_time": "0:02:02", "throughput": 2651.09, "total_tokens": 9905768} {"current_steps": 36940, "total_steps": 38150, "loss": 0.1111, "lr": 1.5331320200073497e-07, "epoch": 9.682830930537353, "percentage": 96.83, "elapsed_time": "1:02:17", "remaining_time": "0:02:02", "throughput": 2651.23, "total_tokens": 9907912} {"current_steps": 36945, "total_steps": 38150, "loss": 0.0536, "lr": 1.520510928164076e-07, "epoch": 9.684141546526867, "percentage": 96.84, "elapsed_time": "1:02:17", "remaining_time": "0:02:01", "throughput": 2651.22, "total_tokens": 9908984} {"current_steps": 36950, "total_steps": 38150, "loss": 0.2044, "lr": 1.5079418426485193e-07, "epoch": 9.685452162516382, "percentage": 96.85, "elapsed_time": "1:02:17", "remaining_time": "0:02:01", "throughput": 2651.24, "total_tokens": 9910216} {"current_steps": 36955, "total_steps": 38150, "loss": 0.1604, "lr": 1.49542476609138e-07, "epoch": 9.686762778505898, "percentage": 96.87, "elapsed_time": "1:02:18", "remaining_time": "0:02:00", "throughput": 2651.27, "total_tokens": 9911544} {"current_steps": 36960, "total_steps": 38150, "loss": 0.1311, "lr": 1.482959701112452e-07, "epoch": 9.688073394495413, "percentage": 96.88, "elapsed_time": "1:02:18", "remaining_time": "0:02:00", "throughput": 2651.35, "total_tokens": 9913352} {"current_steps": 36965, "total_steps": 38150, "loss": 0.1137, "lr": 1.47054665032062e-07, "epoch": 9.689384010484927, "percentage": 96.89, "elapsed_time": "1:02:19", "remaining_time": "0:01:59", "throughput": 2651.33, "total_tokens": 9914376} {"current_steps": 36970, "total_steps": 38150, "loss": 0.1273, "lr": 1.4581856163140008e-07, "epoch": 9.690694626474443, "percentage": 96.91, "elapsed_time": "1:02:19", "remaining_time": "0:01:59", "throughput": 2651.31, "total_tokens": 9915448} {"current_steps": 36975, "total_steps": 38150, "loss": 0.1952, "lr": 1.4458766016796632e-07, "epoch": 9.692005242463958, "percentage": 96.92, "elapsed_time": "1:02:20", "remaining_time": "0:01:58", "throughput": 2651.37, "total_tokens": 9916936} {"current_steps": 36980, "total_steps": 38150, "loss": 0.1393, "lr": 1.4336196089938802e-07, "epoch": 9.693315858453474, "percentage": 96.93, "elapsed_time": "1:02:20", "remaining_time": "0:01:58", "throughput": 2651.4, "total_tokens": 9918200} {"current_steps": 36985, "total_steps": 38150, "loss": 0.1943, "lr": 1.4214146408220163e-07, "epoch": 9.694626474442988, "percentage": 96.95, "elapsed_time": "1:02:21", "remaining_time": "0:01:57", "throughput": 2651.55, "total_tokens": 9920120} {"current_steps": 36990, "total_steps": 38150, "loss": 0.1336, "lr": 1.4092616997185837e-07, "epoch": 9.695937090432503, "percentage": 96.96, "elapsed_time": "1:02:21", "remaining_time": "0:01:57", "throughput": 2651.59, "total_tokens": 9921464} {"current_steps": 36995, "total_steps": 38150, "loss": 0.2762, "lr": 1.397160788227131e-07, "epoch": 9.697247706422019, "percentage": 96.97, "elapsed_time": "1:02:22", "remaining_time": "0:01:56", "throughput": 2651.67, "total_tokens": 9923128} {"current_steps": 37000, "total_steps": 38150, "loss": 0.1702, "lr": 1.385111908880382e-07, "epoch": 9.698558322411534, "percentage": 96.99, "elapsed_time": "1:02:22", "remaining_time": "0:01:56", "throughput": 2651.71, "total_tokens": 9924408} {"current_steps": 37005, "total_steps": 38150, "loss": 0.2028, "lr": 1.3731150642001255e-07, "epoch": 9.699868938401048, "percentage": 97.0, "elapsed_time": "1:02:23", "remaining_time": "0:01:55", "throughput": 2651.77, "total_tokens": 9925912} {"current_steps": 37010, "total_steps": 38150, "loss": 0.1353, "lr": 1.3611702566972694e-07, "epoch": 9.701179554390563, "percentage": 97.01, "elapsed_time": "1:02:23", "remaining_time": "0:01:55", "throughput": 2651.76, "total_tokens": 9927000} {"current_steps": 37015, "total_steps": 38150, "loss": 0.1407, "lr": 1.3492774888718974e-07, "epoch": 9.702490170380079, "percentage": 97.02, "elapsed_time": "1:02:23", "remaining_time": "0:01:54", "throughput": 2651.73, "total_tokens": 9927992} {"current_steps": 37020, "total_steps": 38150, "loss": 0.2649, "lr": 1.3374367632131014e-07, "epoch": 9.703800786369595, "percentage": 97.04, "elapsed_time": "1:02:24", "remaining_time": "0:01:54", "throughput": 2651.8, "total_tokens": 9929448} {"current_steps": 37025, "total_steps": 38150, "loss": 0.1376, "lr": 1.3256480821991213e-07, "epoch": 9.705111402359108, "percentage": 97.05, "elapsed_time": "1:02:24", "remaining_time": "0:01:53", "throughput": 2651.84, "total_tokens": 9930808} {"current_steps": 37030, "total_steps": 38150, "loss": 0.1696, "lr": 1.3139114482973448e-07, "epoch": 9.706422018348624, "percentage": 97.06, "elapsed_time": "1:02:25", "remaining_time": "0:01:53", "throughput": 2651.9, "total_tokens": 9932232} {"current_steps": 37035, "total_steps": 38150, "loss": 0.2084, "lr": 1.3022268639641956e-07, "epoch": 9.70773263433814, "percentage": 97.08, "elapsed_time": "1:02:25", "remaining_time": "0:01:52", "throughput": 2651.94, "total_tokens": 9933656} {"current_steps": 37040, "total_steps": 38150, "loss": 0.1302, "lr": 1.290594331645245e-07, "epoch": 9.709043250327653, "percentage": 97.09, "elapsed_time": "1:02:26", "remaining_time": "0:01:52", "throughput": 2652.02, "total_tokens": 9935368} {"current_steps": 37045, "total_steps": 38150, "loss": 0.0587, "lr": 1.279013853775185e-07, "epoch": 9.710353866317169, "percentage": 97.1, "elapsed_time": "1:02:26", "remaining_time": "0:01:51", "throughput": 2651.99, "total_tokens": 9936376} {"current_steps": 37050, "total_steps": 38150, "loss": 0.1608, "lr": 1.267485432777743e-07, "epoch": 9.711664482306684, "percentage": 97.12, "elapsed_time": "1:02:27", "remaining_time": "0:01:51", "throughput": 2651.98, "total_tokens": 9937464} {"current_steps": 37055, "total_steps": 38150, "loss": 0.1002, "lr": 1.2560090710658223e-07, "epoch": 9.7129750982962, "percentage": 97.13, "elapsed_time": "1:02:27", "remaining_time": "0:01:50", "throughput": 2652.01, "total_tokens": 9938696} {"current_steps": 37060, "total_steps": 38150, "loss": 0.0309, "lr": 1.2445847710414183e-07, "epoch": 9.714285714285714, "percentage": 97.14, "elapsed_time": "1:02:28", "remaining_time": "0:01:50", "throughput": 2651.97, "total_tokens": 9939656} {"current_steps": 37065, "total_steps": 38150, "loss": 0.1133, "lr": 1.233212535095618e-07, "epoch": 9.715596330275229, "percentage": 97.16, "elapsed_time": "1:02:28", "remaining_time": "0:01:49", "throughput": 2651.99, "total_tokens": 9940888} {"current_steps": 37070, "total_steps": 38150, "loss": 0.0987, "lr": 1.2218923656085735e-07, "epoch": 9.716906946264745, "percentage": 97.17, "elapsed_time": "1:02:28", "remaining_time": "0:01:49", "throughput": 2651.99, "total_tokens": 9942024} {"current_steps": 37075, "total_steps": 38150, "loss": 0.1676, "lr": 1.2106242649496112e-07, "epoch": 9.71821756225426, "percentage": 97.18, "elapsed_time": "1:02:29", "remaining_time": "0:01:48", "throughput": 2652.02, "total_tokens": 9943336} {"current_steps": 37080, "total_steps": 38150, "loss": 0.3596, "lr": 1.199408235477123e-07, "epoch": 9.719528178243774, "percentage": 97.2, "elapsed_time": "1:02:29", "remaining_time": "0:01:48", "throughput": 2652.13, "total_tokens": 9945096} {"current_steps": 37085, "total_steps": 38150, "loss": 0.1564, "lr": 1.188244279538564e-07, "epoch": 9.72083879423329, "percentage": 97.21, "elapsed_time": "1:02:30", "remaining_time": "0:01:47", "throughput": 2652.16, "total_tokens": 9946344} {"current_steps": 37090, "total_steps": 38150, "loss": 0.0906, "lr": 1.1771323994705929e-07, "epoch": 9.722149410222805, "percentage": 97.22, "elapsed_time": "1:02:30", "remaining_time": "0:01:47", "throughput": 2652.18, "total_tokens": 9947688} {"current_steps": 37095, "total_steps": 38150, "loss": 0.1409, "lr": 1.1660725975988773e-07, "epoch": 9.72346002621232, "percentage": 97.23, "elapsed_time": "1:02:31", "remaining_time": "0:01:46", "throughput": 2652.34, "total_tokens": 9949816} {"current_steps": 37100, "total_steps": 38150, "loss": 0.2164, "lr": 1.1550648762382044e-07, "epoch": 9.724770642201834, "percentage": 97.25, "elapsed_time": "1:02:31", "remaining_time": "0:01:46", "throughput": 2652.37, "total_tokens": 9951112} {"current_steps": 37105, "total_steps": 38150, "loss": 0.1131, "lr": 1.144109237692509e-07, "epoch": 9.72608125819135, "percentage": 97.26, "elapsed_time": "1:02:32", "remaining_time": "0:01:45", "throughput": 2652.39, "total_tokens": 9952312} {"current_steps": 37110, "total_steps": 38150, "loss": 0.1201, "lr": 1.1332056842547344e-07, "epoch": 9.727391874180865, "percentage": 97.27, "elapsed_time": "1:02:32", "remaining_time": "0:01:45", "throughput": 2652.39, "total_tokens": 9953448} {"current_steps": 37115, "total_steps": 38150, "loss": 0.1869, "lr": 1.1223542182070002e-07, "epoch": 9.728702490170381, "percentage": 97.29, "elapsed_time": "1:02:33", "remaining_time": "0:01:44", "throughput": 2652.46, "total_tokens": 9954936} {"current_steps": 37120, "total_steps": 38150, "loss": 0.2003, "lr": 1.1115548418205168e-07, "epoch": 9.730013106159895, "percentage": 97.3, "elapsed_time": "1:02:33", "remaining_time": "0:01:44", "throughput": 2652.5, "total_tokens": 9956216} {"current_steps": 37125, "total_steps": 38150, "loss": 0.1544, "lr": 1.1008075573555599e-07, "epoch": 9.73132372214941, "percentage": 97.31, "elapsed_time": "1:02:33", "remaining_time": "0:01:43", "throughput": 2652.51, "total_tokens": 9957416} {"current_steps": 37130, "total_steps": 38150, "loss": 0.0887, "lr": 1.0901123670614965e-07, "epoch": 9.732634338138926, "percentage": 97.33, "elapsed_time": "1:02:34", "remaining_time": "0:01:43", "throughput": 2652.5, "total_tokens": 9958504} {"current_steps": 37135, "total_steps": 38150, "loss": 0.1886, "lr": 1.0794692731768419e-07, "epoch": 9.73394495412844, "percentage": 97.34, "elapsed_time": "1:02:34", "remaining_time": "0:01:42", "throughput": 2652.53, "total_tokens": 9959784} {"current_steps": 37140, "total_steps": 38150, "loss": 0.2485, "lr": 1.0688782779291473e-07, "epoch": 9.735255570117955, "percentage": 97.35, "elapsed_time": "1:02:35", "remaining_time": "0:01:42", "throughput": 2652.64, "total_tokens": 9961576} {"current_steps": 37145, "total_steps": 38150, "loss": 0.1229, "lr": 1.0583393835351396e-07, "epoch": 9.73656618610747, "percentage": 97.37, "elapsed_time": "1:02:35", "remaining_time": "0:01:41", "throughput": 2652.69, "total_tokens": 9963032} {"current_steps": 37150, "total_steps": 38150, "loss": 0.0875, "lr": 1.0478525922005545e-07, "epoch": 9.737876802096986, "percentage": 97.38, "elapsed_time": "1:02:36", "remaining_time": "0:01:41", "throughput": 2652.68, "total_tokens": 9964056} {"current_steps": 37155, "total_steps": 38150, "loss": 0.065, "lr": 1.0374179061202749e-07, "epoch": 9.7391874180865, "percentage": 97.39, "elapsed_time": "1:02:36", "remaining_time": "0:01:40", "throughput": 2652.71, "total_tokens": 9965368} {"current_steps": 37160, "total_steps": 38150, "loss": 0.1973, "lr": 1.0270353274782207e-07, "epoch": 9.740498034076015, "percentage": 97.4, "elapsed_time": "1:02:37", "remaining_time": "0:01:40", "throughput": 2652.73, "total_tokens": 9966680} {"current_steps": 37165, "total_steps": 38150, "loss": 0.1115, "lr": 1.0167048584475147e-07, "epoch": 9.741808650065531, "percentage": 97.42, "elapsed_time": "1:02:37", "remaining_time": "0:01:39", "throughput": 2652.73, "total_tokens": 9967864} {"current_steps": 37170, "total_steps": 38150, "loss": 0.1481, "lr": 1.006426501190233e-07, "epoch": 9.743119266055047, "percentage": 97.43, "elapsed_time": "1:02:38", "remaining_time": "0:01:39", "throughput": 2652.82, "total_tokens": 9969448} {"current_steps": 37175, "total_steps": 38150, "loss": 0.1174, "lr": 9.962002578576823e-08, "epoch": 9.74442988204456, "percentage": 97.44, "elapsed_time": "1:02:38", "remaining_time": "0:01:38", "throughput": 2652.84, "total_tokens": 9970712} {"current_steps": 37180, "total_steps": 38150, "loss": 0.1594, "lr": 9.860261305901785e-08, "epoch": 9.745740498034076, "percentage": 97.46, "elapsed_time": "1:02:38", "remaining_time": "0:01:38", "throughput": 2652.81, "total_tokens": 9971736} {"current_steps": 37185, "total_steps": 38150, "loss": 0.1186, "lr": 9.759041215171295e-08, "epoch": 9.747051114023591, "percentage": 97.47, "elapsed_time": "1:02:39", "remaining_time": "0:01:37", "throughput": 2652.81, "total_tokens": 9972872} {"current_steps": 37190, "total_steps": 38150, "loss": 0.2553, "lr": 9.658342327570902e-08, "epoch": 9.748361730013107, "percentage": 97.48, "elapsed_time": "1:02:39", "remaining_time": "0:01:37", "throughput": 2652.76, "total_tokens": 9973784} {"current_steps": 37195, "total_steps": 38150, "loss": 0.0937, "lr": 9.55816466417625e-08, "epoch": 9.74967234600262, "percentage": 97.5, "elapsed_time": "1:02:40", "remaining_time": "0:01:36", "throughput": 2652.74, "total_tokens": 9974840} {"current_steps": 37200, "total_steps": 38150, "loss": 0.1639, "lr": 9.458508245954456e-08, "epoch": 9.750982961992136, "percentage": 97.51, "elapsed_time": "1:02:40", "remaining_time": "0:01:36", "throughput": 2652.76, "total_tokens": 9976088} {"current_steps": 37205, "total_steps": 38150, "loss": 0.1298, "lr": 9.359373093763835e-08, "epoch": 9.752293577981652, "percentage": 97.52, "elapsed_time": "1:02:41", "remaining_time": "0:01:35", "throughput": 2652.81, "total_tokens": 9977432} {"current_steps": 37210, "total_steps": 38150, "loss": 0.1769, "lr": 9.260759228352789e-08, "epoch": 9.753604193971167, "percentage": 97.54, "elapsed_time": "1:02:41", "remaining_time": "0:01:35", "throughput": 2652.77, "total_tokens": 9978392} {"current_steps": 37215, "total_steps": 38150, "loss": 0.2187, "lr": 9.162666670361198e-08, "epoch": 9.754914809960681, "percentage": 97.55, "elapsed_time": "1:02:41", "remaining_time": "0:01:34", "throughput": 2652.87, "total_tokens": 9980024} {"current_steps": 37220, "total_steps": 38150, "loss": 0.1725, "lr": 9.065095440319582e-08, "epoch": 9.756225425950197, "percentage": 97.56, "elapsed_time": "1:02:42", "remaining_time": "0:01:34", "throughput": 2652.91, "total_tokens": 9981416} {"current_steps": 37225, "total_steps": 38150, "loss": 0.0916, "lr": 8.968045558649663e-08, "epoch": 9.757536041939712, "percentage": 97.58, "elapsed_time": "1:02:42", "remaining_time": "0:01:33", "throughput": 2652.94, "total_tokens": 9982664} {"current_steps": 37230, "total_steps": 38150, "loss": 0.096, "lr": 8.871517045663524e-08, "epoch": 9.758846657929226, "percentage": 97.59, "elapsed_time": "1:02:43", "remaining_time": "0:01:32", "throughput": 2652.99, "total_tokens": 9984040} {"current_steps": 37235, "total_steps": 38150, "loss": 0.1811, "lr": 8.775509921564728e-08, "epoch": 9.760157273918741, "percentage": 97.6, "elapsed_time": "1:02:43", "remaining_time": "0:01:32", "throughput": 2653.02, "total_tokens": 9985400} {"current_steps": 37240, "total_steps": 38150, "loss": 0.26, "lr": 8.680024206446924e-08, "epoch": 9.761467889908257, "percentage": 97.61, "elapsed_time": "1:02:44", "remaining_time": "0:01:31", "throughput": 2653.03, "total_tokens": 9986584} {"current_steps": 37245, "total_steps": 38150, "loss": 0.2173, "lr": 8.585059920295512e-08, "epoch": 9.762778505897773, "percentage": 97.63, "elapsed_time": "1:02:44", "remaining_time": "0:01:31", "throughput": 2653.1, "total_tokens": 9988088} {"current_steps": 37250, "total_steps": 38150, "loss": 0.2054, "lr": 8.490617082985986e-08, "epoch": 9.764089121887286, "percentage": 97.64, "elapsed_time": "1:02:45", "remaining_time": "0:01:30", "throughput": 2653.09, "total_tokens": 9989192} {"current_steps": 37255, "total_steps": 38150, "loss": 0.1346, "lr": 8.396695714285585e-08, "epoch": 9.765399737876802, "percentage": 97.65, "elapsed_time": "1:02:45", "remaining_time": "0:01:30", "throughput": 2653.11, "total_tokens": 9990392} {"current_steps": 37260, "total_steps": 38150, "loss": 0.1504, "lr": 8.303295833851365e-08, "epoch": 9.766710353866317, "percentage": 97.67, "elapsed_time": "1:02:45", "remaining_time": "0:01:29", "throughput": 2653.13, "total_tokens": 9991608} {"current_steps": 37265, "total_steps": 38150, "loss": 0.1396, "lr": 8.210417461232412e-08, "epoch": 9.768020969855833, "percentage": 97.68, "elapsed_time": "1:02:46", "remaining_time": "0:01:29", "throughput": 2653.16, "total_tokens": 9992968} {"current_steps": 37270, "total_steps": 38150, "loss": 0.1273, "lr": 8.11806061586734e-08, "epoch": 9.769331585845347, "percentage": 97.69, "elapsed_time": "1:02:46", "remaining_time": "0:01:28", "throughput": 2653.2, "total_tokens": 9994280} {"current_steps": 37275, "total_steps": 38150, "loss": 0.1413, "lr": 8.026225317086522e-08, "epoch": 9.770642201834862, "percentage": 97.71, "elapsed_time": "1:02:47", "remaining_time": "0:01:28", "throughput": 2653.25, "total_tokens": 9995736} {"current_steps": 37280, "total_steps": 38150, "loss": 0.1667, "lr": 7.934911584110971e-08, "epoch": 9.771952817824378, "percentage": 97.72, "elapsed_time": "1:02:47", "remaining_time": "0:01:27", "throughput": 2653.3, "total_tokens": 9997064} {"current_steps": 37285, "total_steps": 38150, "loss": 0.1005, "lr": 7.844119436052622e-08, "epoch": 9.773263433813893, "percentage": 97.73, "elapsed_time": "1:02:48", "remaining_time": "0:01:27", "throughput": 2653.27, "total_tokens": 9998072} {"current_steps": 37290, "total_steps": 38150, "loss": 0.1651, "lr": 7.753848891913772e-08, "epoch": 9.774574049803407, "percentage": 97.75, "elapsed_time": "1:02:48", "remaining_time": "0:01:26", "throughput": 2653.32, "total_tokens": 9999416} {"current_steps": 37295, "total_steps": 38150, "loss": 0.1225, "lr": 7.664099970588201e-08, "epoch": 9.775884665792923, "percentage": 97.76, "elapsed_time": "1:02:49", "remaining_time": "0:01:26", "throughput": 2653.33, "total_tokens": 10000648} {"current_steps": 37300, "total_steps": 38150, "loss": 0.0339, "lr": 7.57487269085977e-08, "epoch": 9.777195281782438, "percentage": 97.77, "elapsed_time": "1:02:49", "remaining_time": "0:01:25", "throughput": 2653.27, "total_tokens": 10001544} {"current_steps": 37305, "total_steps": 38150, "loss": 0.0857, "lr": 7.486167071404371e-08, "epoch": 9.778505897771954, "percentage": 97.79, "elapsed_time": "1:02:49", "remaining_time": "0:01:25", "throughput": 2653.27, "total_tokens": 10002648} {"current_steps": 37310, "total_steps": 38150, "loss": 0.1473, "lr": 7.397983130787156e-08, "epoch": 9.779816513761467, "percentage": 97.8, "elapsed_time": "1:02:50", "remaining_time": "0:01:24", "throughput": 2653.3, "total_tokens": 10004024} {"current_steps": 37315, "total_steps": 38150, "loss": 0.1754, "lr": 7.310320887465305e-08, "epoch": 9.781127129750983, "percentage": 97.81, "elapsed_time": "1:02:50", "remaining_time": "0:01:24", "throughput": 2653.32, "total_tokens": 10005288} {"current_steps": 37320, "total_steps": 38150, "loss": 0.1704, "lr": 7.223180359786086e-08, "epoch": 9.782437745740499, "percentage": 97.82, "elapsed_time": "1:02:51", "remaining_time": "0:01:23", "throughput": 2653.36, "total_tokens": 10006600} {"current_steps": 37325, "total_steps": 38150, "loss": 0.1791, "lr": 7.136561565988242e-08, "epoch": 9.783748361730012, "percentage": 97.84, "elapsed_time": "1:02:51", "remaining_time": "0:01:23", "throughput": 2653.47, "total_tokens": 10008328} {"current_steps": 37330, "total_steps": 38150, "loss": 0.1542, "lr": 7.050464524200607e-08, "epoch": 9.785058977719528, "percentage": 97.85, "elapsed_time": "1:02:52", "remaining_time": "0:01:22", "throughput": 2653.49, "total_tokens": 10009528} {"current_steps": 37335, "total_steps": 38150, "loss": 0.1194, "lr": 6.964889252443485e-08, "epoch": 9.786369593709043, "percentage": 97.86, "elapsed_time": "1:02:52", "remaining_time": "0:01:22", "throughput": 2653.53, "total_tokens": 10010920} {"current_steps": 37340, "total_steps": 38150, "loss": 0.2579, "lr": 6.879835768627274e-08, "epoch": 9.787680209698559, "percentage": 97.88, "elapsed_time": "1:02:53", "remaining_time": "0:01:21", "throughput": 2653.63, "total_tokens": 10012584} {"current_steps": 37345, "total_steps": 38150, "loss": 0.1656, "lr": 6.795304090553567e-08, "epoch": 9.788990825688073, "percentage": 97.89, "elapsed_time": "1:02:53", "remaining_time": "0:01:21", "throughput": 2653.67, "total_tokens": 10013864} {"current_steps": 37350, "total_steps": 38150, "loss": 0.2039, "lr": 6.711294235914877e-08, "epoch": 9.790301441677588, "percentage": 97.9, "elapsed_time": "1:02:54", "remaining_time": "0:01:20", "throughput": 2653.81, "total_tokens": 10016008} {"current_steps": 37355, "total_steps": 38150, "loss": 0.1005, "lr": 6.627806222294086e-08, "epoch": 9.791612057667104, "percentage": 97.92, "elapsed_time": "1:02:54", "remaining_time": "0:01:20", "throughput": 2653.83, "total_tokens": 10017176} {"current_steps": 37360, "total_steps": 38150, "loss": 0.1054, "lr": 6.544840067165548e-08, "epoch": 9.79292267365662, "percentage": 97.93, "elapsed_time": "1:02:55", "remaining_time": "0:01:19", "throughput": 2653.88, "total_tokens": 10018584} {"current_steps": 37365, "total_steps": 38150, "loss": 0.1791, "lr": 6.462395787893427e-08, "epoch": 9.794233289646133, "percentage": 97.94, "elapsed_time": "1:02:55", "remaining_time": "0:01:19", "throughput": 2653.98, "total_tokens": 10020392} {"current_steps": 37370, "total_steps": 38150, "loss": 0.1947, "lr": 6.380473401733366e-08, "epoch": 9.795543905635649, "percentage": 97.96, "elapsed_time": "1:02:56", "remaining_time": "0:01:18", "throughput": 2654.12, "total_tokens": 10022424} {"current_steps": 37375, "total_steps": 38150, "loss": 0.1129, "lr": 6.299072925831373e-08, "epoch": 9.796854521625164, "percentage": 97.97, "elapsed_time": "1:02:56", "remaining_time": "0:01:18", "throughput": 2654.25, "total_tokens": 10024296} {"current_steps": 37380, "total_steps": 38150, "loss": 0.1901, "lr": 6.218194377224928e-08, "epoch": 9.79816513761468, "percentage": 97.98, "elapsed_time": "1:02:57", "remaining_time": "0:01:17", "throughput": 2654.23, "total_tokens": 10025304} {"current_steps": 37385, "total_steps": 38150, "loss": 0.0631, "lr": 6.137837772841326e-08, "epoch": 9.799475753604193, "percentage": 97.99, "elapsed_time": "1:02:57", "remaining_time": "0:01:17", "throughput": 2654.2, "total_tokens": 10026344} {"current_steps": 37390, "total_steps": 38150, "loss": 0.1662, "lr": 6.058003129499334e-08, "epoch": 9.800786369593709, "percentage": 98.01, "elapsed_time": "1:02:57", "remaining_time": "0:01:16", "throughput": 2654.21, "total_tokens": 10027464} {"current_steps": 37395, "total_steps": 38150, "loss": 0.1315, "lr": 5.978690463908088e-08, "epoch": 9.802096985583225, "percentage": 98.02, "elapsed_time": "1:02:58", "remaining_time": "0:01:16", "throughput": 2654.23, "total_tokens": 10028680} {"current_steps": 37400, "total_steps": 38150, "loss": 0.1931, "lr": 5.8998997926676405e-08, "epoch": 9.80340760157274, "percentage": 98.03, "elapsed_time": "1:02:58", "remaining_time": "0:01:15", "throughput": 2654.25, "total_tokens": 10029928} {"current_steps": 37405, "total_steps": 38150, "loss": 0.1339, "lr": 5.821631132268412e-08, "epoch": 9.804718217562254, "percentage": 98.05, "elapsed_time": "1:02:59", "remaining_time": "0:01:15", "throughput": 2654.27, "total_tokens": 10031208} {"current_steps": 37410, "total_steps": 38150, "loss": 0.1047, "lr": 5.743884499092578e-08, "epoch": 9.80602883355177, "percentage": 98.06, "elapsed_time": "1:02:59", "remaining_time": "0:01:14", "throughput": 2654.23, "total_tokens": 10032136} {"current_steps": 37415, "total_steps": 38150, "loss": 0.1277, "lr": 5.6666599094115646e-08, "epoch": 9.807339449541285, "percentage": 98.07, "elapsed_time": "1:03:00", "remaining_time": "0:01:14", "throughput": 2654.21, "total_tokens": 10033176} {"current_steps": 37420, "total_steps": 38150, "loss": 0.1038, "lr": 5.58995737938911e-08, "epoch": 9.808650065530799, "percentage": 98.09, "elapsed_time": "1:03:00", "remaining_time": "0:01:13", "throughput": 2654.2, "total_tokens": 10034280} {"current_steps": 37425, "total_steps": 38150, "loss": 0.1245, "lr": 5.513776925078207e-08, "epoch": 9.809960681520314, "percentage": 98.1, "elapsed_time": "1:03:01", "remaining_time": "0:01:13", "throughput": 2654.31, "total_tokens": 10035960} {"current_steps": 37430, "total_steps": 38150, "loss": 0.07, "lr": 5.4381185624238776e-08, "epoch": 9.81127129750983, "percentage": 98.11, "elapsed_time": "1:03:01", "remaining_time": "0:01:12", "throughput": 2654.29, "total_tokens": 10036984} {"current_steps": 37435, "total_steps": 38150, "loss": 0.1575, "lr": 5.362982307261233e-08, "epoch": 9.812581913499345, "percentage": 98.13, "elapsed_time": "1:03:01", "remaining_time": "0:01:12", "throughput": 2654.26, "total_tokens": 10038008} {"current_steps": 37440, "total_steps": 38150, "loss": 0.1566, "lr": 5.2883681753157497e-08, "epoch": 9.813892529488859, "percentage": 98.14, "elapsed_time": "1:03:02", "remaining_time": "0:01:11", "throughput": 2654.24, "total_tokens": 10039112} {"current_steps": 37445, "total_steps": 38150, "loss": 0.0962, "lr": 5.214276182204381e-08, "epoch": 9.815203145478375, "percentage": 98.15, "elapsed_time": "1:03:02", "remaining_time": "0:01:11", "throughput": 2654.23, "total_tokens": 10040216} {"current_steps": 37450, "total_steps": 38150, "loss": 0.1576, "lr": 5.140706343434165e-08, "epoch": 9.81651376146789, "percentage": 98.17, "elapsed_time": "1:03:03", "remaining_time": "0:01:10", "throughput": 2654.26, "total_tokens": 10041528} {"current_steps": 37455, "total_steps": 38150, "loss": 0.1097, "lr": 5.0676586744036194e-08, "epoch": 9.817824377457406, "percentage": 98.18, "elapsed_time": "1:03:03", "remaining_time": "0:01:10", "throughput": 2654.25, "total_tokens": 10042600} {"current_steps": 37460, "total_steps": 38150, "loss": 0.1815, "lr": 4.9951331904007915e-08, "epoch": 9.81913499344692, "percentage": 98.19, "elapsed_time": "1:03:04", "remaining_time": "0:01:09", "throughput": 2654.29, "total_tokens": 10043960} {"current_steps": 37465, "total_steps": 38150, "loss": 0.1454, "lr": 4.923129906606039e-08, "epoch": 9.820445609436435, "percentage": 98.2, "elapsed_time": "1:03:04", "remaining_time": "0:01:09", "throughput": 2654.29, "total_tokens": 10045080} {"current_steps": 37470, "total_steps": 38150, "loss": 0.1158, "lr": 4.851648838088696e-08, "epoch": 9.82175622542595, "percentage": 98.22, "elapsed_time": "1:03:04", "remaining_time": "0:01:08", "throughput": 2654.35, "total_tokens": 10046440} {"current_steps": 37475, "total_steps": 38150, "loss": 0.1061, "lr": 4.7806899998101283e-08, "epoch": 9.823066841415466, "percentage": 98.23, "elapsed_time": "1:03:05", "remaining_time": "0:01:08", "throughput": 2654.31, "total_tokens": 10047416} {"current_steps": 37480, "total_steps": 38150, "loss": 0.1268, "lr": 4.71025340662179e-08, "epoch": 9.82437745740498, "percentage": 98.24, "elapsed_time": "1:03:05", "remaining_time": "0:01:07", "throughput": 2654.33, "total_tokens": 10048648} {"current_steps": 37485, "total_steps": 38150, "loss": 0.1763, "lr": 4.6403390732654985e-08, "epoch": 9.825688073394495, "percentage": 98.26, "elapsed_time": "1:03:06", "remaining_time": "0:01:07", "throughput": 2654.36, "total_tokens": 10050008} {"current_steps": 37490, "total_steps": 38150, "loss": 0.1758, "lr": 4.570947014374827e-08, "epoch": 9.82699868938401, "percentage": 98.27, "elapsed_time": "1:03:06", "remaining_time": "0:01:06", "throughput": 2654.47, "total_tokens": 10051752} {"current_steps": 37495, "total_steps": 38150, "loss": 0.1611, "lr": 4.502077244473435e-08, "epoch": 9.828309305373526, "percentage": 98.28, "elapsed_time": "1:03:07", "remaining_time": "0:01:06", "throughput": 2654.49, "total_tokens": 10053032} {"current_steps": 37500, "total_steps": 38150, "loss": 0.0778, "lr": 4.4337297779750705e-08, "epoch": 9.82961992136304, "percentage": 98.3, "elapsed_time": "1:03:07", "remaining_time": "0:01:05", "throughput": 2654.48, "total_tokens": 10054104} {"current_steps": 37505, "total_steps": 38150, "loss": 0.0905, "lr": 4.365904629185236e-08, "epoch": 9.830930537352556, "percentage": 98.31, "elapsed_time": "1:03:08", "remaining_time": "0:01:05", "throughput": 2654.47, "total_tokens": 10055288} {"current_steps": 37510, "total_steps": 38150, "loss": 0.1889, "lr": 4.298601812299241e-08, "epoch": 9.832241153342071, "percentage": 98.32, "elapsed_time": "1:03:08", "remaining_time": "0:01:04", "throughput": 2654.55, "total_tokens": 10056808} {"current_steps": 37515, "total_steps": 38150, "loss": 0.1385, "lr": 4.2318213414038745e-08, "epoch": 9.833551769331585, "percentage": 98.34, "elapsed_time": "1:03:08", "remaining_time": "0:01:04", "throughput": 2654.56, "total_tokens": 10057960} {"current_steps": 37520, "total_steps": 38150, "loss": 0.1577, "lr": 4.1655632304757334e-08, "epoch": 9.8348623853211, "percentage": 98.35, "elapsed_time": "1:03:09", "remaining_time": "0:01:03", "throughput": 2654.62, "total_tokens": 10059544} {"current_steps": 37525, "total_steps": 38150, "loss": 0.0989, "lr": 4.0998274933828905e-08, "epoch": 9.836173001310616, "percentage": 98.36, "elapsed_time": "1:03:09", "remaining_time": "0:01:03", "throughput": 2654.63, "total_tokens": 10060680} {"current_steps": 37530, "total_steps": 38150, "loss": 0.1692, "lr": 4.034614143883508e-08, "epoch": 9.837483617300132, "percentage": 98.37, "elapsed_time": "1:03:10", "remaining_time": "0:01:02", "throughput": 2654.64, "total_tokens": 10061848} {"current_steps": 37535, "total_steps": 38150, "loss": 0.1286, "lr": 3.969923195626668e-08, "epoch": 9.838794233289645, "percentage": 98.39, "elapsed_time": "1:03:10", "remaining_time": "0:01:02", "throughput": 2654.69, "total_tokens": 10063224} {"current_steps": 37540, "total_steps": 38150, "loss": 0.1245, "lr": 3.9057546621520946e-08, "epoch": 9.840104849279161, "percentage": 98.4, "elapsed_time": "1:03:11", "remaining_time": "0:01:01", "throughput": 2654.74, "total_tokens": 10064728} {"current_steps": 37545, "total_steps": 38150, "loss": 0.062, "lr": 3.842108556890156e-08, "epoch": 9.841415465268676, "percentage": 98.41, "elapsed_time": "1:03:11", "remaining_time": "0:01:01", "throughput": 2654.74, "total_tokens": 10065832} {"current_steps": 37550, "total_steps": 38150, "loss": 0.1085, "lr": 3.778984893161863e-08, "epoch": 9.842726081258192, "percentage": 98.43, "elapsed_time": "1:03:12", "remaining_time": "0:01:00", "throughput": 2654.77, "total_tokens": 10067112} {"current_steps": 37555, "total_steps": 38150, "loss": 0.2165, "lr": 3.7163836841791476e-08, "epoch": 9.844036697247706, "percentage": 98.44, "elapsed_time": "1:03:12", "remaining_time": "0:01:00", "throughput": 2654.76, "total_tokens": 10068264} {"current_steps": 37560, "total_steps": 38150, "loss": 0.173, "lr": 3.654304943043752e-08, "epoch": 9.845347313237221, "percentage": 98.45, "elapsed_time": "1:03:12", "remaining_time": "0:00:59", "throughput": 2654.77, "total_tokens": 10069448} {"current_steps": 37565, "total_steps": 38150, "loss": 0.2022, "lr": 3.5927486827491696e-08, "epoch": 9.846657929226737, "percentage": 98.47, "elapsed_time": "1:03:13", "remaining_time": "0:00:59", "throughput": 2654.82, "total_tokens": 10070776} {"current_steps": 37570, "total_steps": 38150, "loss": 0.0696, "lr": 3.531714916178708e-08, "epoch": 9.847968545216252, "percentage": 98.48, "elapsed_time": "1:03:13", "remaining_time": "0:00:58", "throughput": 2654.83, "total_tokens": 10071928} {"current_steps": 37575, "total_steps": 38150, "loss": 0.1198, "lr": 3.4712036561068693e-08, "epoch": 9.849279161205766, "percentage": 98.49, "elapsed_time": "1:03:14", "remaining_time": "0:00:58", "throughput": 2654.79, "total_tokens": 10072888} {"current_steps": 37580, "total_steps": 38150, "loss": 0.058, "lr": 3.4112149151982466e-08, "epoch": 9.850589777195282, "percentage": 98.51, "elapsed_time": "1:03:14", "remaining_time": "0:00:57", "throughput": 2654.78, "total_tokens": 10074008} {"current_steps": 37585, "total_steps": 38150, "loss": 0.1727, "lr": 3.351748706008628e-08, "epoch": 9.851900393184797, "percentage": 98.52, "elapsed_time": "1:03:15", "remaining_time": "0:00:57", "throughput": 2654.85, "total_tokens": 10075544} {"current_steps": 37590, "total_steps": 38150, "loss": 0.2012, "lr": 3.292805040984171e-08, "epoch": 9.853211009174313, "percentage": 98.53, "elapsed_time": "1:03:15", "remaining_time": "0:00:56", "throughput": 2654.89, "total_tokens": 10076920} {"current_steps": 37595, "total_steps": 38150, "loss": 0.1669, "lr": 3.234383932461671e-08, "epoch": 9.854521625163827, "percentage": 98.55, "elapsed_time": "1:03:16", "remaining_time": "0:00:56", "throughput": 2654.96, "total_tokens": 10078456} {"current_steps": 37600, "total_steps": 38150, "loss": 0.1817, "lr": 3.176485392668571e-08, "epoch": 9.855832241153342, "percentage": 98.56, "elapsed_time": "1:03:16", "remaining_time": "0:00:55", "throughput": 2655.03, "total_tokens": 10079896} {"current_steps": 37605, "total_steps": 38150, "loss": 0.1492, "lr": 3.119109433722955e-08, "epoch": 9.857142857142858, "percentage": 98.57, "elapsed_time": "1:03:17", "remaining_time": "0:00:55", "throughput": 2655.11, "total_tokens": 10081512} {"current_steps": 37610, "total_steps": 38150, "loss": 0.333, "lr": 3.0622560676332734e-08, "epoch": 9.858453473132371, "percentage": 98.58, "elapsed_time": "1:03:17", "remaining_time": "0:00:54", "throughput": 2655.19, "total_tokens": 10083096} {"current_steps": 37615, "total_steps": 38150, "loss": 0.163, "lr": 3.005925306299173e-08, "epoch": 9.859764089121887, "percentage": 98.6, "elapsed_time": "1:03:18", "remaining_time": "0:00:54", "throughput": 2655.25, "total_tokens": 10084632} {"current_steps": 37620, "total_steps": 38150, "loss": 0.1332, "lr": 2.9501171615103907e-08, "epoch": 9.861074705111402, "percentage": 98.61, "elapsed_time": "1:03:18", "remaining_time": "0:00:53", "throughput": 2655.31, "total_tokens": 10086152} {"current_steps": 37625, "total_steps": 38150, "loss": 0.1895, "lr": 2.8948316449473044e-08, "epoch": 9.862385321100918, "percentage": 98.62, "elapsed_time": "1:03:18", "remaining_time": "0:00:53", "throughput": 2655.4, "total_tokens": 10087864} {"current_steps": 37630, "total_steps": 38150, "loss": 0.186, "lr": 2.840068768181492e-08, "epoch": 9.863695937090432, "percentage": 98.64, "elapsed_time": "1:03:19", "remaining_time": "0:00:52", "throughput": 2655.45, "total_tokens": 10089288} {"current_steps": 37635, "total_steps": 38150, "loss": 0.1775, "lr": 2.785828542674618e-08, "epoch": 9.865006553079947, "percentage": 98.65, "elapsed_time": "1:03:19", "remaining_time": "0:00:51", "throughput": 2655.49, "total_tokens": 10090552} {"current_steps": 37640, "total_steps": 38150, "loss": 0.1587, "lr": 2.7321109797787125e-08, "epoch": 9.866317169069463, "percentage": 98.66, "elapsed_time": "1:03:20", "remaining_time": "0:00:51", "throughput": 2655.51, "total_tokens": 10091944} {"current_steps": 37645, "total_steps": 38150, "loss": 0.1536, "lr": 2.6789160907372822e-08, "epoch": 9.867627785058978, "percentage": 98.68, "elapsed_time": "1:03:20", "remaining_time": "0:00:50", "throughput": 2655.57, "total_tokens": 10093400} {"current_steps": 37650, "total_steps": 38150, "loss": 0.1645, "lr": 2.626243886683366e-08, "epoch": 9.868938401048492, "percentage": 98.69, "elapsed_time": "1:03:21", "remaining_time": "0:00:50", "throughput": 2655.58, "total_tokens": 10094536} {"current_steps": 37655, "total_steps": 38150, "loss": 0.1396, "lr": 2.574094378641756e-08, "epoch": 9.870249017038008, "percentage": 98.7, "elapsed_time": "1:03:21", "remaining_time": "0:00:49", "throughput": 2655.59, "total_tokens": 10095736} {"current_steps": 37660, "total_steps": 38150, "loss": 0.2736, "lr": 2.5224675775270544e-08, "epoch": 9.871559633027523, "percentage": 98.72, "elapsed_time": "1:03:22", "remaining_time": "0:00:49", "throughput": 2655.6, "total_tokens": 10096888} {"current_steps": 37665, "total_steps": 38150, "loss": 0.0679, "lr": 2.4713634941442298e-08, "epoch": 9.872870249017039, "percentage": 98.73, "elapsed_time": "1:03:22", "remaining_time": "0:00:48", "throughput": 2655.61, "total_tokens": 10098072} {"current_steps": 37670, "total_steps": 38150, "loss": 0.2254, "lr": 2.4207821391900032e-08, "epoch": 9.874180865006553, "percentage": 98.74, "elapsed_time": "1:03:23", "remaining_time": "0:00:48", "throughput": 2655.71, "total_tokens": 10099832} {"current_steps": 37675, "total_steps": 38150, "loss": 0.0752, "lr": 2.370723523250351e-08, "epoch": 9.875491480996068, "percentage": 98.75, "elapsed_time": "1:03:23", "remaining_time": "0:00:47", "throughput": 2655.79, "total_tokens": 10101352} {"current_steps": 37680, "total_steps": 38150, "loss": 0.1054, "lr": 2.321187656802726e-08, "epoch": 9.876802096985584, "percentage": 98.77, "elapsed_time": "1:03:23", "remaining_time": "0:00:47", "throughput": 2655.82, "total_tokens": 10102632} {"current_steps": 37685, "total_steps": 38150, "loss": 0.1462, "lr": 2.272174550214945e-08, "epoch": 9.8781127129751, "percentage": 98.78, "elapsed_time": "1:03:24", "remaining_time": "0:00:46", "throughput": 2655.8, "total_tokens": 10103688} {"current_steps": 37690, "total_steps": 38150, "loss": 0.0636, "lr": 2.223684213745192e-08, "epoch": 9.879423328964613, "percentage": 98.79, "elapsed_time": "1:03:24", "remaining_time": "0:00:46", "throughput": 2655.82, "total_tokens": 10104904} {"current_steps": 37695, "total_steps": 38150, "loss": 0.1645, "lr": 2.1757166575425702e-08, "epoch": 9.880733944954128, "percentage": 98.81, "elapsed_time": "1:03:25", "remaining_time": "0:00:45", "throughput": 2655.87, "total_tokens": 10106328} {"current_steps": 37700, "total_steps": 38150, "loss": 0.0896, "lr": 2.1282718916465494e-08, "epoch": 9.882044560943644, "percentage": 98.82, "elapsed_time": "1:03:25", "remaining_time": "0:00:45", "throughput": 2655.87, "total_tokens": 10107496} {"current_steps": 37705, "total_steps": 38150, "loss": 0.1148, "lr": 2.0813499259872414e-08, "epoch": 9.883355176933158, "percentage": 98.83, "elapsed_time": "1:03:26", "remaining_time": "0:00:44", "throughput": 2655.86, "total_tokens": 10108632} {"current_steps": 37710, "total_steps": 38150, "loss": 0.1435, "lr": 2.0349507703851244e-08, "epoch": 9.884665792922673, "percentage": 98.85, "elapsed_time": "1:03:26", "remaining_time": "0:00:44", "throughput": 2655.91, "total_tokens": 10110008} {"current_steps": 37715, "total_steps": 38150, "loss": 0.174, "lr": 1.9890744345518742e-08, "epoch": 9.885976408912189, "percentage": 98.86, "elapsed_time": "1:03:27", "remaining_time": "0:00:43", "throughput": 2655.94, "total_tokens": 10111272} {"current_steps": 37720, "total_steps": 38150, "loss": 0.1573, "lr": 1.9437209280889768e-08, "epoch": 9.887287024901704, "percentage": 98.87, "elapsed_time": "1:03:27", "remaining_time": "0:00:43", "throughput": 2656.04, "total_tokens": 10112920} {"current_steps": 37725, "total_steps": 38150, "loss": 0.3003, "lr": 1.8988902604891166e-08, "epoch": 9.888597640891218, "percentage": 98.89, "elapsed_time": "1:03:28", "remaining_time": "0:00:42", "throughput": 2656.16, "total_tokens": 10114760} {"current_steps": 37730, "total_steps": 38150, "loss": 0.2854, "lr": 1.8545824411350665e-08, "epoch": 9.889908256880734, "percentage": 98.9, "elapsed_time": "1:03:28", "remaining_time": "0:00:42", "throughput": 2656.21, "total_tokens": 10116120} {"current_steps": 37735, "total_steps": 38150, "loss": 0.1543, "lr": 1.810797479300519e-08, "epoch": 9.89121887287025, "percentage": 98.91, "elapsed_time": "1:03:28", "remaining_time": "0:00:41", "throughput": 2656.3, "total_tokens": 10117784} {"current_steps": 37740, "total_steps": 38150, "loss": 0.1859, "lr": 1.7675353841495325e-08, "epoch": 9.892529488859765, "percentage": 98.93, "elapsed_time": "1:03:29", "remaining_time": "0:00:41", "throughput": 2656.33, "total_tokens": 10119112} {"current_steps": 37745, "total_steps": 38150, "loss": 0.2088, "lr": 1.7247961647368082e-08, "epoch": 9.893840104849279, "percentage": 98.94, "elapsed_time": "1:03:29", "remaining_time": "0:00:40", "throughput": 2656.36, "total_tokens": 10120424} {"current_steps": 37750, "total_steps": 38150, "loss": 0.102, "lr": 1.6825798300074137e-08, "epoch": 9.895150720838794, "percentage": 98.95, "elapsed_time": "1:03:30", "remaining_time": "0:00:40", "throughput": 2656.35, "total_tokens": 10121592} {"current_steps": 37755, "total_steps": 38150, "loss": 0.0713, "lr": 1.640886388797336e-08, "epoch": 9.89646133682831, "percentage": 98.96, "elapsed_time": "1:03:30", "remaining_time": "0:00:39", "throughput": 2656.32, "total_tokens": 10122600} {"current_steps": 37760, "total_steps": 38150, "loss": 0.1229, "lr": 1.5997158498329277e-08, "epoch": 9.897771952817825, "percentage": 98.98, "elapsed_time": "1:03:31", "remaining_time": "0:00:39", "throughput": 2656.34, "total_tokens": 10123880} {"current_steps": 37765, "total_steps": 38150, "loss": 0.0939, "lr": 1.559068221731186e-08, "epoch": 9.899082568807339, "percentage": 98.99, "elapsed_time": "1:03:31", "remaining_time": "0:00:38", "throughput": 2656.36, "total_tokens": 10125112} {"current_steps": 37770, "total_steps": 38150, "loss": 0.1205, "lr": 1.518943512999471e-08, "epoch": 9.900393184796854, "percentage": 99.0, "elapsed_time": "1:03:32", "remaining_time": "0:00:38", "throughput": 2656.35, "total_tokens": 10126280} {"current_steps": 37775, "total_steps": 38150, "loss": 0.1311, "lr": 1.4793417320357882e-08, "epoch": 9.90170380078637, "percentage": 99.02, "elapsed_time": "1:03:32", "remaining_time": "0:00:37", "throughput": 2656.45, "total_tokens": 10128024} {"current_steps": 37780, "total_steps": 38150, "loss": 0.1458, "lr": 1.4402628871285073e-08, "epoch": 9.903014416775886, "percentage": 99.03, "elapsed_time": "1:03:33", "remaining_time": "0:00:37", "throughput": 2656.52, "total_tokens": 10129528} {"current_steps": 37785, "total_steps": 38150, "loss": 0.1462, "lr": 1.401706986457474e-08, "epoch": 9.9043250327654, "percentage": 99.04, "elapsed_time": "1:03:33", "remaining_time": "0:00:36", "throughput": 2656.61, "total_tokens": 10131192} {"current_steps": 37790, "total_steps": 38150, "loss": 0.1805, "lr": 1.3636740380915113e-08, "epoch": 9.905635648754915, "percentage": 99.06, "elapsed_time": "1:03:34", "remaining_time": "0:00:36", "throughput": 2656.62, "total_tokens": 10132424} {"current_steps": 37795, "total_steps": 38150, "loss": 0.1156, "lr": 1.326164049991474e-08, "epoch": 9.90694626474443, "percentage": 99.07, "elapsed_time": "1:03:34", "remaining_time": "0:00:35", "throughput": 2656.67, "total_tokens": 10133816} {"current_steps": 37800, "total_steps": 38150, "loss": 0.2247, "lr": 1.2891770300080263e-08, "epoch": 9.908256880733944, "percentage": 99.08, "elapsed_time": "1:03:34", "remaining_time": "0:00:35", "throughput": 2656.72, "total_tokens": 10135176} {"current_steps": 37805, "total_steps": 38150, "loss": 0.154, "lr": 1.2527129858821985e-08, "epoch": 9.90956749672346, "percentage": 99.1, "elapsed_time": "1:03:35", "remaining_time": "0:00:34", "throughput": 2656.74, "total_tokens": 10136376} {"current_steps": 37810, "total_steps": 38150, "loss": 0.2345, "lr": 1.2167719252462183e-08, "epoch": 9.910878112712975, "percentage": 99.11, "elapsed_time": "1:03:35", "remaining_time": "0:00:34", "throughput": 2656.9, "total_tokens": 10138408} {"current_steps": 37815, "total_steps": 38150, "loss": 0.1353, "lr": 1.1813538556221249e-08, "epoch": 9.91218872870249, "percentage": 99.12, "elapsed_time": "1:03:36", "remaining_time": "0:00:33", "throughput": 2656.92, "total_tokens": 10139672} {"current_steps": 37820, "total_steps": 38150, "loss": 0.2638, "lr": 1.1464587844231544e-08, "epoch": 9.913499344692005, "percentage": 99.13, "elapsed_time": "1:03:36", "remaining_time": "0:00:33", "throughput": 2657.03, "total_tokens": 10141624} {"current_steps": 37825, "total_steps": 38150, "loss": 0.1724, "lr": 1.1120867189526318e-08, "epoch": 9.91480996068152, "percentage": 99.15, "elapsed_time": "1:03:37", "remaining_time": "0:00:32", "throughput": 2657.04, "total_tokens": 10142920} {"current_steps": 37830, "total_steps": 38150, "loss": 0.1568, "lr": 1.0782376664045246e-08, "epoch": 9.916120576671036, "percentage": 99.16, "elapsed_time": "1:03:37", "remaining_time": "0:00:32", "throughput": 2657.15, "total_tokens": 10144664} {"current_steps": 37835, "total_steps": 38150, "loss": 0.0871, "lr": 1.044911633863721e-08, "epoch": 9.917431192660551, "percentage": 99.17, "elapsed_time": "1:03:38", "remaining_time": "0:00:31", "throughput": 2657.19, "total_tokens": 10146008} {"current_steps": 37840, "total_steps": 38150, "loss": 0.1192, "lr": 1.0121086283049198e-08, "epoch": 9.918741808650065, "percentage": 99.19, "elapsed_time": "1:03:38", "remaining_time": "0:00:31", "throughput": 2657.27, "total_tokens": 10147608} {"current_steps": 37845, "total_steps": 38150, "loss": 0.2001, "lr": 9.798286565937399e-09, "epoch": 9.92005242463958, "percentage": 99.2, "elapsed_time": "1:03:39", "remaining_time": "0:00:30", "throughput": 2657.27, "total_tokens": 10148712} {"current_steps": 37850, "total_steps": 38150, "loss": 0.1447, "lr": 9.48071725486721e-09, "epoch": 9.921363040629096, "percentage": 99.21, "elapsed_time": "1:03:39", "remaining_time": "0:00:30", "throughput": 2657.32, "total_tokens": 10150040} {"current_steps": 37855, "total_steps": 38150, "loss": 0.1506, "lr": 9.168378416299362e-09, "epoch": 9.922673656618612, "percentage": 99.23, "elapsed_time": "1:03:40", "remaining_time": "0:00:29", "throughput": 2657.44, "total_tokens": 10152024} {"current_steps": 37860, "total_steps": 38150, "loss": 0.2274, "lr": 8.861270115612108e-09, "epoch": 9.923984272608125, "percentage": 99.24, "elapsed_time": "1:03:40", "remaining_time": "0:00:29", "throughput": 2657.51, "total_tokens": 10153480} {"current_steps": 37865, "total_steps": 38150, "loss": 0.1447, "lr": 8.559392417079038e-09, "epoch": 9.92529488859764, "percentage": 99.25, "elapsed_time": "1:03:41", "remaining_time": "0:00:28", "throughput": 2657.57, "total_tokens": 10154936} {"current_steps": 37870, "total_steps": 38150, "loss": 0.0527, "lr": 8.262745383880166e-09, "epoch": 9.926605504587156, "percentage": 99.27, "elapsed_time": "1:03:41", "remaining_time": "0:00:28", "throughput": 2657.54, "total_tokens": 10155960} {"current_steps": 37875, "total_steps": 38150, "loss": 0.2633, "lr": 7.971329078110268e-09, "epoch": 9.927916120576672, "percentage": 99.28, "elapsed_time": "1:03:41", "remaining_time": "0:00:27", "throughput": 2657.56, "total_tokens": 10157160} {"current_steps": 37880, "total_steps": 38150, "loss": 0.1345, "lr": 7.68514356075667e-09, "epoch": 9.929226736566186, "percentage": 99.29, "elapsed_time": "1:03:42", "remaining_time": "0:00:27", "throughput": 2657.57, "total_tokens": 10158472} {"current_steps": 37885, "total_steps": 38150, "loss": 0.2196, "lr": 7.4041888917186775e-09, "epoch": 9.930537352555701, "percentage": 99.31, "elapsed_time": "1:03:42", "remaining_time": "0:00:26", "throughput": 2657.61, "total_tokens": 10159832} {"current_steps": 37890, "total_steps": 38150, "loss": 0.0851, "lr": 7.1284651297992556e-09, "epoch": 9.931847968545217, "percentage": 99.32, "elapsed_time": "1:03:43", "remaining_time": "0:00:26", "throughput": 2657.64, "total_tokens": 10161096} {"current_steps": 37895, "total_steps": 38150, "loss": 0.1187, "lr": 6.8579723327105715e-09, "epoch": 9.93315858453473, "percentage": 99.33, "elapsed_time": "1:03:43", "remaining_time": "0:00:25", "throughput": 2657.69, "total_tokens": 10162616} {"current_steps": 37900, "total_steps": 38150, "loss": 0.1574, "lr": 6.5927105570601224e-09, "epoch": 9.934469200524246, "percentage": 99.34, "elapsed_time": "1:03:44", "remaining_time": "0:00:25", "throughput": 2657.71, "total_tokens": 10163912} {"current_steps": 37905, "total_steps": 38150, "loss": 0.1258, "lr": 6.3326798583729364e-09, "epoch": 9.935779816513762, "percentage": 99.36, "elapsed_time": "1:03:44", "remaining_time": "0:00:24", "throughput": 2657.74, "total_tokens": 10165224} {"current_steps": 37910, "total_steps": 38150, "loss": 0.1768, "lr": 6.077880291069371e-09, "epoch": 9.937090432503277, "percentage": 99.37, "elapsed_time": "1:03:45", "remaining_time": "0:00:24", "throughput": 2657.82, "total_tokens": 10166904} {"current_steps": 37915, "total_steps": 38150, "loss": 0.1451, "lr": 5.8283119084789895e-09, "epoch": 9.938401048492791, "percentage": 99.38, "elapsed_time": "1:03:45", "remaining_time": "0:00:23", "throughput": 2657.87, "total_tokens": 10168280} {"current_steps": 37920, "total_steps": 38150, "loss": 0.1806, "lr": 5.583974762835009e-09, "epoch": 9.939711664482306, "percentage": 99.4, "elapsed_time": "1:03:46", "remaining_time": "0:00:23", "throughput": 2657.92, "total_tokens": 10169624} {"current_steps": 37925, "total_steps": 38150, "loss": 0.1136, "lr": 5.344868905279854e-09, "epoch": 9.941022280471822, "percentage": 99.41, "elapsed_time": "1:03:46", "remaining_time": "0:00:22", "throughput": 2657.92, "total_tokens": 10170840} {"current_steps": 37930, "total_steps": 38150, "loss": 0.1074, "lr": 5.110994385856826e-09, "epoch": 9.942332896461338, "percentage": 99.42, "elapsed_time": "1:03:47", "remaining_time": "0:00:22", "throughput": 2657.92, "total_tokens": 10172008} {"current_steps": 37935, "total_steps": 38150, "loss": 0.1091, "lr": 4.8823512535128845e-09, "epoch": 9.943643512450851, "percentage": 99.44, "elapsed_time": "1:03:47", "remaining_time": "0:00:21", "throughput": 2658.14, "total_tokens": 10174936} {"current_steps": 37940, "total_steps": 38150, "loss": 0.2523, "lr": 4.658939556104191e-09, "epoch": 9.944954128440367, "percentage": 99.45, "elapsed_time": "1:03:48", "remaining_time": "0:00:21", "throughput": 2658.17, "total_tokens": 10176232} {"current_steps": 37945, "total_steps": 38150, "loss": 0.194, "lr": 4.440759340393341e-09, "epoch": 9.946264744429882, "percentage": 99.46, "elapsed_time": "1:03:48", "remaining_time": "0:00:20", "throughput": 2658.19, "total_tokens": 10177416} {"current_steps": 37950, "total_steps": 38150, "loss": 0.1112, "lr": 4.227810652041031e-09, "epoch": 9.947575360419398, "percentage": 99.48, "elapsed_time": "1:03:49", "remaining_time": "0:00:20", "throughput": 2658.24, "total_tokens": 10178792} {"current_steps": 37955, "total_steps": 38150, "loss": 0.0539, "lr": 4.0200935356171645e-09, "epoch": 9.948885976408912, "percentage": 99.49, "elapsed_time": "1:03:49", "remaining_time": "0:00:19", "throughput": 2658.24, "total_tokens": 10179912} {"current_steps": 37960, "total_steps": 38150, "loss": 0.0891, "lr": 3.817608034600851e-09, "epoch": 9.950196592398427, "percentage": 99.5, "elapsed_time": "1:03:50", "remaining_time": "0:00:19", "throughput": 2658.26, "total_tokens": 10181160} {"current_steps": 37965, "total_steps": 38150, "loss": 0.2526, "lr": 3.620354191366526e-09, "epoch": 9.951507208387943, "percentage": 99.52, "elapsed_time": "1:03:50", "remaining_time": "0:00:18", "throughput": 2658.27, "total_tokens": 10182376} {"current_steps": 37970, "total_steps": 38150, "loss": 0.2101, "lr": 3.4283320472033864e-09, "epoch": 9.952817824377458, "percentage": 99.53, "elapsed_time": "1:03:50", "remaining_time": "0:00:18", "throughput": 2658.33, "total_tokens": 10183816} {"current_steps": 37975, "total_steps": 38150, "loss": 0.2558, "lr": 3.241541642298729e-09, "epoch": 9.954128440366972, "percentage": 99.54, "elapsed_time": "1:03:51", "remaining_time": "0:00:17", "throughput": 2658.34, "total_tokens": 10185016} {"current_steps": 37980, "total_steps": 38150, "loss": 0.1513, "lr": 3.059983015749057e-09, "epoch": 9.955439056356488, "percentage": 99.55, "elapsed_time": "1:03:51", "remaining_time": "0:00:17", "throughput": 2658.35, "total_tokens": 10186248} {"current_steps": 37985, "total_steps": 38150, "loss": 0.1296, "lr": 2.88365620555453e-09, "epoch": 9.956749672346003, "percentage": 99.57, "elapsed_time": "1:03:52", "remaining_time": "0:00:16", "throughput": 2658.43, "total_tokens": 10187944} {"current_steps": 37990, "total_steps": 38150, "loss": 0.1516, "lr": 2.712561248618961e-09, "epoch": 9.958060288335517, "percentage": 99.58, "elapsed_time": "1:03:52", "remaining_time": "0:00:16", "throughput": 2658.42, "total_tokens": 10189064} {"current_steps": 37995, "total_steps": 38150, "loss": 0.1585, "lr": 2.546698180749818e-09, "epoch": 9.959370904325032, "percentage": 99.59, "elapsed_time": "1:03:53", "remaining_time": "0:00:15", "throughput": 2658.5, "total_tokens": 10190616} {"current_steps": 38000, "total_steps": 38150, "loss": 0.1679, "lr": 2.3860670366665505e-09, "epoch": 9.960681520314548, "percentage": 99.61, "elapsed_time": "1:03:53", "remaining_time": "0:00:15", "throughput": 2658.58, "total_tokens": 10192200} {"current_steps": 38005, "total_steps": 38150, "loss": 0.1765, "lr": 2.2306678499867116e-09, "epoch": 9.961992136304064, "percentage": 99.62, "elapsed_time": "1:03:54", "remaining_time": "0:00:14", "throughput": 2658.69, "total_tokens": 10193928} {"current_steps": 38010, "total_steps": 38150, "loss": 0.151, "lr": 2.080500653234285e-09, "epoch": 9.963302752293577, "percentage": 99.63, "elapsed_time": "1:03:54", "remaining_time": "0:00:14", "throughput": 2658.73, "total_tokens": 10195240} {"current_steps": 38015, "total_steps": 38150, "loss": 0.164, "lr": 1.935565477839685e-09, "epoch": 9.964613368283093, "percentage": 99.65, "elapsed_time": "1:03:55", "remaining_time": "0:00:13", "throughput": 2658.85, "total_tokens": 10197112} {"current_steps": 38020, "total_steps": 38150, "loss": 0.1545, "lr": 1.7958623541397546e-09, "epoch": 9.965923984272608, "percentage": 99.66, "elapsed_time": "1:03:55", "remaining_time": "0:00:13", "throughput": 2658.89, "total_tokens": 10198408} {"current_steps": 38025, "total_steps": 38150, "loss": 0.1132, "lr": 1.6613913113694424e-09, "epoch": 9.967234600262124, "percentage": 99.67, "elapsed_time": "1:03:56", "remaining_time": "0:00:12", "throughput": 2658.93, "total_tokens": 10199784} {"current_steps": 38030, "total_steps": 38150, "loss": 0.0771, "lr": 1.532152377678453e-09, "epoch": 9.968545216251638, "percentage": 99.69, "elapsed_time": "1:03:56", "remaining_time": "0:00:12", "throughput": 2658.91, "total_tokens": 10200824} {"current_steps": 38035, "total_steps": 38150, "loss": 0.1052, "lr": 1.4081455801145948e-09, "epoch": 9.969855832241153, "percentage": 99.7, "elapsed_time": "1:03:56", "remaining_time": "0:00:11", "throughput": 2658.9, "total_tokens": 10201912} {"current_steps": 38040, "total_steps": 38150, "loss": 0.0675, "lr": 1.289370944629331e-09, "epoch": 9.971166448230669, "percentage": 99.71, "elapsed_time": "1:03:57", "remaining_time": "0:00:11", "throughput": 2658.86, "total_tokens": 10202856} {"current_steps": 38045, "total_steps": 38150, "loss": 0.1379, "lr": 1.1758284960861066e-09, "epoch": 9.972477064220184, "percentage": 99.72, "elapsed_time": "1:03:57", "remaining_time": "0:00:10", "throughput": 2658.84, "total_tokens": 10203896} {"current_steps": 38050, "total_steps": 38150, "loss": 0.1102, "lr": 1.0675182582464693e-09, "epoch": 9.973787680209698, "percentage": 99.74, "elapsed_time": "1:03:58", "remaining_time": "0:00:10", "throughput": 2658.89, "total_tokens": 10205272} {"current_steps": 38055, "total_steps": 38150, "loss": 0.2056, "lr": 9.644402537811736e-10, "epoch": 9.975098296199214, "percentage": 99.75, "elapsed_time": "1:03:58", "remaining_time": "0:00:09", "throughput": 2658.99, "total_tokens": 10206936} {"current_steps": 38060, "total_steps": 38150, "loss": 0.0884, "lr": 8.665945042618529e-10, "epoch": 9.97640891218873, "percentage": 99.76, "elapsed_time": "1:03:59", "remaining_time": "0:00:09", "throughput": 2658.96, "total_tokens": 10207912} {"current_steps": 38065, "total_steps": 38150, "loss": 0.1877, "lr": 7.739810301693462e-10, "epoch": 9.977719528178245, "percentage": 99.78, "elapsed_time": "1:03:59", "remaining_time": "0:00:08", "throughput": 2658.92, "total_tokens": 10208904} {"current_steps": 38070, "total_steps": 38150, "loss": 0.2342, "lr": 6.865998508881477e-10, "epoch": 9.979030144167758, "percentage": 99.79, "elapsed_time": "1:03:59", "remaining_time": "0:00:08", "throughput": 2658.9, "total_tokens": 10209928} {"current_steps": 38075, "total_steps": 38150, "loss": 0.0629, "lr": 6.044509847064062e-10, "epoch": 9.980340760157274, "percentage": 99.8, "elapsed_time": "1:04:00", "remaining_time": "0:00:07", "throughput": 2658.96, "total_tokens": 10211368} {"current_steps": 38080, "total_steps": 38150, "loss": 0.1347, "lr": 5.275344488187006e-10, "epoch": 9.98165137614679, "percentage": 99.82, "elapsed_time": "1:04:00", "remaining_time": "0:00:07", "throughput": 2658.97, "total_tokens": 10212600} {"current_steps": 38085, "total_steps": 38150, "loss": 0.1151, "lr": 4.5585025932048943e-10, "epoch": 9.982961992136303, "percentage": 99.83, "elapsed_time": "1:04:01", "remaining_time": "0:00:06", "throughput": 2658.95, "total_tokens": 10213656} {"current_steps": 38090, "total_steps": 38150, "loss": 0.2345, "lr": 3.893984312164367e-10, "epoch": 9.984272608125819, "percentage": 99.84, "elapsed_time": "1:04:01", "remaining_time": "0:00:06", "throughput": 2659.04, "total_tokens": 10215272} {"current_steps": 38095, "total_steps": 38150, "loss": 0.1064, "lr": 3.28178978417637e-10, "epoch": 9.985583224115334, "percentage": 99.86, "elapsed_time": "1:04:02", "remaining_time": "0:00:05", "throughput": 2659.1, "total_tokens": 10216776} {"current_steps": 38100, "total_steps": 38150, "loss": 0.0903, "lr": 2.7219191373328846e-10, "epoch": 9.98689384010485, "percentage": 99.87, "elapsed_time": "1:04:02", "remaining_time": "0:00:05", "throughput": 2659.1, "total_tokens": 10217960} {"current_steps": 38105, "total_steps": 38150, "loss": 0.0594, "lr": 2.2143724888179506e-10, "epoch": 9.988204456094364, "percentage": 99.88, "elapsed_time": "1:04:03", "remaining_time": "0:00:04", "throughput": 2659.12, "total_tokens": 10219192} {"current_steps": 38110, "total_steps": 38150, "loss": 0.2746, "lr": 1.759149944879912e-10, "epoch": 9.98951507208388, "percentage": 99.9, "elapsed_time": "1:04:03", "remaining_time": "0:00:04", "throughput": 2659.22, "total_tokens": 10220904} {"current_steps": 38115, "total_steps": 38150, "loss": 0.2931, "lr": 1.3562516008036597e-10, "epoch": 9.990825688073395, "percentage": 99.91, "elapsed_time": "1:04:04", "remaining_time": "0:00:03", "throughput": 2659.25, "total_tokens": 10222152} {"current_steps": 38120, "total_steps": 38150, "loss": 0.1849, "lr": 1.0056775408828767e-10, "epoch": 9.99213630406291, "percentage": 99.92, "elapsed_time": "1:04:04", "remaining_time": "0:00:03", "throughput": 2659.31, "total_tokens": 10223672} {"current_steps": 38125, "total_steps": 38150, "loss": 0.2286, "lr": 7.07427838503305e-11, "epoch": 9.993446920052424, "percentage": 99.93, "elapsed_time": "1:04:05", "remaining_time": "0:00:02", "throughput": 2659.47, "total_tokens": 10225736} {"current_steps": 38130, "total_steps": 38150, "loss": 0.1213, "lr": 4.6150255611498996e-11, "epoch": 9.99475753604194, "percentage": 99.95, "elapsed_time": "1:04:05", "remaining_time": "0:00:02", "throughput": 2659.56, "total_tokens": 10227320} {"current_steps": 38135, "total_steps": 38150, "loss": 0.1191, "lr": 2.679017451490129e-11, "epoch": 9.996068152031455, "percentage": 99.96, "elapsed_time": "1:04:05", "remaining_time": "0:00:01", "throughput": 2659.57, "total_tokens": 10228504} {"current_steps": 38140, "total_steps": 38150, "loss": 0.2585, "lr": 1.2662544615626993e-11, "epoch": 9.997378768020969, "percentage": 99.97, "elapsed_time": "1:04:06", "remaining_time": "0:00:01", "throughput": 2659.57, "total_tokens": 10229624} {"current_steps": 38145, "total_steps": 38150, "loss": 0.2906, "lr": 3.767368869644905e-12, "epoch": 9.998689384010484, "percentage": 99.99, "elapsed_time": "1:04:06", "remaining_time": "0:00:00", "throughput": 2659.62, "total_tokens": 10231048} {"current_steps": 38150, "total_steps": 38150, "loss": 0.2814, "lr": 1.0464913657859399e-13, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "1:04:07", "remaining_time": "0:00:00", "throughput": 2659.55, "total_tokens": 10232192} {"current_steps": 38150, "total_steps": 38150, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "1:04:09", "remaining_time": "0:00:00", "throughput": 2658.36, "total_tokens": 10232192}