train_record_1745940979 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 3400
b38ac1e verified
{"current_steps": 5, "total_steps": 40000, "loss": 15.2834, "lr": 4.999999876629946e-05, "epoch": 0.0012803277639075604, "percentage": 0.01, "elapsed_time": "0:00:09", "remaining_time": "22:12:01", "throughput": 6117.21, "total_tokens": 61120}
{"current_steps": 10, "total_steps": 40000, "loss": 15.0379, "lr": 4.999999375439123e-05, "epoch": 0.002560655527815121, "percentage": 0.03, "elapsed_time": "0:00:17", "remaining_time": "19:47:14", "throughput": 6756.39, "total_tokens": 120352}
{"current_steps": 15, "total_steps": 40000, "loss": 14.9528, "lr": 4.9999984887169785e-05, "epoch": 0.003840983291722681, "percentage": 0.04, "elapsed_time": "0:00:25", "remaining_time": "18:51:42", "throughput": 7093.99, "total_tokens": 180704}
{"current_steps": 20, "total_steps": 40000, "loss": 15.7283, "lr": 4.9999972164636506e-05, "epoch": 0.005121311055630242, "percentage": 0.05, "elapsed_time": "0:00:33", "remaining_time": "18:24:47", "throughput": 7163.23, "total_tokens": 237536}
{"current_steps": 25, "total_steps": 40000, "loss": 15.305, "lr": 4.999995558679334e-05, "epoch": 0.006401638819537802, "percentage": 0.06, "elapsed_time": "0:00:40", "remaining_time": "18:06:03", "throughput": 7312.77, "total_tokens": 298016}
{"current_steps": 30, "total_steps": 40000, "loss": 14.4976, "lr": 4.999993515364287e-05, "epoch": 0.007681966583445362, "percentage": 0.07, "elapsed_time": "0:00:48", "remaining_time": "17:56:48", "throughput": 7349.92, "total_tokens": 356416}
{"current_steps": 35, "total_steps": 40000, "loss": 15.2672, "lr": 4.999991086518822e-05, "epoch": 0.008962294347352922, "percentage": 0.09, "elapsed_time": "0:00:56", "remaining_time": "17:49:36", "throughput": 7367.52, "total_tokens": 414080}
{"current_steps": 40, "total_steps": 40000, "loss": 15.0168, "lr": 4.999988272143315e-05, "epoch": 0.010242622111260483, "percentage": 0.1, "elapsed_time": "0:01:03", "remaining_time": "17:44:07", "throughput": 7363.15, "total_tokens": 470592}
{"current_steps": 45, "total_steps": 40000, "loss": 15.0017, "lr": 4.999985072238199e-05, "epoch": 0.011522949875168043, "percentage": 0.11, "elapsed_time": "0:01:11", "remaining_time": "17:39:17", "throughput": 7389.0, "total_tokens": 528928}
{"current_steps": 50, "total_steps": 40000, "loss": 13.5516, "lr": 4.999981486803969e-05, "epoch": 0.012803277639075603, "percentage": 0.12, "elapsed_time": "0:01:19", "remaining_time": "17:35:46", "throughput": 7409.66, "total_tokens": 587456}
{"current_steps": 55, "total_steps": 40000, "loss": 12.7551, "lr": 4.999977515841176e-05, "epoch": 0.014083605402983163, "percentage": 0.14, "elapsed_time": "0:01:26", "remaining_time": "17:32:37", "throughput": 7415.88, "total_tokens": 644896}
{"current_steps": 60, "total_steps": 40000, "loss": 11.6318, "lr": 4.9999731593504344e-05, "epoch": 0.015363933166890723, "percentage": 0.15, "elapsed_time": "0:01:34", "remaining_time": "17:30:15", "throughput": 7442.19, "total_tokens": 704512}
{"current_steps": 65, "total_steps": 40000, "loss": 10.2242, "lr": 4.999968417332415e-05, "epoch": 0.016644260930798283, "percentage": 0.16, "elapsed_time": "0:01:42", "remaining_time": "17:28:15", "throughput": 7462.75, "total_tokens": 763968}
{"current_steps": 70, "total_steps": 40000, "loss": 9.6774, "lr": 4.999963289787848e-05, "epoch": 0.017924588694705843, "percentage": 0.18, "elapsed_time": "0:01:50", "remaining_time": "17:26:11", "throughput": 7478.44, "total_tokens": 822944}
{"current_steps": 75, "total_steps": 40000, "loss": 8.3831, "lr": 4.999957776717526e-05, "epoch": 0.019204916458613407, "percentage": 0.19, "elapsed_time": "0:01:57", "remaining_time": "17:24:01", "throughput": 7493.87, "total_tokens": 881824}
{"current_steps": 80, "total_steps": 40000, "loss": 7.7808, "lr": 4.9999518781222984e-05, "epoch": 0.020485244222520967, "percentage": 0.2, "elapsed_time": "0:02:05", "remaining_time": "17:22:40", "throughput": 7498.42, "total_tokens": 940096}
{"current_steps": 85, "total_steps": 40000, "loss": 7.5708, "lr": 4.9999455940030746e-05, "epoch": 0.021765571986428527, "percentage": 0.21, "elapsed_time": "0:02:12", "remaining_time": "17:20:51", "throughput": 7518.97, "total_tokens": 999968}
{"current_steps": 90, "total_steps": 40000, "loss": 7.0188, "lr": 4.999938924360824e-05, "epoch": 0.023045899750336087, "percentage": 0.22, "elapsed_time": "0:02:20", "remaining_time": "17:20:02", "throughput": 7520.04, "total_tokens": 1058240}
{"current_steps": 95, "total_steps": 40000, "loss": 6.9531, "lr": 4.999931869196575e-05, "epoch": 0.024326227514243647, "percentage": 0.24, "elapsed_time": "0:02:28", "remaining_time": "17:18:31", "throughput": 7525.28, "total_tokens": 1116320}
{"current_steps": 100, "total_steps": 40000, "loss": 7.2064, "lr": 4.999924428511416e-05, "epoch": 0.025606555278151207, "percentage": 0.25, "elapsed_time": "0:02:36", "remaining_time": "17:17:49", "throughput": 7522.51, "total_tokens": 1173984}
{"current_steps": 105, "total_steps": 40000, "loss": 6.5087, "lr": 4.999916602306494e-05, "epoch": 0.026886883042058767, "percentage": 0.26, "elapsed_time": "0:02:43", "remaining_time": "17:16:31", "throughput": 7534.59, "total_tokens": 1233280}
{"current_steps": 110, "total_steps": 40000, "loss": 7.1347, "lr": 4.999908390583016e-05, "epoch": 0.028167210805966326, "percentage": 0.27, "elapsed_time": "0:02:51", "remaining_time": "17:15:05", "throughput": 7533.94, "total_tokens": 1290272}
{"current_steps": 115, "total_steps": 40000, "loss": 6.2922, "lr": 4.999899793342247e-05, "epoch": 0.029447538569873886, "percentage": 0.29, "elapsed_time": "0:02:58", "remaining_time": "17:14:04", "throughput": 7531.49, "total_tokens": 1347328}
{"current_steps": 120, "total_steps": 40000, "loss": 6.5867, "lr": 4.999890810585516e-05, "epoch": 0.030727866333781446, "percentage": 0.3, "elapsed_time": "0:03:06", "remaining_time": "17:13:28", "throughput": 7542.24, "total_tokens": 1407264}
{"current_steps": 125, "total_steps": 40000, "loss": 6.1606, "lr": 4.999881442314206e-05, "epoch": 0.032008194097689006, "percentage": 0.31, "elapsed_time": "0:03:14", "remaining_time": "17:12:24", "throughput": 7552.96, "total_tokens": 1466656}
{"current_steps": 130, "total_steps": 40000, "loss": 6.1292, "lr": 4.9998716885297617e-05, "epoch": 0.033288521861596566, "percentage": 0.33, "elapsed_time": "0:03:21", "remaining_time": "17:11:46", "throughput": 7554.97, "total_tokens": 1524992}
{"current_steps": 135, "total_steps": 40000, "loss": 5.8556, "lr": 4.999861549233688e-05, "epoch": 0.034568849625504126, "percentage": 0.34, "elapsed_time": "0:03:29", "remaining_time": "17:11:11", "throughput": 7553.16, "total_tokens": 1582560}
{"current_steps": 140, "total_steps": 40000, "loss": 5.493, "lr": 4.999851024427548e-05, "epoch": 0.035849177389411686, "percentage": 0.35, "elapsed_time": "0:03:37", "remaining_time": "17:10:23", "throughput": 7557.22, "total_tokens": 1640992}
{"current_steps": 145, "total_steps": 40000, "loss": 5.4286, "lr": 4.999840114112965e-05, "epoch": 0.037129505153319246, "percentage": 0.36, "elapsed_time": "0:03:44", "remaining_time": "17:09:48", "throughput": 7554.69, "total_tokens": 1698272}
{"current_steps": 150, "total_steps": 40000, "loss": 4.8266, "lr": 4.999828818291621e-05, "epoch": 0.03840983291722681, "percentage": 0.38, "elapsed_time": "0:03:52", "remaining_time": "17:09:00", "throughput": 7554.9, "total_tokens": 1755744}
{"current_steps": 155, "total_steps": 40000, "loss": 5.0264, "lr": 4.999817136965259e-05, "epoch": 0.03969016068113437, "percentage": 0.39, "elapsed_time": "0:04:00", "remaining_time": "17:08:21", "throughput": 7556.78, "total_tokens": 1813792}
{"current_steps": 160, "total_steps": 40000, "loss": 4.1507, "lr": 4.9998050701356794e-05, "epoch": 0.04097048844504193, "percentage": 0.4, "elapsed_time": "0:04:07", "remaining_time": "17:07:50", "throughput": 7555.37, "total_tokens": 1871328}
{"current_steps": 165, "total_steps": 40000, "loss": 4.2897, "lr": 4.999792617804744e-05, "epoch": 0.04225081620894949, "percentage": 0.41, "elapsed_time": "0:04:15", "remaining_time": "17:07:18", "throughput": 7560.17, "total_tokens": 1930208}
{"current_steps": 170, "total_steps": 40000, "loss": 3.9536, "lr": 4.9997797799743724e-05, "epoch": 0.04353114397285705, "percentage": 0.43, "elapsed_time": "0:04:22", "remaining_time": "17:06:48", "throughput": 7561.78, "total_tokens": 1988384}
{"current_steps": 175, "total_steps": 40000, "loss": 3.8245, "lr": 4.999766556646545e-05, "epoch": 0.04481147173676461, "percentage": 0.44, "elapsed_time": "0:04:30", "remaining_time": "17:06:36", "throughput": 7561.49, "total_tokens": 2046656}
{"current_steps": 180, "total_steps": 40000, "loss": 3.4797, "lr": 4.9997529478232996e-05, "epoch": 0.04609179950067217, "percentage": 0.45, "elapsed_time": "0:04:38", "remaining_time": "17:05:59", "throughput": 7556.25, "total_tokens": 2102688}
{"current_steps": 185, "total_steps": 40000, "loss": 3.2203, "lr": 4.9997389535067365e-05, "epoch": 0.04737212726457973, "percentage": 0.46, "elapsed_time": "0:04:45", "remaining_time": "17:05:41", "throughput": 7558.53, "total_tokens": 2161376}
{"current_steps": 190, "total_steps": 40000, "loss": 2.8925, "lr": 4.999724573699012e-05, "epoch": 0.04865245502848729, "percentage": 0.47, "elapsed_time": "0:04:53", "remaining_time": "17:05:13", "throughput": 7554.23, "total_tokens": 2217792}
{"current_steps": 195, "total_steps": 40000, "loss": 2.8108, "lr": 4.9997098084023457e-05, "epoch": 0.04993278279239485, "percentage": 0.49, "elapsed_time": "0:05:01", "remaining_time": "17:04:49", "throughput": 7554.96, "total_tokens": 2275776}
{"current_steps": 200, "total_steps": 40000, "loss": 2.6098, "lr": 4.999694657619013e-05, "epoch": 0.05121311055630241, "percentage": 0.5, "elapsed_time": "0:05:08", "remaining_time": "17:04:23", "throughput": 7560.46, "total_tokens": 2335136}
{"current_steps": 200, "total_steps": 40000, "eval_loss": 2.6221702098846436, "epoch": 0.05121311055630241, "percentage": 0.5, "elapsed_time": "0:08:41", "remaining_time": "1 day, 4:48:09", "throughput": 4481.58, "total_tokens": 2335136}
{"current_steps": 205, "total_steps": 40000, "loss": 2.7737, "lr": 4.999679121351352e-05, "epoch": 0.05249343832020997, "percentage": 0.51, "elapsed_time": "0:08:51", "remaining_time": "1 day, 4:38:22", "throughput": 4507.16, "total_tokens": 2393856}
{"current_steps": 210, "total_steps": 40000, "loss": 2.6059, "lr": 4.9996631996017565e-05, "epoch": 0.05377376608411753, "percentage": 0.53, "elapsed_time": "0:08:58", "remaining_time": "1 day, 4:21:20", "throughput": 4552.15, "total_tokens": 2452480}
{"current_steps": 215, "total_steps": 40000, "loss": 2.508, "lr": 4.9996468923726835e-05, "epoch": 0.05505409384802509, "percentage": 0.54, "elapsed_time": "0:09:06", "remaining_time": "1 day, 4:05:07", "throughput": 4601.94, "total_tokens": 2514464}
{"current_steps": 220, "total_steps": 40000, "loss": 2.3129, "lr": 4.999630199666647e-05, "epoch": 0.05633442161193265, "percentage": 0.55, "elapsed_time": "0:09:14", "remaining_time": "1 day, 3:49:42", "throughput": 4645.04, "total_tokens": 2573600}
{"current_steps": 225, "total_steps": 40000, "loss": 2.1023, "lr": 4.999613121486222e-05, "epoch": 0.05761474937584021, "percentage": 0.56, "elapsed_time": "0:09:21", "remaining_time": "1 day, 3:34:54", "throughput": 4684.88, "total_tokens": 2631456}
{"current_steps": 230, "total_steps": 40000, "loss": 2.1422, "lr": 4.999595657834041e-05, "epoch": 0.05889507713974777, "percentage": 0.57, "elapsed_time": "0:09:29", "remaining_time": "1 day, 3:20:46", "throughput": 4723.76, "total_tokens": 2689440}
{"current_steps": 235, "total_steps": 40000, "loss": 1.9473, "lr": 4.999577808712798e-05, "epoch": 0.06017540490365533, "percentage": 0.59, "elapsed_time": "0:09:37", "remaining_time": "1 day, 3:07:21", "throughput": 4762.08, "total_tokens": 2747872}
{"current_steps": 240, "total_steps": 40000, "loss": 2.049, "lr": 4.999559574125244e-05, "epoch": 0.06145573266756289, "percentage": 0.6, "elapsed_time": "0:09:44", "remaining_time": "1 day, 2:54:29", "throughput": 4798.01, "total_tokens": 2805504}
{"current_steps": 245, "total_steps": 40000, "loss": 1.9734, "lr": 4.9995409540741934e-05, "epoch": 0.06273606043147045, "percentage": 0.61, "elapsed_time": "0:09:52", "remaining_time": "1 day, 2:41:56", "throughput": 4835.9, "total_tokens": 2864512}
{"current_steps": 250, "total_steps": 40000, "loss": 1.9758, "lr": 4.999521948562516e-05, "epoch": 0.06401638819537801, "percentage": 0.62, "elapsed_time": "0:10:00", "remaining_time": "1 day, 2:30:00", "throughput": 4875.55, "total_tokens": 2925344}
{"current_steps": 255, "total_steps": 40000, "loss": 1.7787, "lr": 4.999502557593143e-05, "epoch": 0.06529671595928557, "percentage": 0.64, "elapsed_time": "0:10:07", "remaining_time": "1 day, 2:18:31", "throughput": 4907.99, "total_tokens": 2982400}
{"current_steps": 260, "total_steps": 40000, "loss": 1.7864, "lr": 4.999482781169066e-05, "epoch": 0.06657704372319313, "percentage": 0.65, "elapsed_time": "0:10:15", "remaining_time": "1 day, 2:07:32", "throughput": 4943.04, "total_tokens": 3041664}
{"current_steps": 265, "total_steps": 40000, "loss": 1.6344, "lr": 4.9994626192933324e-05, "epoch": 0.06785737148710069, "percentage": 0.66, "elapsed_time": "0:10:23", "remaining_time": "1 day, 1:56:56", "throughput": 4976.85, "total_tokens": 3100640}
{"current_steps": 270, "total_steps": 40000, "loss": 1.6159, "lr": 4.999442071969054e-05, "epoch": 0.06913769925100825, "percentage": 0.68, "elapsed_time": "0:10:30", "remaining_time": "1 day, 1:46:34", "throughput": 5008.58, "total_tokens": 3158496}
{"current_steps": 275, "total_steps": 40000, "loss": 1.6112, "lr": 4.999421139199397e-05, "epoch": 0.07041802701491581, "percentage": 0.69, "elapsed_time": "0:10:38", "remaining_time": "1 day, 1:36:44", "throughput": 5038.19, "total_tokens": 3215840}
{"current_steps": 280, "total_steps": 40000, "loss": 1.6656, "lr": 4.999399820987592e-05, "epoch": 0.07169835477882337, "percentage": 0.7, "elapsed_time": "0:10:45", "remaining_time": "1 day, 1:27:12", "throughput": 5069.4, "total_tokens": 3274592}
{"current_steps": 285, "total_steps": 40000, "loss": 1.5322, "lr": 4.999378117336924e-05, "epoch": 0.07297868254273093, "percentage": 0.71, "elapsed_time": "0:10:53", "remaining_time": "1 day, 1:17:54", "throughput": 5099.29, "total_tokens": 3332704}
{"current_steps": 290, "total_steps": 40000, "loss": 1.5836, "lr": 4.9993560282507415e-05, "epoch": 0.07425901030663849, "percentage": 0.73, "elapsed_time": "0:11:01", "remaining_time": "1 day, 1:09:12", "throughput": 5131.06, "total_tokens": 3393184}
{"current_steps": 295, "total_steps": 40000, "loss": 1.4367, "lr": 4.9993335537324495e-05, "epoch": 0.07553933807054607, "percentage": 0.74, "elapsed_time": "0:11:08", "remaining_time": "1 day, 1:00:36", "throughput": 5158.35, "total_tokens": 3450688}
{"current_steps": 300, "total_steps": 40000, "loss": 1.4147, "lr": 4.999310693785516e-05, "epoch": 0.07681966583445363, "percentage": 0.75, "elapsed_time": "0:11:16", "remaining_time": "1 day, 0:52:32", "throughput": 5189.3, "total_tokens": 3511712}
{"current_steps": 305, "total_steps": 40000, "loss": 1.3699, "lr": 4.9992874484134653e-05, "epoch": 0.07809999359836119, "percentage": 0.76, "elapsed_time": "0:11:24", "remaining_time": "1 day, 0:44:24", "throughput": 5216.55, "total_tokens": 3569856}
{"current_steps": 310, "total_steps": 40000, "loss": 1.5005, "lr": 4.999263817619882e-05, "epoch": 0.07938032136226875, "percentage": 0.78, "elapsed_time": "0:11:32", "remaining_time": "1 day, 0:36:43", "throughput": 5242.36, "total_tokens": 3627936}
{"current_steps": 315, "total_steps": 40000, "loss": 1.4846, "lr": 4.9992398014084105e-05, "epoch": 0.0806606491261763, "percentage": 0.79, "elapsed_time": "0:11:39", "remaining_time": "1 day, 0:29:05", "throughput": 5268.58, "total_tokens": 3686176}
{"current_steps": 320, "total_steps": 40000, "loss": 1.4344, "lr": 4.999215399782754e-05, "epoch": 0.08194097689008387, "percentage": 0.8, "elapsed_time": "0:11:47", "remaining_time": "1 day, 0:21:45", "throughput": 5294.3, "total_tokens": 3744672}
{"current_steps": 325, "total_steps": 40000, "loss": 1.4975, "lr": 4.999190612746675e-05, "epoch": 0.08322130465399143, "percentage": 0.81, "elapsed_time": "0:11:54", "remaining_time": "1 day, 0:14:38", "throughput": 5321.56, "total_tokens": 3804608}
{"current_steps": 330, "total_steps": 40000, "loss": 1.3576, "lr": 4.999165440303998e-05, "epoch": 0.08450163241789899, "percentage": 0.83, "elapsed_time": "0:12:02", "remaining_time": "1 day, 0:07:50", "throughput": 5348.7, "total_tokens": 3865184}
{"current_steps": 335, "total_steps": 40000, "loss": 1.373, "lr": 4.999139882458603e-05, "epoch": 0.08578196018180655, "percentage": 0.84, "elapsed_time": "0:12:10", "remaining_time": "1 day, 0:01:04", "throughput": 5373.26, "total_tokens": 3923840}
{"current_steps": 340, "total_steps": 40000, "loss": 1.2575, "lr": 4.9991139392144314e-05, "epoch": 0.0870622879457141, "percentage": 0.85, "elapsed_time": "0:12:17", "remaining_time": "23:54:32", "throughput": 5396.91, "total_tokens": 3982336}
{"current_steps": 345, "total_steps": 40000, "loss": 1.1972, "lr": 4.999087610575485e-05, "epoch": 0.08834261570962167, "percentage": 0.86, "elapsed_time": "0:12:25", "remaining_time": "23:48:06", "throughput": 5420.54, "total_tokens": 4040864}
{"current_steps": 350, "total_steps": 40000, "loss": 1.3621, "lr": 4.999060896545824e-05, "epoch": 0.08962294347352923, "percentage": 0.88, "elapsed_time": "0:12:33", "remaining_time": "23:41:53", "throughput": 5444.59, "total_tokens": 4100224}
{"current_steps": 355, "total_steps": 40000, "loss": 1.4205, "lr": 4.999033797129568e-05, "epoch": 0.09090327123743679, "percentage": 0.89, "elapsed_time": "0:12:40", "remaining_time": "23:35:53", "throughput": 5465.74, "total_tokens": 4157888}
{"current_steps": 360, "total_steps": 40000, "loss": 1.2999, "lr": 4.999006312330894e-05, "epoch": 0.09218359900134435, "percentage": 0.9, "elapsed_time": "0:12:48", "remaining_time": "23:30:05", "throughput": 5486.62, "total_tokens": 4215712}
{"current_steps": 365, "total_steps": 40000, "loss": 1.4194, "lr": 4.998978442154043e-05, "epoch": 0.0934639267652519, "percentage": 0.91, "elapsed_time": "0:12:56", "remaining_time": "23:24:25", "throughput": 5507.78, "total_tokens": 4274048}
{"current_steps": 370, "total_steps": 40000, "loss": 1.3199, "lr": 4.9989501866033125e-05, "epoch": 0.09474425452915947, "percentage": 0.92, "elapsed_time": "0:13:03", "remaining_time": "23:18:55", "throughput": 5527.02, "total_tokens": 4331264}
{"current_steps": 375, "total_steps": 40000, "loss": 1.262, "lr": 4.998921545683059e-05, "epoch": 0.09602458229306703, "percentage": 0.94, "elapsed_time": "0:13:11", "remaining_time": "23:13:30", "throughput": 5549.66, "total_tokens": 4391264}
{"current_steps": 380, "total_steps": 40000, "loss": 1.3388, "lr": 4.9988925193976996e-05, "epoch": 0.09730491005697459, "percentage": 0.95, "elapsed_time": "0:13:18", "remaining_time": "23:08:18", "throughput": 5569.62, "total_tokens": 4449696}
{"current_steps": 385, "total_steps": 40000, "loss": 1.2727, "lr": 4.998863107751711e-05, "epoch": 0.09858523782088215, "percentage": 0.96, "elapsed_time": "0:13:26", "remaining_time": "23:03:08", "throughput": 5588.46, "total_tokens": 4507264}
{"current_steps": 390, "total_steps": 40000, "loss": 1.3354, "lr": 4.998833310749629e-05, "epoch": 0.0998655655847897, "percentage": 0.97, "elapsed_time": "0:13:34", "remaining_time": "22:58:16", "throughput": 5607.76, "total_tokens": 4566016}
{"current_steps": 395, "total_steps": 40000, "loss": 1.2047, "lr": 4.998803128396047e-05, "epoch": 0.10114589334869727, "percentage": 0.99, "elapsed_time": "0:13:41", "remaining_time": "22:53:24", "throughput": 5629.46, "total_tokens": 4626624}
{"current_steps": 400, "total_steps": 40000, "loss": 1.2879, "lr": 4.9987725606956215e-05, "epoch": 0.10242622111260483, "percentage": 1.0, "elapsed_time": "0:13:49", "remaining_time": "22:48:37", "throughput": 5650.07, "total_tokens": 4686560}
{"current_steps": 400, "total_steps": 40000, "eval_loss": 1.2604845762252808, "epoch": 0.10242622111260483, "percentage": 1.0, "elapsed_time": "0:17:21", "remaining_time": "1 day, 4:38:38", "throughput": 4499.37, "total_tokens": 4686560}
{"current_steps": 405, "total_steps": 40000, "loss": 1.217, "lr": 4.998741607653066e-05, "epoch": 0.10370654887651239, "percentage": 1.01, "elapsed_time": "0:17:31", "remaining_time": "1 day, 4:33:15", "throughput": 4512.4, "total_tokens": 4744576}
{"current_steps": 410, "total_steps": 40000, "loss": 1.3774, "lr": 4.9987102692731523e-05, "epoch": 0.10498687664041995, "percentage": 1.03, "elapsed_time": "0:17:39", "remaining_time": "1 day, 4:24:28", "throughput": 4533.64, "total_tokens": 4801632}
{"current_steps": 415, "total_steps": 40000, "loss": 1.1828, "lr": 4.9986785455607157e-05, "epoch": 0.1062672044043275, "percentage": 1.04, "elapsed_time": "0:17:46", "remaining_time": "1 day, 4:15:50", "throughput": 4555.52, "total_tokens": 4859520}
{"current_steps": 420, "total_steps": 40000, "loss": 1.3262, "lr": 4.9986464365206456e-05, "epoch": 0.10754753216823507, "percentage": 1.05, "elapsed_time": "0:17:54", "remaining_time": "1 day, 4:07:24", "throughput": 4578.5, "total_tokens": 4918912}
{"current_steps": 425, "total_steps": 40000, "loss": 1.2432, "lr": 4.9986139421578956e-05, "epoch": 0.10882785993214263, "percentage": 1.06, "elapsed_time": "0:18:02", "remaining_time": "1 day, 3:59:13", "throughput": 4599.83, "total_tokens": 4977024}
{"current_steps": 430, "total_steps": 40000, "loss": 1.2942, "lr": 4.998581062477477e-05, "epoch": 0.11010818769605019, "percentage": 1.07, "elapsed_time": "0:18:09", "remaining_time": "1 day, 3:51:18", "throughput": 4623.22, "total_tokens": 5037984}
{"current_steps": 435, "total_steps": 40000, "loss": 1.2133, "lr": 4.998547797484458e-05, "epoch": 0.11138851545995775, "percentage": 1.09, "elapsed_time": "0:18:17", "remaining_time": "1 day, 3:43:29", "throughput": 4644.04, "total_tokens": 5096192}
{"current_steps": 440, "total_steps": 40000, "loss": 1.2076, "lr": 4.9985141471839706e-05, "epoch": 0.1126688432238653, "percentage": 1.1, "elapsed_time": "0:18:24", "remaining_time": "1 day, 3:35:47", "throughput": 4665.78, "total_tokens": 5155584}
{"current_steps": 445, "total_steps": 40000, "loss": 1.2043, "lr": 4.998480111581203e-05, "epoch": 0.11394917098777287, "percentage": 1.11, "elapsed_time": "0:18:33", "remaining_time": "1 day, 3:28:58", "throughput": 4690.09, "total_tokens": 5220416}
{"current_steps": 450, "total_steps": 40000, "loss": 1.13, "lr": 4.998445690681405e-05, "epoch": 0.11522949875168043, "percentage": 1.12, "elapsed_time": "0:18:40", "remaining_time": "1 day, 3:21:40", "throughput": 4709.39, "total_tokens": 5278016}
{"current_steps": 455, "total_steps": 40000, "loss": 1.0499, "lr": 4.9984108844898834e-05, "epoch": 0.11650982651558799, "percentage": 1.14, "elapsed_time": "0:18:48", "remaining_time": "1 day, 3:14:30", "throughput": 4730.37, "total_tokens": 5337664}
{"current_steps": 460, "total_steps": 40000, "loss": 1.1291, "lr": 4.9983756930120076e-05, "epoch": 0.11779015427949555, "percentage": 1.15, "elapsed_time": "0:18:55", "remaining_time": "1 day, 3:07:24", "throughput": 4751.75, "total_tokens": 5397888}
{"current_steps": 465, "total_steps": 40000, "loss": 1.0839, "lr": 4.9983401162532025e-05, "epoch": 0.1190704820434031, "percentage": 1.16, "elapsed_time": "0:19:03", "remaining_time": "1 day, 3:00:32", "throughput": 4772.2, "total_tokens": 5457600}
{"current_steps": 470, "total_steps": 40000, "loss": 1.1443, "lr": 4.998304154218955e-05, "epoch": 0.12035080980731067, "percentage": 1.18, "elapsed_time": "0:19:11", "remaining_time": "1 day, 2:53:44", "throughput": 4791.98, "total_tokens": 5516608}
{"current_steps": 475, "total_steps": 40000, "loss": 1.0957, "lr": 4.998267806914812e-05, "epoch": 0.12163113757121823, "percentage": 1.19, "elapsed_time": "0:19:18", "remaining_time": "1 day, 2:47:10", "throughput": 4810.58, "total_tokens": 5574848}
{"current_steps": 480, "total_steps": 40000, "loss": 1.253, "lr": 4.998231074346378e-05, "epoch": 0.12291146533512579, "percentage": 1.2, "elapsed_time": "0:19:26", "remaining_time": "1 day, 2:40:42", "throughput": 4829.75, "total_tokens": 5633920}
{"current_steps": 485, "total_steps": 40000, "loss": 1.0683, "lr": 4.998193956519317e-05, "epoch": 0.12419179309903335, "percentage": 1.21, "elapsed_time": "0:19:34", "remaining_time": "1 day, 2:34:21", "throughput": 4847.24, "total_tokens": 5691296}
{"current_steps": 490, "total_steps": 40000, "loss": 1.1551, "lr": 4.9981564534393545e-05, "epoch": 0.1254721208629409, "percentage": 1.23, "elapsed_time": "0:19:41", "remaining_time": "1 day, 2:28:10", "throughput": 4866.6, "total_tokens": 5751264}
{"current_steps": 495, "total_steps": 40000, "loss": 1.2107, "lr": 4.998118565112272e-05, "epoch": 0.12675244862684848, "percentage": 1.24, "elapsed_time": "0:19:49", "remaining_time": "1 day, 2:22:10", "throughput": 4884.92, "total_tokens": 5810528}
{"current_steps": 500, "total_steps": 40000, "loss": 1.0804, "lr": 4.998080291543914e-05, "epoch": 0.12803277639075603, "percentage": 1.25, "elapsed_time": "0:19:57", "remaining_time": "1 day, 2:16:09", "throughput": 4902.93, "total_tokens": 5869216}
{"current_steps": 505, "total_steps": 40000, "loss": 1.1712, "lr": 4.9980416327401826e-05, "epoch": 0.1293131041546636, "percentage": 1.26, "elapsed_time": "0:20:04", "remaining_time": "1 day, 2:10:18", "throughput": 4919.33, "total_tokens": 5926432}
{"current_steps": 510, "total_steps": 40000, "loss": 1.0727, "lr": 4.998002588707038e-05, "epoch": 0.13059343191857115, "percentage": 1.27, "elapsed_time": "0:20:12", "remaining_time": "1 day, 2:04:33", "throughput": 4935.58, "total_tokens": 5983616}
{"current_steps": 515, "total_steps": 40000, "loss": 1.0388, "lr": 4.997963159450503e-05, "epoch": 0.13187375968247872, "percentage": 1.29, "elapsed_time": "0:20:19", "remaining_time": "1 day, 1:58:53", "throughput": 4951.91, "total_tokens": 6041088}
{"current_steps": 520, "total_steps": 40000, "loss": 1.0909, "lr": 4.9979233449766575e-05, "epoch": 0.13315408744638627, "percentage": 1.3, "elapsed_time": "0:20:27", "remaining_time": "1 day, 1:53:21", "throughput": 4968.97, "total_tokens": 6099776}
{"current_steps": 525, "total_steps": 40000, "loss": 1.0392, "lr": 4.997883145291641e-05, "epoch": 0.13443441521029384, "percentage": 1.31, "elapsed_time": "0:20:35", "remaining_time": "1 day, 1:47:57", "throughput": 4986.89, "total_tokens": 6159936}
{"current_steps": 530, "total_steps": 40000, "loss": 1.183, "lr": 4.9978425604016536e-05, "epoch": 0.13571474297420139, "percentage": 1.32, "elapsed_time": "0:20:42", "remaining_time": "1 day, 1:42:38", "throughput": 5003.94, "total_tokens": 6219264}
{"current_steps": 535, "total_steps": 40000, "loss": 1.1467, "lr": 4.9978015903129536e-05, "epoch": 0.13699507073810896, "percentage": 1.34, "elapsed_time": "0:20:50", "remaining_time": "1 day, 1:37:27", "throughput": 5019.98, "total_tokens": 6277696}
{"current_steps": 540, "total_steps": 40000, "loss": 1.1345, "lr": 4.997760235031859e-05, "epoch": 0.1382753985020165, "percentage": 1.35, "elapsed_time": "0:20:58", "remaining_time": "1 day, 1:32:20", "throughput": 5036.81, "total_tokens": 6337216}
{"current_steps": 545, "total_steps": 40000, "loss": 1.1095, "lr": 4.9977184945647473e-05, "epoch": 0.13955572626592408, "percentage": 1.36, "elapsed_time": "0:21:05", "remaining_time": "1 day, 1:27:20", "throughput": 5052.95, "total_tokens": 6396288}
{"current_steps": 550, "total_steps": 40000, "loss": 1.1103, "lr": 4.997676368918055e-05, "epoch": 0.14083605402983163, "percentage": 1.38, "elapsed_time": "0:21:13", "remaining_time": "1 day, 1:22:25", "throughput": 5069.14, "total_tokens": 6455616}
{"current_steps": 555, "total_steps": 40000, "loss": 1.1294, "lr": 4.9976338580982794e-05, "epoch": 0.1421163817937392, "percentage": 1.39, "elapsed_time": "0:21:21", "remaining_time": "1 day, 1:17:41", "throughput": 5084.53, "total_tokens": 6514560}
{"current_steps": 560, "total_steps": 40000, "loss": 1.0222, "lr": 4.9975909621119755e-05, "epoch": 0.14339670955764675, "percentage": 1.4, "elapsed_time": "0:21:28", "remaining_time": "1 day, 1:12:50", "throughput": 5099.81, "total_tokens": 6572832}
{"current_steps": 565, "total_steps": 40000, "loss": 1.1194, "lr": 4.997547680965758e-05, "epoch": 0.14467703732155432, "percentage": 1.41, "elapsed_time": "0:21:36", "remaining_time": "1 day, 1:08:07", "throughput": 5115.56, "total_tokens": 6632032}
{"current_steps": 570, "total_steps": 40000, "loss": 1.0502, "lr": 4.997504014666302e-05, "epoch": 0.14595736508546187, "percentage": 1.43, "elapsed_time": "0:21:44", "remaining_time": "1 day, 1:03:31", "throughput": 5130.45, "total_tokens": 6690624}
{"current_steps": 575, "total_steps": 40000, "loss": 1.0461, "lr": 4.997459963220342e-05, "epoch": 0.14723769284936944, "percentage": 1.44, "elapsed_time": "0:21:51", "remaining_time": "1 day, 0:58:59", "throughput": 5144.94, "total_tokens": 6748832}
{"current_steps": 580, "total_steps": 40000, "loss": 1.0679, "lr": 4.997415526634671e-05, "epoch": 0.14851802061327699, "percentage": 1.45, "elapsed_time": "0:21:59", "remaining_time": "1 day, 0:54:29", "throughput": 5159.48, "total_tokens": 6807072}
{"current_steps": 585, "total_steps": 40000, "loss": 1.0766, "lr": 4.99737070491614e-05, "epoch": 0.14979834837718456, "percentage": 1.46, "elapsed_time": "0:22:07", "remaining_time": "1 day, 0:50:08", "throughput": 5173.39, "total_tokens": 6865152}
{"current_steps": 590, "total_steps": 40000, "loss": 1.0903, "lr": 4.997325498071663e-05, "epoch": 0.15107867614109213, "percentage": 1.47, "elapsed_time": "0:22:14", "remaining_time": "1 day, 0:45:52", "throughput": 5186.13, "total_tokens": 6921888}
{"current_steps": 595, "total_steps": 40000, "loss": 1.0834, "lr": 4.997279906108211e-05, "epoch": 0.15235900390499968, "percentage": 1.49, "elapsed_time": "0:22:22", "remaining_time": "1 day, 0:41:38", "throughput": 5199.93, "total_tokens": 6980000}
{"current_steps": 600, "total_steps": 40000, "loss": 1.1437, "lr": 4.9972339290328155e-05, "epoch": 0.15363933166890725, "percentage": 1.5, "elapsed_time": "0:22:29", "remaining_time": "1 day, 0:37:26", "throughput": 5213.72, "total_tokens": 7038272}
{"current_steps": 600, "total_steps": 40000, "eval_loss": 1.0865777730941772, "epoch": 0.15363933166890725, "percentage": 1.5, "elapsed_time": "0:26:01", "remaining_time": "1 day, 4:29:25", "throughput": 4506.18, "total_tokens": 7038272}
{"current_steps": 605, "total_steps": 40000, "loss": 1.1129, "lr": 4.9971875668525646e-05, "epoch": 0.1549196594328148, "percentage": 1.51, "elapsed_time": "0:26:11", "remaining_time": "1 day, 4:25:45", "throughput": 4514.86, "total_tokens": 7096192}
{"current_steps": 610, "total_steps": 40000, "loss": 1.0804, "lr": 4.997140819574609e-05, "epoch": 0.15619998719672237, "percentage": 1.52, "elapsed_time": "0:26:19", "remaining_time": "1 day, 4:19:48", "throughput": 4529.57, "total_tokens": 7154016}
{"current_steps": 615, "total_steps": 40000, "loss": 1.1931, "lr": 4.997093687206159e-05, "epoch": 0.15748031496062992, "percentage": 1.54, "elapsed_time": "0:26:27", "remaining_time": "1 day, 4:13:59", "throughput": 4545.97, "total_tokens": 7214912}
{"current_steps": 620, "total_steps": 40000, "loss": 1.0684, "lr": 4.997046169754482e-05, "epoch": 0.1587606427245375, "percentage": 1.55, "elapsed_time": "0:26:34", "remaining_time": "1 day, 4:08:13", "throughput": 4561.39, "total_tokens": 7274336}
{"current_steps": 625, "total_steps": 40000, "loss": 1.1246, "lr": 4.996998267226905e-05, "epoch": 0.16004097048844504, "percentage": 1.56, "elapsed_time": "0:26:42", "remaining_time": "1 day, 4:02:31", "throughput": 4576.88, "total_tokens": 7333984}
{"current_steps": 630, "total_steps": 40000, "loss": 1.0655, "lr": 4.996949979630817e-05, "epoch": 0.1613212982523526, "percentage": 1.57, "elapsed_time": "0:26:50", "remaining_time": "1 day, 3:56:55", "throughput": 4592.09, "total_tokens": 7393504}
{"current_steps": 635, "total_steps": 40000, "loss": 1.0628, "lr": 4.996901306973663e-05, "epoch": 0.16260162601626016, "percentage": 1.59, "elapsed_time": "0:26:57", "remaining_time": "1 day, 3:51:22", "throughput": 4606.47, "total_tokens": 7451744}
{"current_steps": 640, "total_steps": 40000, "loss": 1.0746, "lr": 4.996852249262949e-05, "epoch": 0.16388195378016773, "percentage": 1.6, "elapsed_time": "0:27:05", "remaining_time": "1 day, 3:45:54", "throughput": 4621.46, "total_tokens": 7511136}
{"current_steps": 645, "total_steps": 40000, "loss": 0.994, "lr": 4.996802806506241e-05, "epoch": 0.16516228154407528, "percentage": 1.61, "elapsed_time": "0:27:12", "remaining_time": "1 day, 3:40:32", "throughput": 4636.09, "total_tokens": 7570336}
{"current_steps": 650, "total_steps": 40000, "loss": 1.0151, "lr": 4.996752978711164e-05, "epoch": 0.16644260930798285, "percentage": 1.62, "elapsed_time": "0:27:20", "remaining_time": "1 day, 3:35:18", "throughput": 4649.9, "total_tokens": 7628544}
{"current_steps": 655, "total_steps": 40000, "loss": 1.0617, "lr": 4.996702765885401e-05, "epoch": 0.1677229370718904, "percentage": 1.64, "elapsed_time": "0:27:28", "remaining_time": "1 day, 3:30:07", "throughput": 4664.0, "total_tokens": 7687360}
{"current_steps": 660, "total_steps": 40000, "loss": 1.0602, "lr": 4.9966521680366964e-05, "epoch": 0.16900326483579797, "percentage": 1.65, "elapsed_time": "0:27:35", "remaining_time": "1 day, 3:25:02", "throughput": 4677.52, "total_tokens": 7745568}
{"current_steps": 665, "total_steps": 40000, "loss": 1.1621, "lr": 4.9966011851728524e-05, "epoch": 0.17028359259970552, "percentage": 1.66, "elapsed_time": "0:27:43", "remaining_time": "1 day, 3:19:59", "throughput": 4690.65, "total_tokens": 7803136}
{"current_steps": 670, "total_steps": 40000, "loss": 1.1239, "lr": 4.996549817301731e-05, "epoch": 0.1715639203636131, "percentage": 1.68, "elapsed_time": "0:27:51", "remaining_time": "1 day, 3:15:02", "throughput": 4703.31, "total_tokens": 7860224}
{"current_steps": 675, "total_steps": 40000, "loss": 1.028, "lr": 4.9964980644312544e-05, "epoch": 0.17284424812752064, "percentage": 1.69, "elapsed_time": "0:27:58", "remaining_time": "1 day, 3:10:08", "throughput": 4716.5, "total_tokens": 7918304}
{"current_steps": 680, "total_steps": 40000, "loss": 1.0191, "lr": 4.996445926569403e-05, "epoch": 0.1741245758914282, "percentage": 1.7, "elapsed_time": "0:28:06", "remaining_time": "1 day, 3:05:23", "throughput": 4728.93, "total_tokens": 7975680}
{"current_steps": 685, "total_steps": 40000, "loss": 1.0535, "lr": 4.996393403724218e-05, "epoch": 0.17540490365533576, "percentage": 1.71, "elapsed_time": "0:28:14", "remaining_time": "1 day, 3:00:36", "throughput": 4742.11, "total_tokens": 8034048}
{"current_steps": 690, "total_steps": 40000, "loss": 1.0139, "lr": 4.9963404959037985e-05, "epoch": 0.17668523141924333, "percentage": 1.73, "elapsed_time": "0:28:21", "remaining_time": "1 day, 2:55:55", "throughput": 4754.99, "total_tokens": 8092192}
{"current_steps": 695, "total_steps": 40000, "loss": 0.9872, "lr": 4.996287203116303e-05, "epoch": 0.17796555918315088, "percentage": 1.74, "elapsed_time": "0:28:29", "remaining_time": "1 day, 2:51:16", "throughput": 4767.84, "total_tokens": 8150368}
{"current_steps": 700, "total_steps": 40000, "loss": 1.0083, "lr": 4.996233525369951e-05, "epoch": 0.17924588694705845, "percentage": 1.75, "elapsed_time": "0:28:37", "remaining_time": "1 day, 2:46:41", "throughput": 4780.28, "total_tokens": 8208128}
{"current_steps": 705, "total_steps": 40000, "loss": 0.995, "lr": 4.99617946267302e-05, "epoch": 0.180526214710966, "percentage": 1.76, "elapsed_time": "0:28:44", "remaining_time": "1 day, 2:42:17", "throughput": 4792.09, "total_tokens": 8265504}
{"current_steps": 710, "total_steps": 40000, "loss": 0.9728, "lr": 4.996125015033846e-05, "epoch": 0.18180654247487357, "percentage": 1.77, "elapsed_time": "0:28:52", "remaining_time": "1 day, 2:37:53", "throughput": 4806.14, "total_tokens": 8326656}
{"current_steps": 715, "total_steps": 40000, "loss": 1.0038, "lr": 4.996070182460827e-05, "epoch": 0.18308687023878112, "percentage": 1.79, "elapsed_time": "0:29:00", "remaining_time": "1 day, 2:33:26", "throughput": 4819.31, "total_tokens": 8385984}
{"current_steps": 720, "total_steps": 40000, "loss": 1.0275, "lr": 4.996014964962418e-05, "epoch": 0.1843671980026887, "percentage": 1.8, "elapsed_time": "0:29:07", "remaining_time": "1 day, 2:29:06", "throughput": 4831.83, "total_tokens": 8444608}
{"current_steps": 725, "total_steps": 40000, "loss": 0.9747, "lr": 4.9959593625471344e-05, "epoch": 0.18564752576659624, "percentage": 1.81, "elapsed_time": "0:29:15", "remaining_time": "1 day, 2:24:52", "throughput": 4844.55, "total_tokens": 8504000}
{"current_steps": 730, "total_steps": 40000, "loss": 0.9898, "lr": 4.995903375223552e-05, "epoch": 0.1869278535305038, "percentage": 1.82, "elapsed_time": "0:29:23", "remaining_time": "1 day, 2:20:40", "throughput": 4857.37, "total_tokens": 8563648}
{"current_steps": 735, "total_steps": 40000, "loss": 0.9707, "lr": 4.995847003000302e-05, "epoch": 0.18820818129441136, "percentage": 1.84, "elapsed_time": "0:29:30", "remaining_time": "1 day, 2:16:34", "throughput": 4869.21, "total_tokens": 8621920}
{"current_steps": 740, "total_steps": 40000, "loss": 0.9829, "lr": 4.9957902458860804e-05, "epoch": 0.18948850905831893, "percentage": 1.85, "elapsed_time": "0:29:38", "remaining_time": "1 day, 2:12:29", "throughput": 4880.33, "total_tokens": 8679008}
{"current_steps": 745, "total_steps": 40000, "loss": 1.0266, "lr": 4.995733103889639e-05, "epoch": 0.19076883682222648, "percentage": 1.86, "elapsed_time": "0:29:46", "remaining_time": "1 day, 2:08:29", "throughput": 4891.56, "total_tokens": 8736640}
{"current_steps": 750, "total_steps": 40000, "loss": 0.903, "lr": 4.99567557701979e-05, "epoch": 0.19204916458613405, "percentage": 1.88, "elapsed_time": "0:29:53", "remaining_time": "1 day, 2:04:26", "throughput": 4903.18, "total_tokens": 8794464}
{"current_steps": 755, "total_steps": 40000, "loss": 0.9411, "lr": 4.995617665285403e-05, "epoch": 0.1933294923500416, "percentage": 1.89, "elapsed_time": "0:30:01", "remaining_time": "1 day, 2:00:30", "throughput": 4914.86, "total_tokens": 8853056}
{"current_steps": 760, "total_steps": 40000, "loss": 0.9965, "lr": 4.99555936869541e-05, "epoch": 0.19460982011394917, "percentage": 1.9, "elapsed_time": "0:30:08", "remaining_time": "1 day, 1:56:37", "throughput": 4926.2, "total_tokens": 8911136}
{"current_steps": 765, "total_steps": 40000, "loss": 1.023, "lr": 4.995500687258803e-05, "epoch": 0.19589014787785672, "percentage": 1.91, "elapsed_time": "0:30:16", "remaining_time": "1 day, 1:52:47", "throughput": 4938.03, "total_tokens": 8970272}
{"current_steps": 770, "total_steps": 40000, "loss": 0.9153, "lr": 4.995441620984628e-05, "epoch": 0.1971704756417643, "percentage": 1.93, "elapsed_time": "0:30:24", "remaining_time": "1 day, 1:49:03", "throughput": 4949.34, "total_tokens": 9028992}
{"current_steps": 775, "total_steps": 40000, "loss": 0.9709, "lr": 4.995382169881996e-05, "epoch": 0.19845080340567184, "percentage": 1.94, "elapsed_time": "0:30:31", "remaining_time": "1 day, 1:45:22", "throughput": 4959.99, "total_tokens": 9086656}
{"current_steps": 780, "total_steps": 40000, "loss": 1.0704, "lr": 4.9953223339600755e-05, "epoch": 0.1997311311695794, "percentage": 1.95, "elapsed_time": "0:30:39", "remaining_time": "1 day, 1:41:35", "throughput": 4971.73, "total_tokens": 9145664}
{"current_steps": 785, "total_steps": 40000, "loss": 1.0161, "lr": 4.995262113228091e-05, "epoch": 0.201011458933487, "percentage": 1.96, "elapsed_time": "0:30:47", "remaining_time": "1 day, 1:37:57", "throughput": 4981.73, "total_tokens": 9202208}
{"current_steps": 790, "total_steps": 40000, "loss": 0.9753, "lr": 4.995201507695332e-05, "epoch": 0.20229178669739453, "percentage": 1.98, "elapsed_time": "0:30:54", "remaining_time": "1 day, 1:34:15", "throughput": 4992.34, "total_tokens": 9259456}
{"current_steps": 795, "total_steps": 40000, "loss": 0.9808, "lr": 4.995140517371144e-05, "epoch": 0.2035721144613021, "percentage": 1.99, "elapsed_time": "0:31:02", "remaining_time": "1 day, 1:30:43", "throughput": 5003.39, "total_tokens": 9318368}
{"current_steps": 800, "total_steps": 40000, "loss": 0.9394, "lr": 4.995079142264932e-05, "epoch": 0.20485244222520965, "percentage": 2.0, "elapsed_time": "0:31:10", "remaining_time": "1 day, 1:27:12", "throughput": 5014.06, "total_tokens": 9376512}
{"current_steps": 800, "total_steps": 40000, "eval_loss": 1.0057785511016846, "epoch": 0.20485244222520965, "percentage": 2.0, "elapsed_time": "0:34:42", "remaining_time": "1 day, 4:20:20", "throughput": 4503.49, "total_tokens": 9376512}
{"current_steps": 805, "total_steps": 40000, "loss": 0.8976, "lr": 4.995017382386162e-05, "epoch": 0.20613276998911723, "percentage": 2.01, "elapsed_time": "0:34:52", "remaining_time": "1 day, 4:18:08", "throughput": 4508.75, "total_tokens": 9435104}
{"current_steps": 810, "total_steps": 40000, "loss": 0.9945, "lr": 4.994955237744356e-05, "epoch": 0.20741309775302477, "percentage": 2.02, "elapsed_time": "0:35:00", "remaining_time": "1 day, 4:13:36", "throughput": 4520.18, "total_tokens": 9493600}
{"current_steps": 815, "total_steps": 40000, "loss": 0.997, "lr": 4.994892708349101e-05, "epoch": 0.20869342551693235, "percentage": 2.04, "elapsed_time": "0:35:07", "remaining_time": "1 day, 4:09:08", "throughput": 4531.1, "total_tokens": 9551232}
{"current_steps": 820, "total_steps": 40000, "loss": 1.0474, "lr": 4.994829794210035e-05, "epoch": 0.2099737532808399, "percentage": 2.05, "elapsed_time": "0:35:15", "remaining_time": "1 day, 4:04:45", "throughput": 4542.62, "total_tokens": 9610464}
{"current_steps": 825, "total_steps": 40000, "loss": 0.9523, "lr": 4.994766495336864e-05, "epoch": 0.21125408104474747, "percentage": 2.06, "elapsed_time": "0:35:23", "remaining_time": "1 day, 4:00:22", "throughput": 4553.29, "total_tokens": 9667776}
{"current_steps": 830, "total_steps": 40000, "loss": 0.9904, "lr": 4.994702811739348e-05, "epoch": 0.212534408808655, "percentage": 2.08, "elapsed_time": "0:35:30", "remaining_time": "1 day, 3:56:05", "throughput": 4563.53, "total_tokens": 9724608}
{"current_steps": 835, "total_steps": 40000, "loss": 0.9402, "lr": 4.994638743427308e-05, "epoch": 0.21381473657256259, "percentage": 2.09, "elapsed_time": "0:35:38", "remaining_time": "1 day, 3:51:46", "throughput": 4574.88, "total_tokens": 9783520}
{"current_steps": 840, "total_steps": 40000, "loss": 1.0263, "lr": 4.994574290410624e-05, "epoch": 0.21509506433647013, "percentage": 2.1, "elapsed_time": "0:35:46", "remaining_time": "1 day, 3:47:32", "throughput": 4586.11, "total_tokens": 9842624}
{"current_steps": 845, "total_steps": 40000, "loss": 0.9629, "lr": 4.9945094526992364e-05, "epoch": 0.2163753921003777, "percentage": 2.11, "elapsed_time": "0:35:53", "remaining_time": "1 day, 3:43:22", "throughput": 4596.34, "total_tokens": 9899744}
{"current_steps": 850, "total_steps": 40000, "loss": 0.934, "lr": 4.994444230303142e-05, "epoch": 0.21765571986428525, "percentage": 2.12, "elapsed_time": "0:36:01", "remaining_time": "1 day, 3:39:15", "throughput": 4607.04, "total_tokens": 9958016}
{"current_steps": 855, "total_steps": 40000, "loss": 1.061, "lr": 4.994378623232402e-05, "epoch": 0.21893604762819283, "percentage": 2.14, "elapsed_time": "0:36:09", "remaining_time": "1 day, 3:35:11", "throughput": 4617.14, "total_tokens": 10015296}
{"current_steps": 860, "total_steps": 40000, "loss": 1.0334, "lr": 4.99431263149713e-05, "epoch": 0.22021637539210037, "percentage": 2.15, "elapsed_time": "0:36:16", "remaining_time": "1 day, 3:31:10", "throughput": 4627.46, "total_tokens": 10073152}
{"current_steps": 865, "total_steps": 40000, "loss": 1.0055, "lr": 4.9942462551075056e-05, "epoch": 0.22149670315600795, "percentage": 2.16, "elapsed_time": "0:36:24", "remaining_time": "1 day, 3:27:10", "throughput": 4638.06, "total_tokens": 10131584}
{"current_steps": 870, "total_steps": 40000, "loss": 0.9752, "lr": 4.994179494073764e-05, "epoch": 0.2227770309199155, "percentage": 2.17, "elapsed_time": "0:36:32", "remaining_time": "1 day, 3:23:15", "throughput": 4648.11, "total_tokens": 10189248}
{"current_steps": 875, "total_steps": 40000, "loss": 0.9754, "lr": 4.9941123484062e-05, "epoch": 0.22405735868382307, "percentage": 2.19, "elapsed_time": "0:36:39", "remaining_time": "1 day, 3:19:21", "throughput": 4657.73, "total_tokens": 10245984}
{"current_steps": 880, "total_steps": 40000, "loss": 1.0447, "lr": 4.99404481811517e-05, "epoch": 0.2253376864477306, "percentage": 2.2, "elapsed_time": "0:36:47", "remaining_time": "1 day, 3:15:29", "throughput": 4669.46, "total_tokens": 10307424}
{"current_steps": 885, "total_steps": 40000, "loss": 0.9058, "lr": 4.9939769032110864e-05, "epoch": 0.22661801421163819, "percentage": 2.21, "elapsed_time": "0:36:55", "remaining_time": "1 day, 3:11:41", "throughput": 4679.59, "total_tokens": 10365664}
{"current_steps": 890, "total_steps": 40000, "loss": 0.8815, "lr": 4.993908603704423e-05, "epoch": 0.22789834197554573, "percentage": 2.23, "elapsed_time": "0:37:02", "remaining_time": "1 day, 3:07:52", "throughput": 4689.7, "total_tokens": 10423680}
{"current_steps": 895, "total_steps": 40000, "loss": 1.0555, "lr": 4.9938399196057126e-05, "epoch": 0.2291786697394533, "percentage": 2.24, "elapsed_time": "0:37:10", "remaining_time": "1 day, 3:04:08", "throughput": 4700.14, "total_tokens": 10482816}
{"current_steps": 900, "total_steps": 40000, "loss": 0.9612, "lr": 4.993770850925547e-05, "epoch": 0.23045899750336085, "percentage": 2.25, "elapsed_time": "0:37:17", "remaining_time": "1 day, 3:00:25", "throughput": 4710.79, "total_tokens": 10542432}
{"current_steps": 905, "total_steps": 40000, "loss": 0.9264, "lr": 4.993701397674577e-05, "epoch": 0.23173932526726843, "percentage": 2.26, "elapsed_time": "0:37:25", "remaining_time": "1 day, 2:56:44", "throughput": 4721.12, "total_tokens": 10601472}
{"current_steps": 910, "total_steps": 40000, "loss": 0.9628, "lr": 4.993631559863515e-05, "epoch": 0.23301965303117597, "percentage": 2.27, "elapsed_time": "0:37:33", "remaining_time": "1 day, 2:53:10", "throughput": 4731.29, "total_tokens": 10660736}
{"current_steps": 915, "total_steps": 40000, "loss": 1.0408, "lr": 4.9935613375031283e-05, "epoch": 0.23429998079508355, "percentage": 2.29, "elapsed_time": "0:37:40", "remaining_time": "1 day, 2:49:35", "throughput": 4741.19, "total_tokens": 10719264}
{"current_steps": 920, "total_steps": 40000, "loss": 1.0113, "lr": 4.993490730604248e-05, "epoch": 0.2355803085589911, "percentage": 2.3, "elapsed_time": "0:37:48", "remaining_time": "1 day, 2:46:03", "throughput": 4750.25, "total_tokens": 10776096}
{"current_steps": 925, "total_steps": 40000, "loss": 0.9446, "lr": 4.993419739177761e-05, "epoch": 0.23686063632289867, "percentage": 2.31, "elapsed_time": "0:37:56", "remaining_time": "1 day, 2:42:53", "throughput": 4758.34, "total_tokens": 10833088}
{"current_steps": 930, "total_steps": 40000, "loss": 1.0034, "lr": 4.9933483632346164e-05, "epoch": 0.2381409640868062, "percentage": 2.33, "elapsed_time": "0:38:04", "remaining_time": "1 day, 2:39:24", "throughput": 4768.01, "total_tokens": 10891488}
{"current_steps": 935, "total_steps": 40000, "loss": 0.9188, "lr": 4.993276602785821e-05, "epoch": 0.23942129185071379, "percentage": 2.34, "elapsed_time": "0:38:11", "remaining_time": "1 day, 2:35:56", "throughput": 4777.82, "total_tokens": 10950240}
{"current_steps": 940, "total_steps": 40000, "loss": 0.9311, "lr": 4.993204457842441e-05, "epoch": 0.24070161961462133, "percentage": 2.35, "elapsed_time": "0:38:19", "remaining_time": "1 day, 2:32:34", "throughput": 4787.56, "total_tokens": 11009312}
{"current_steps": 945, "total_steps": 40000, "loss": 0.9697, "lr": 4.993131928415602e-05, "epoch": 0.2419819473785289, "percentage": 2.36, "elapsed_time": "0:38:27", "remaining_time": "1 day, 2:29:10", "throughput": 4797.75, "total_tokens": 11069248}
{"current_steps": 950, "total_steps": 40000, "loss": 0.9197, "lr": 4.993059014516489e-05, "epoch": 0.24326227514243645, "percentage": 2.38, "elapsed_time": "0:38:34", "remaining_time": "1 day, 2:25:53", "throughput": 4807.25, "total_tokens": 11128160}
{"current_steps": 955, "total_steps": 40000, "loss": 0.921, "lr": 4.9929857161563464e-05, "epoch": 0.24454260290634403, "percentage": 2.39, "elapsed_time": "0:38:42", "remaining_time": "1 day, 2:22:32", "throughput": 4817.14, "total_tokens": 11187488}
{"current_steps": 960, "total_steps": 40000, "loss": 1.0146, "lr": 4.992912033346477e-05, "epoch": 0.24582293067025157, "percentage": 2.4, "elapsed_time": "0:38:50", "remaining_time": "1 day, 2:19:18", "throughput": 4826.97, "total_tokens": 11247424}
{"current_steps": 965, "total_steps": 40000, "loss": 0.9497, "lr": 4.992837966098245e-05, "epoch": 0.24710325843415915, "percentage": 2.41, "elapsed_time": "0:38:57", "remaining_time": "1 day, 2:16:03", "throughput": 4836.56, "total_tokens": 11306624}
{"current_steps": 970, "total_steps": 40000, "loss": 0.9419, "lr": 4.992763514423071e-05, "epoch": 0.2483835861980667, "percentage": 2.43, "elapsed_time": "0:39:05", "remaining_time": "1 day, 2:12:52", "throughput": 4846.17, "total_tokens": 11366208}
{"current_steps": 975, "total_steps": 40000, "loss": 0.9531, "lr": 4.992688678332437e-05, "epoch": 0.24966391396197427, "percentage": 2.44, "elapsed_time": "0:39:13", "remaining_time": "1 day, 2:09:42", "throughput": 4855.18, "total_tokens": 11424512}
{"current_steps": 980, "total_steps": 40000, "loss": 0.8518, "lr": 4.992613457837884e-05, "epoch": 0.2509442417258818, "percentage": 2.45, "elapsed_time": "0:39:20", "remaining_time": "1 day, 2:06:33", "throughput": 4863.98, "total_tokens": 11482272}
{"current_steps": 985, "total_steps": 40000, "loss": 1.0159, "lr": 4.992537852951011e-05, "epoch": 0.2522245694897894, "percentage": 2.46, "elapsed_time": "0:39:28", "remaining_time": "1 day, 2:03:26", "throughput": 4873.19, "total_tokens": 11541152}
{"current_steps": 990, "total_steps": 40000, "loss": 0.9513, "lr": 4.9924618636834785e-05, "epoch": 0.25350489725369696, "percentage": 2.48, "elapsed_time": "0:39:35", "remaining_time": "1 day, 2:00:22", "throughput": 4882.64, "total_tokens": 11601024}
{"current_steps": 995, "total_steps": 40000, "loss": 0.9269, "lr": 4.9923854900470046e-05, "epoch": 0.25478522501760453, "percentage": 2.49, "elapsed_time": "0:39:43", "remaining_time": "1 day, 1:57:21", "throughput": 4890.68, "total_tokens": 11657728}
{"current_steps": 1000, "total_steps": 40000, "loss": 0.9007, "lr": 4.992308732053367e-05, "epoch": 0.25606555278151205, "percentage": 2.5, "elapsed_time": "0:39:51", "remaining_time": "1 day, 1:54:19", "throughput": 4899.29, "total_tokens": 11715488}
{"current_steps": 1000, "total_steps": 40000, "eval_loss": 0.955946683883667, "epoch": 0.25606555278151205, "percentage": 2.5, "elapsed_time": "0:43:23", "remaining_time": "1 day, 4:11:57", "throughput": 4500.74, "total_tokens": 11715488}
{"current_steps": 1005, "total_steps": 40000, "loss": 0.8804, "lr": 4.992231589714402e-05, "epoch": 0.2573458805454196, "percentage": 2.51, "elapsed_time": "0:43:33", "remaining_time": "1 day, 4:09:47", "throughput": 4505.64, "total_tokens": 11773248}
{"current_steps": 1010, "total_steps": 40000, "loss": 1.0144, "lr": 4.992154063042007e-05, "epoch": 0.2586262083093272, "percentage": 2.53, "elapsed_time": "0:43:40", "remaining_time": "1 day, 4:06:09", "throughput": 4515.15, "total_tokens": 11832896}
{"current_steps": 1015, "total_steps": 40000, "loss": 0.9619, "lr": 4.992076152048136e-05, "epoch": 0.2599065360732348, "percentage": 2.54, "elapsed_time": "0:43:48", "remaining_time": "1 day, 4:02:32", "throughput": 4524.19, "total_tokens": 11891168}
{"current_steps": 1020, "total_steps": 40000, "loss": 0.9151, "lr": 4.991997856744807e-05, "epoch": 0.2611868638371423, "percentage": 2.55, "elapsed_time": "0:43:55", "remaining_time": "1 day, 3:58:55", "throughput": 4533.57, "total_tokens": 11950400}
{"current_steps": 1025, "total_steps": 40000, "loss": 0.9221, "lr": 4.9919191771440905e-05, "epoch": 0.26246719160104987, "percentage": 2.56, "elapsed_time": "0:44:03", "remaining_time": "1 day, 3:55:19", "throughput": 4541.74, "total_tokens": 12006336}
{"current_steps": 1030, "total_steps": 40000, "loss": 0.9439, "lr": 4.991840113258122e-05, "epoch": 0.26374751936495744, "percentage": 2.57, "elapsed_time": "0:44:11", "remaining_time": "1 day, 3:51:48", "throughput": 4550.35, "total_tokens": 12063936}
{"current_steps": 1035, "total_steps": 40000, "loss": 0.9123, "lr": 4.9917606650990933e-05, "epoch": 0.265027847128865, "percentage": 2.59, "elapsed_time": "0:44:18", "remaining_time": "1 day, 3:48:18", "throughput": 4559.27, "total_tokens": 12122400}
{"current_steps": 1040, "total_steps": 40000, "loss": 0.9153, "lr": 4.9916808326792566e-05, "epoch": 0.26630817489277253, "percentage": 2.6, "elapsed_time": "0:44:26", "remaining_time": "1 day, 3:44:52", "throughput": 4567.71, "total_tokens": 12179904}
{"current_steps": 1045, "total_steps": 40000, "loss": 0.9595, "lr": 4.9916006160109235e-05, "epoch": 0.2675885026566801, "percentage": 2.61, "elapsed_time": "0:44:34", "remaining_time": "1 day, 3:41:25", "throughput": 4576.99, "total_tokens": 12239520}
{"current_steps": 1050, "total_steps": 40000, "loss": 0.8627, "lr": 4.991520015106464e-05, "epoch": 0.2688688304205877, "percentage": 2.62, "elapsed_time": "0:44:41", "remaining_time": "1 day, 3:38:02", "throughput": 4585.25, "total_tokens": 12296800}
{"current_steps": 1055, "total_steps": 40000, "loss": 0.8823, "lr": 4.991439029978308e-05, "epoch": 0.27014915818449525, "percentage": 2.64, "elapsed_time": "0:44:49", "remaining_time": "1 day, 3:34:39", "throughput": 4593.78, "total_tokens": 12354592}
{"current_steps": 1060, "total_steps": 40000, "loss": 0.9534, "lr": 4.9913576606389434e-05, "epoch": 0.27142948594840277, "percentage": 2.65, "elapsed_time": "0:44:57", "remaining_time": "1 day, 3:31:17", "throughput": 4602.42, "total_tokens": 12412864}
{"current_steps": 1065, "total_steps": 40000, "loss": 0.9001, "lr": 4.991275907100919e-05, "epoch": 0.27270981371231034, "percentage": 2.66, "elapsed_time": "0:45:04", "remaining_time": "1 day, 3:27:59", "throughput": 4611.12, "total_tokens": 12471616}
{"current_steps": 1070, "total_steps": 40000, "loss": 0.9404, "lr": 4.9911937693768434e-05, "epoch": 0.2739901414762179, "percentage": 2.67, "elapsed_time": "0:45:12", "remaining_time": "1 day, 3:24:44", "throughput": 4619.48, "total_tokens": 12529760}
{"current_steps": 1075, "total_steps": 40000, "loss": 0.9869, "lr": 4.991111247479382e-05, "epoch": 0.2752704692401255, "percentage": 2.69, "elapsed_time": "0:45:20", "remaining_time": "1 day, 3:21:30", "throughput": 4627.25, "total_tokens": 12586272}
{"current_steps": 1080, "total_steps": 40000, "loss": 0.9556, "lr": 4.9910283414212605e-05, "epoch": 0.276550797004033, "percentage": 2.7, "elapsed_time": "0:45:27", "remaining_time": "1 day, 3:18:16", "throughput": 4635.46, "total_tokens": 12643872}
{"current_steps": 1085, "total_steps": 40000, "loss": 0.8641, "lr": 4.990945051215265e-05, "epoch": 0.2778311247679406, "percentage": 2.71, "elapsed_time": "0:45:35", "remaining_time": "1 day, 3:15:07", "throughput": 4643.96, "total_tokens": 12702880}
{"current_steps": 1090, "total_steps": 40000, "loss": 0.9631, "lr": 4.99086137687424e-05, "epoch": 0.27911145253184816, "percentage": 2.73, "elapsed_time": "0:45:43", "remaining_time": "1 day, 3:11:57", "throughput": 4652.2, "total_tokens": 12760992}
{"current_steps": 1095, "total_steps": 40000, "loss": 0.9662, "lr": 4.9907773184110874e-05, "epoch": 0.28039178029575573, "percentage": 2.74, "elapsed_time": "0:45:50", "remaining_time": "1 day, 3:08:49", "throughput": 4660.52, "total_tokens": 12819424}
{"current_steps": 1100, "total_steps": 40000, "loss": 0.8212, "lr": 4.9906928758387715e-05, "epoch": 0.28167210805966325, "percentage": 2.75, "elapsed_time": "0:45:58", "remaining_time": "1 day, 3:05:43", "throughput": 4669.1, "total_tokens": 12878848}
{"current_steps": 1105, "total_steps": 40000, "loss": 0.8996, "lr": 4.9906080491703146e-05, "epoch": 0.2829524358235708, "percentage": 2.76, "elapsed_time": "0:46:05", "remaining_time": "1 day, 3:02:38", "throughput": 4677.79, "total_tokens": 12938496}
{"current_steps": 1110, "total_steps": 40000, "loss": 0.936, "lr": 4.990522838418797e-05, "epoch": 0.2842327635874784, "percentage": 2.77, "elapsed_time": "0:46:13", "remaining_time": "1 day, 2:59:35", "throughput": 4685.81, "total_tokens": 12996480}
{"current_steps": 1115, "total_steps": 40000, "loss": 0.9668, "lr": 4.9904372435973604e-05, "epoch": 0.285513091351386, "percentage": 2.79, "elapsed_time": "0:46:21", "remaining_time": "1 day, 2:56:36", "throughput": 4693.97, "total_tokens": 13055296}
{"current_steps": 1120, "total_steps": 40000, "loss": 0.848, "lr": 4.990351264719203e-05, "epoch": 0.2867934191152935, "percentage": 2.8, "elapsed_time": "0:46:28", "remaining_time": "1 day, 2:53:35", "throughput": 4701.63, "total_tokens": 13112512}
{"current_steps": 1125, "total_steps": 40000, "loss": 0.8958, "lr": 4.990264901797586e-05, "epoch": 0.28807374687920106, "percentage": 2.81, "elapsed_time": "0:46:36", "remaining_time": "1 day, 2:50:35", "throughput": 4709.69, "total_tokens": 13170752}
{"current_steps": 1130, "total_steps": 40000, "loss": 0.9781, "lr": 4.990178154845826e-05, "epoch": 0.28935407464310864, "percentage": 2.83, "elapsed_time": "0:46:44", "remaining_time": "1 day, 2:47:38", "throughput": 4717.94, "total_tokens": 13229952}
{"current_steps": 1135, "total_steps": 40000, "loss": 0.8544, "lr": 4.9900910238773014e-05, "epoch": 0.2906344024070162, "percentage": 2.84, "elapsed_time": "0:46:51", "remaining_time": "1 day, 2:44:41", "throughput": 4725.95, "total_tokens": 13288352}
{"current_steps": 1140, "total_steps": 40000, "loss": 0.874, "lr": 4.990003508905448e-05, "epoch": 0.29191473017092373, "percentage": 2.85, "elapsed_time": "0:46:59", "remaining_time": "1 day, 2:41:48", "throughput": 4733.81, "total_tokens": 13346720}
{"current_steps": 1145, "total_steps": 40000, "loss": 1.0379, "lr": 4.989915609943763e-05, "epoch": 0.2931950579348313, "percentage": 2.86, "elapsed_time": "0:47:07", "remaining_time": "1 day, 2:38:55", "throughput": 4741.72, "total_tokens": 13405184}
{"current_steps": 1150, "total_steps": 40000, "loss": 0.8945, "lr": 4.9898273270058e-05, "epoch": 0.2944753856987389, "percentage": 2.88, "elapsed_time": "0:47:14", "remaining_time": "1 day, 2:36:04", "throughput": 4749.22, "total_tokens": 13462720}
{"current_steps": 1155, "total_steps": 40000, "loss": 0.8813, "lr": 4.989738660105174e-05, "epoch": 0.29575571346264645, "percentage": 2.89, "elapsed_time": "0:47:22", "remaining_time": "1 day, 2:33:12", "throughput": 4756.68, "total_tokens": 13519968}
{"current_steps": 1160, "total_steps": 40000, "loss": 0.9248, "lr": 4.989649609255559e-05, "epoch": 0.29703604122655397, "percentage": 2.9, "elapsed_time": "0:47:29", "remaining_time": "1 day, 2:30:23", "throughput": 4764.42, "total_tokens": 13578304}
{"current_steps": 1165, "total_steps": 40000, "loss": 1.0159, "lr": 4.989560174470687e-05, "epoch": 0.29831636899046154, "percentage": 2.91, "elapsed_time": "0:47:37", "remaining_time": "1 day, 2:27:36", "throughput": 4771.64, "total_tokens": 13635264}
{"current_steps": 1170, "total_steps": 40000, "loss": 0.8694, "lr": 4.989470355764351e-05, "epoch": 0.2995966967543691, "percentage": 2.93, "elapsed_time": "0:47:45", "remaining_time": "1 day, 2:24:51", "throughput": 4778.67, "total_tokens": 13692000}
{"current_steps": 1175, "total_steps": 40000, "loss": 0.8874, "lr": 4.9893801531504e-05, "epoch": 0.3008770245182767, "percentage": 2.94, "elapsed_time": "0:47:52", "remaining_time": "1 day, 2:22:09", "throughput": 4786.47, "total_tokens": 13751200}
{"current_steps": 1180, "total_steps": 40000, "loss": 0.8952, "lr": 4.9892895666427475e-05, "epoch": 0.30215735228218427, "percentage": 2.95, "elapsed_time": "0:48:00", "remaining_time": "1 day, 2:19:25", "throughput": 4793.76, "total_tokens": 13808672}
{"current_steps": 1185, "total_steps": 40000, "loss": 0.9595, "lr": 4.9891985962553606e-05, "epoch": 0.3034376800460918, "percentage": 2.96, "elapsed_time": "0:48:08", "remaining_time": "1 day, 2:16:43", "throughput": 4801.34, "total_tokens": 13867200}
{"current_steps": 1190, "total_steps": 40000, "loss": 0.8602, "lr": 4.989107242002269e-05, "epoch": 0.30471800780999936, "percentage": 2.97, "elapsed_time": "0:48:15", "remaining_time": "1 day, 2:14:03", "throughput": 4808.65, "total_tokens": 13925088}
{"current_steps": 1195, "total_steps": 40000, "loss": 0.8948, "lr": 4.989015503897561e-05, "epoch": 0.30599833557390693, "percentage": 2.99, "elapsed_time": "0:48:23", "remaining_time": "1 day, 2:11:25", "throughput": 4815.87, "total_tokens": 13983040}
{"current_steps": 1200, "total_steps": 40000, "loss": 0.9518, "lr": 4.988923381955383e-05, "epoch": 0.3072786633378145, "percentage": 3.0, "elapsed_time": "0:48:31", "remaining_time": "1 day, 2:08:49", "throughput": 4822.96, "total_tokens": 14040704}
{"current_steps": 1200, "total_steps": 40000, "eval_loss": 0.9228436946868896, "epoch": 0.3072786633378145, "percentage": 3.0, "elapsed_time": "0:52:02", "remaining_time": "1 day, 4:02:50", "throughput": 4496.19, "total_tokens": 14040704}
{"current_steps": 1205, "total_steps": 40000, "loss": 0.9044, "lr": 4.988830876189942e-05, "epoch": 0.308558991101722, "percentage": 3.01, "elapsed_time": "0:52:12", "remaining_time": "1 day, 4:00:56", "throughput": 4500.65, "total_tokens": 14099072}
{"current_steps": 1210, "total_steps": 40000, "loss": 0.9168, "lr": 4.988737986615503e-05, "epoch": 0.3098393188656296, "percentage": 3.02, "elapsed_time": "0:52:20", "remaining_time": "1 day, 3:57:51", "throughput": 4508.69, "total_tokens": 14158688}
{"current_steps": 1215, "total_steps": 40000, "loss": 0.9417, "lr": 4.988644713246391e-05, "epoch": 0.31111964662953717, "percentage": 3.04, "elapsed_time": "0:52:27", "remaining_time": "1 day, 3:54:46", "throughput": 4516.28, "total_tokens": 14216800}
{"current_steps": 1220, "total_steps": 40000, "loss": 0.9012, "lr": 4.988551056096991e-05, "epoch": 0.31239997439344475, "percentage": 3.05, "elapsed_time": "0:52:35", "remaining_time": "1 day, 3:51:44", "throughput": 4523.77, "total_tokens": 14274880}
{"current_steps": 1225, "total_steps": 40000, "loss": 1.0061, "lr": 4.988457015181743e-05, "epoch": 0.31368030215735226, "percentage": 3.06, "elapsed_time": "0:52:43", "remaining_time": "1 day, 3:48:44", "throughput": 4531.25, "total_tokens": 14333120}
{"current_steps": 1230, "total_steps": 40000, "loss": 0.9093, "lr": 4.988362590515153e-05, "epoch": 0.31496062992125984, "percentage": 3.08, "elapsed_time": "0:52:50", "remaining_time": "1 day, 3:45:47", "throughput": 4538.41, "total_tokens": 14390752}
{"current_steps": 1235, "total_steps": 40000, "loss": 0.9311, "lr": 4.9882677821117805e-05, "epoch": 0.3162409576851674, "percentage": 3.09, "elapsed_time": "0:52:58", "remaining_time": "1 day, 3:42:47", "throughput": 4546.46, "total_tokens": 14450784}
{"current_steps": 1240, "total_steps": 40000, "loss": 0.8523, "lr": 4.988172589986246e-05, "epoch": 0.317521285449075, "percentage": 3.1, "elapsed_time": "0:53:06", "remaining_time": "1 day, 3:39:54", "throughput": 4554.85, "total_tokens": 14512672}
{"current_steps": 1245, "total_steps": 40000, "loss": 0.8865, "lr": 4.9880770141532304e-05, "epoch": 0.3188016132129825, "percentage": 3.11, "elapsed_time": "0:53:13", "remaining_time": "1 day, 3:36:58", "throughput": 4562.16, "total_tokens": 14570688}
{"current_steps": 1250, "total_steps": 40000, "loss": 0.9601, "lr": 4.987981054627472e-05, "epoch": 0.3200819409768901, "percentage": 3.12, "elapsed_time": "0:53:21", "remaining_time": "1 day, 3:34:05", "throughput": 4569.65, "total_tokens": 14629600}
{"current_steps": 1255, "total_steps": 40000, "loss": 0.9014, "lr": 4.987884711423769e-05, "epoch": 0.32136226874079765, "percentage": 3.14, "elapsed_time": "0:53:29", "remaining_time": "1 day, 3:31:12", "throughput": 4577.29, "total_tokens": 14688896}
{"current_steps": 1260, "total_steps": 40000, "loss": 0.8654, "lr": 4.9877879845569784e-05, "epoch": 0.3226425965047052, "percentage": 3.15, "elapsed_time": "0:53:36", "remaining_time": "1 day, 3:28:22", "throughput": 4584.46, "total_tokens": 14747168}
{"current_steps": 1265, "total_steps": 40000, "loss": 0.9202, "lr": 4.9876908740420175e-05, "epoch": 0.32392292426861274, "percentage": 3.16, "elapsed_time": "0:53:44", "remaining_time": "1 day, 3:25:32", "throughput": 4591.71, "total_tokens": 14805440}
{"current_steps": 1270, "total_steps": 40000, "loss": 0.8744, "lr": 4.987593379893861e-05, "epoch": 0.3252032520325203, "percentage": 3.17, "elapsed_time": "0:53:52", "remaining_time": "1 day, 3:22:44", "throughput": 4598.52, "total_tokens": 14862624}
{"current_steps": 1275, "total_steps": 40000, "loss": 0.9169, "lr": 4.987495502127545e-05, "epoch": 0.3264835797964279, "percentage": 3.19, "elapsed_time": "0:53:59", "remaining_time": "1 day, 3:19:57", "throughput": 4606.06, "total_tokens": 14922208}
{"current_steps": 1280, "total_steps": 40000, "loss": 0.9327, "lr": 4.987397240758162e-05, "epoch": 0.32776390756033547, "percentage": 3.2, "elapsed_time": "0:54:07", "remaining_time": "1 day, 3:17:11", "throughput": 4613.0, "total_tokens": 14979936}
{"current_steps": 1285, "total_steps": 40000, "loss": 0.9468, "lr": 4.9872985958008664e-05, "epoch": 0.329044235324243, "percentage": 3.21, "elapsed_time": "0:54:15", "remaining_time": "1 day, 3:14:28", "throughput": 4619.93, "total_tokens": 15037984}
{"current_steps": 1290, "total_steps": 40000, "loss": 0.9031, "lr": 4.987199567270871e-05, "epoch": 0.33032456308815056, "percentage": 3.23, "elapsed_time": "0:54:22", "remaining_time": "1 day, 3:11:44", "throughput": 4626.93, "total_tokens": 15096032}
{"current_steps": 1295, "total_steps": 40000, "loss": 0.9285, "lr": 4.9871001551834444e-05, "epoch": 0.33160489085205813, "percentage": 3.24, "elapsed_time": "0:54:30", "remaining_time": "1 day, 3:09:02", "throughput": 4633.9, "total_tokens": 15154176}
{"current_steps": 1300, "total_steps": 40000, "loss": 0.8802, "lr": 4.98700035955392e-05, "epoch": 0.3328852186159657, "percentage": 3.25, "elapsed_time": "0:54:37", "remaining_time": "1 day, 3:06:21", "throughput": 4640.94, "total_tokens": 15212736}
{"current_steps": 1305, "total_steps": 40000, "loss": 0.9161, "lr": 4.986900180397686e-05, "epoch": 0.3341655463798732, "percentage": 3.26, "elapsed_time": "0:54:45", "remaining_time": "1 day, 3:03:44", "throughput": 4647.55, "total_tokens": 15270368}
{"current_steps": 1310, "total_steps": 40000, "loss": 0.8857, "lr": 4.9867996177301926e-05, "epoch": 0.3354458741437808, "percentage": 3.28, "elapsed_time": "0:54:53", "remaining_time": "1 day, 3:01:04", "throughput": 4654.67, "total_tokens": 15329152}
{"current_steps": 1315, "total_steps": 40000, "loss": 0.9706, "lr": 4.9866986715669464e-05, "epoch": 0.33672620190768837, "percentage": 3.29, "elapsed_time": "0:55:00", "remaining_time": "1 day, 2:58:27", "throughput": 4661.84, "total_tokens": 15388416}
{"current_steps": 1320, "total_steps": 40000, "loss": 0.8366, "lr": 4.9865973419235155e-05, "epoch": 0.33800652967159595, "percentage": 3.3, "elapsed_time": "0:55:08", "remaining_time": "1 day, 2:55:50", "throughput": 4669.29, "total_tokens": 15448608}
{"current_steps": 1325, "total_steps": 40000, "loss": 0.8911, "lr": 4.986495628815526e-05, "epoch": 0.33928685743550346, "percentage": 3.31, "elapsed_time": "0:55:16", "remaining_time": "1 day, 2:53:16", "throughput": 4676.23, "total_tokens": 15507424}
{"current_steps": 1330, "total_steps": 40000, "loss": 0.844, "lr": 4.986393532258663e-05, "epoch": 0.34056718519941104, "percentage": 3.33, "elapsed_time": "0:55:23", "remaining_time": "1 day, 2:50:42", "throughput": 4683.01, "total_tokens": 15565760}
{"current_steps": 1335, "total_steps": 40000, "loss": 1.0101, "lr": 4.986291052268671e-05, "epoch": 0.3418475129633186, "percentage": 3.34, "elapsed_time": "0:55:31", "remaining_time": "1 day, 2:48:10", "throughput": 4689.58, "total_tokens": 15623648}
{"current_steps": 1340, "total_steps": 40000, "loss": 0.9409, "lr": 4.986188188861355e-05, "epoch": 0.3431278407272262, "percentage": 3.35, "elapsed_time": "0:55:39", "remaining_time": "1 day, 2:45:38", "throughput": 4696.73, "total_tokens": 15683296}
{"current_steps": 1345, "total_steps": 40000, "loss": 0.8614, "lr": 4.9860849420525766e-05, "epoch": 0.3444081684911337, "percentage": 3.36, "elapsed_time": "0:55:46", "remaining_time": "1 day, 2:43:08", "throughput": 4703.44, "total_tokens": 15741920}
{"current_steps": 1350, "total_steps": 40000, "loss": 0.83, "lr": 4.9859813118582575e-05, "epoch": 0.3456884962550413, "percentage": 3.38, "elapsed_time": "0:55:54", "remaining_time": "1 day, 2:40:38", "throughput": 4709.68, "total_tokens": 15798656}
{"current_steps": 1355, "total_steps": 40000, "loss": 0.9509, "lr": 4.98587729829438e-05, "epoch": 0.34696882401894885, "percentage": 3.39, "elapsed_time": "0:56:02", "remaining_time": "1 day, 2:38:08", "throughput": 4716.1, "total_tokens": 15856128}
{"current_steps": 1360, "total_steps": 40000, "loss": 0.8927, "lr": 4.985772901376983e-05, "epoch": 0.3482491517828564, "percentage": 3.4, "elapsed_time": "0:56:09", "remaining_time": "1 day, 2:35:40", "throughput": 4722.78, "total_tokens": 15914656}
{"current_steps": 1365, "total_steps": 40000, "loss": 0.8422, "lr": 4.9856681211221666e-05, "epoch": 0.349529479546764, "percentage": 3.41, "elapsed_time": "0:56:17", "remaining_time": "1 day, 2:33:13", "throughput": 4729.4, "total_tokens": 15973024}
{"current_steps": 1370, "total_steps": 40000, "loss": 0.8509, "lr": 4.985562957546089e-05, "epoch": 0.3508098073106715, "percentage": 3.43, "elapsed_time": "0:56:25", "remaining_time": "1 day, 2:30:48", "throughput": 4736.0, "total_tokens": 16031616}
{"current_steps": 1375, "total_steps": 40000, "loss": 0.9065, "lr": 4.9854574106649686e-05, "epoch": 0.3520901350745791, "percentage": 3.44, "elapsed_time": "0:56:32", "remaining_time": "1 day, 2:28:25", "throughput": 4742.4, "total_tokens": 16089728}
{"current_steps": 1380, "total_steps": 40000, "loss": 0.8898, "lr": 4.985351480495081e-05, "epoch": 0.35337046283848667, "percentage": 3.45, "elapsed_time": "0:56:40", "remaining_time": "1 day, 2:26:01", "throughput": 4748.61, "total_tokens": 16147136}
{"current_steps": 1385, "total_steps": 40000, "loss": 0.9014, "lr": 4.985245167052762e-05, "epoch": 0.35465079060239424, "percentage": 3.46, "elapsed_time": "0:56:48", "remaining_time": "1 day, 2:23:39", "throughput": 4754.93, "total_tokens": 16205056}
{"current_steps": 1390, "total_steps": 40000, "loss": 0.8009, "lr": 4.9851384703544066e-05, "epoch": 0.35593111836630176, "percentage": 3.48, "elapsed_time": "0:56:55", "remaining_time": "1 day, 2:21:17", "throughput": 4761.67, "total_tokens": 16264416}
{"current_steps": 1395, "total_steps": 40000, "loss": 0.8737, "lr": 4.985031390416469e-05, "epoch": 0.35721144613020933, "percentage": 3.49, "elapsed_time": "0:57:03", "remaining_time": "1 day, 2:18:56", "throughput": 4767.92, "total_tokens": 16322176}
{"current_steps": 1400, "total_steps": 40000, "loss": 0.9142, "lr": 4.984923927255461e-05, "epoch": 0.3584917738941169, "percentage": 3.5, "elapsed_time": "0:57:10", "remaining_time": "1 day, 2:16:36", "throughput": 4773.97, "total_tokens": 16379264}
{"current_steps": 1400, "total_steps": 40000, "eval_loss": 0.8958274722099304, "epoch": 0.3584917738941169, "percentage": 3.5, "elapsed_time": "1:00:43", "remaining_time": "1 day, 3:54:03", "throughput": 4496.06, "total_tokens": 16379264}
{"current_steps": 1405, "total_steps": 40000, "loss": 0.8793, "lr": 4.984816080887958e-05, "epoch": 0.3597721016580245, "percentage": 3.51, "elapsed_time": "1:00:52", "remaining_time": "1 day, 3:52:24", "throughput": 4499.72, "total_tokens": 16437120}
{"current_steps": 1410, "total_steps": 40000, "loss": 0.8717, "lr": 4.9847078513305875e-05, "epoch": 0.361052429421932, "percentage": 3.52, "elapsed_time": "1:01:00", "remaining_time": "1 day, 3:49:47", "throughput": 4506.2, "total_tokens": 16495552}
{"current_steps": 1415, "total_steps": 40000, "loss": 0.9231, "lr": 4.984599238600043e-05, "epoch": 0.36233275718583957, "percentage": 3.54, "elapsed_time": "1:01:08", "remaining_time": "1 day, 3:47:09", "throughput": 4512.58, "total_tokens": 16553472}
{"current_steps": 1420, "total_steps": 40000, "loss": 0.9, "lr": 4.9844902427130716e-05, "epoch": 0.36361308494974715, "percentage": 3.55, "elapsed_time": "1:01:15", "remaining_time": "1 day, 3:44:30", "throughput": 4519.31, "total_tokens": 16612448}
{"current_steps": 1425, "total_steps": 40000, "loss": 0.9719, "lr": 4.984380863686482e-05, "epoch": 0.3648934127136547, "percentage": 3.56, "elapsed_time": "1:01:23", "remaining_time": "1 day, 3:41:53", "throughput": 4525.62, "total_tokens": 16670240}
{"current_steps": 1430, "total_steps": 40000, "loss": 0.8205, "lr": 4.984271101537143e-05, "epoch": 0.36617374047756224, "percentage": 3.57, "elapsed_time": "1:01:31", "remaining_time": "1 day, 3:39:18", "throughput": 4532.18, "total_tokens": 16729056}
{"current_steps": 1435, "total_steps": 40000, "loss": 0.9077, "lr": 4.9841609562819816e-05, "epoch": 0.3674540682414698, "percentage": 3.59, "elapsed_time": "1:01:38", "remaining_time": "1 day, 3:36:43", "throughput": 4538.65, "total_tokens": 16787616}
{"current_steps": 1440, "total_steps": 40000, "loss": 0.8699, "lr": 4.984050427937983e-05, "epoch": 0.3687343960053774, "percentage": 3.6, "elapsed_time": "1:01:46", "remaining_time": "1 day, 3:34:10", "throughput": 4544.7, "total_tokens": 16844704}
{"current_steps": 1445, "total_steps": 40000, "loss": 0.888, "lr": 4.983939516522191e-05, "epoch": 0.37001472376928496, "percentage": 3.61, "elapsed_time": "1:01:54", "remaining_time": "1 day, 3:31:38", "throughput": 4550.64, "total_tokens": 16901504}
{"current_steps": 1450, "total_steps": 40000, "loss": 0.8535, "lr": 4.983828222051711e-05, "epoch": 0.3712950515331925, "percentage": 3.62, "elapsed_time": "1:02:01", "remaining_time": "1 day, 3:29:07", "throughput": 4557.14, "total_tokens": 16960576}
{"current_steps": 1455, "total_steps": 40000, "loss": 0.7816, "lr": 4.983716544543705e-05, "epoch": 0.37257537929710005, "percentage": 3.64, "elapsed_time": "1:02:09", "remaining_time": "1 day, 3:26:36", "throughput": 4563.14, "total_tokens": 17017728}
{"current_steps": 1460, "total_steps": 40000, "loss": 0.8958, "lr": 4.983604484015395e-05, "epoch": 0.3738557070610076, "percentage": 3.65, "elapsed_time": "1:02:17", "remaining_time": "1 day, 3:24:10", "throughput": 4569.3, "total_tokens": 17076096}
{"current_steps": 1465, "total_steps": 40000, "loss": 0.9166, "lr": 4.983492040484064e-05, "epoch": 0.3751360348249152, "percentage": 3.66, "elapsed_time": "1:02:24", "remaining_time": "1 day, 3:21:43", "throughput": 4575.36, "total_tokens": 17133952}
{"current_steps": 1470, "total_steps": 40000, "loss": 0.8786, "lr": 4.98337921396705e-05, "epoch": 0.3764163625888227, "percentage": 3.67, "elapsed_time": "1:02:32", "remaining_time": "1 day, 3:19:14", "throughput": 4582.03, "total_tokens": 17193792}
{"current_steps": 1475, "total_steps": 40000, "loss": 0.8477, "lr": 4.983266004481753e-05, "epoch": 0.3776966903527303, "percentage": 3.69, "elapsed_time": "1:02:40", "remaining_time": "1 day, 3:16:48", "throughput": 4588.13, "total_tokens": 17251776}
{"current_steps": 1480, "total_steps": 40000, "loss": 0.8394, "lr": 4.9831524120456316e-05, "epoch": 0.37897701811663786, "percentage": 3.7, "elapsed_time": "1:02:47", "remaining_time": "1 day, 3:14:25", "throughput": 4594.14, "total_tokens": 17309888}
{"current_steps": 1485, "total_steps": 40000, "loss": 0.9224, "lr": 4.9830384366762026e-05, "epoch": 0.38025734588054544, "percentage": 3.71, "elapsed_time": "1:02:55", "remaining_time": "1 day, 3:12:01", "throughput": 4600.13, "total_tokens": 17367712}
{"current_steps": 1490, "total_steps": 40000, "loss": 0.8969, "lr": 4.9829240783910436e-05, "epoch": 0.38153767364445296, "percentage": 3.72, "elapsed_time": "1:03:03", "remaining_time": "1 day, 3:09:36", "throughput": 4606.36, "total_tokens": 17426272}
{"current_steps": 1495, "total_steps": 40000, "loss": 0.8898, "lr": 4.982809337207789e-05, "epoch": 0.38281800140836053, "percentage": 3.74, "elapsed_time": "1:03:10", "remaining_time": "1 day, 3:07:14", "throughput": 4612.37, "total_tokens": 17484448}
{"current_steps": 1500, "total_steps": 40000, "loss": 0.8591, "lr": 4.9826942131441337e-05, "epoch": 0.3840983291722681, "percentage": 3.75, "elapsed_time": "1:03:18", "remaining_time": "1 day, 3:04:52", "throughput": 4618.15, "total_tokens": 17541696}
{"current_steps": 1505, "total_steps": 40000, "loss": 0.8637, "lr": 4.9825787062178315e-05, "epoch": 0.3853786569361757, "percentage": 3.76, "elapsed_time": "1:03:26", "remaining_time": "1 day, 3:02:31", "throughput": 4624.09, "total_tokens": 17599584}
{"current_steps": 1510, "total_steps": 40000, "loss": 0.8675, "lr": 4.9824628164466945e-05, "epoch": 0.3866589847000832, "percentage": 3.77, "elapsed_time": "1:03:33", "remaining_time": "1 day, 3:00:10", "throughput": 4630.23, "total_tokens": 17658176}
{"current_steps": 1515, "total_steps": 40000, "loss": 0.8915, "lr": 4.982346543848595e-05, "epoch": 0.38793931246399077, "percentage": 3.79, "elapsed_time": "1:03:41", "remaining_time": "1 day, 2:57:51", "throughput": 4635.93, "total_tokens": 17715296}
{"current_steps": 1520, "total_steps": 40000, "loss": 0.8217, "lr": 4.9822298884414626e-05, "epoch": 0.38921964022789834, "percentage": 3.8, "elapsed_time": "1:03:48", "remaining_time": "1 day, 2:55:32", "throughput": 4642.33, "total_tokens": 17775264}
{"current_steps": 1525, "total_steps": 40000, "loss": 0.963, "lr": 4.982112850243288e-05, "epoch": 0.3904999679918059, "percentage": 3.81, "elapsed_time": "1:03:57", "remaining_time": "1 day, 2:53:33", "throughput": 4649.12, "total_tokens": 17840064}
{"current_steps": 1530, "total_steps": 40000, "loss": 0.8541, "lr": 4.98199542927212e-05, "epoch": 0.39178029575571344, "percentage": 3.82, "elapsed_time": "1:04:05", "remaining_time": "1 day, 2:51:18", "throughput": 4655.03, "total_tokens": 17898688}
{"current_steps": 1535, "total_steps": 40000, "loss": 0.8285, "lr": 4.981877625546066e-05, "epoch": 0.393060623519621, "percentage": 3.84, "elapsed_time": "1:04:12", "remaining_time": "1 day, 2:49:04", "throughput": 4660.78, "total_tokens": 17956736}
{"current_steps": 1540, "total_steps": 40000, "loss": 0.8406, "lr": 4.981759439083293e-05, "epoch": 0.3943409512835286, "percentage": 3.85, "elapsed_time": "1:04:20", "remaining_time": "1 day, 2:46:50", "throughput": 4666.63, "total_tokens": 18015104}
{"current_steps": 1545, "total_steps": 40000, "loss": 0.934, "lr": 4.981640869902027e-05, "epoch": 0.39562127904743616, "percentage": 3.86, "elapsed_time": "1:04:28", "remaining_time": "1 day, 2:44:35", "throughput": 4672.55, "total_tokens": 18073536}
{"current_steps": 1550, "total_steps": 40000, "loss": 0.879, "lr": 4.9815219180205517e-05, "epoch": 0.3969016068113437, "percentage": 3.88, "elapsed_time": "1:04:35", "remaining_time": "1 day, 2:42:22", "throughput": 4678.42, "total_tokens": 18132224}
{"current_steps": 1555, "total_steps": 40000, "loss": 0.8093, "lr": 4.9814025834572126e-05, "epoch": 0.39818193457525125, "percentage": 3.89, "elapsed_time": "1:04:43", "remaining_time": "1 day, 2:40:10", "throughput": 4684.02, "total_tokens": 18189888}
{"current_steps": 1560, "total_steps": 40000, "loss": 0.8426, "lr": 4.981282866230411e-05, "epoch": 0.3994622623391588, "percentage": 3.9, "elapsed_time": "1:04:51", "remaining_time": "1 day, 2:37:59", "throughput": 4689.72, "total_tokens": 18247840}
{"current_steps": 1565, "total_steps": 40000, "loss": 0.8068, "lr": 4.981162766358611e-05, "epoch": 0.4007425901030664, "percentage": 3.91, "elapsed_time": "1:04:58", "remaining_time": "1 day, 2:35:47", "throughput": 4695.56, "total_tokens": 18306432}
{"current_steps": 1570, "total_steps": 40000, "loss": 0.8499, "lr": 4.9810422838603316e-05, "epoch": 0.402022917866974, "percentage": 3.92, "elapsed_time": "1:05:06", "remaining_time": "1 day, 2:33:40", "throughput": 4700.83, "total_tokens": 18363392}
{"current_steps": 1575, "total_steps": 40000, "loss": 0.8005, "lr": 4.9809214187541533e-05, "epoch": 0.4033032456308815, "percentage": 3.94, "elapsed_time": "1:05:14", "remaining_time": "1 day, 2:31:29", "throughput": 4706.02, "total_tokens": 18419360}
{"current_steps": 1580, "total_steps": 40000, "loss": 0.8697, "lr": 4.980800171058715e-05, "epoch": 0.40458357339478906, "percentage": 3.95, "elapsed_time": "1:05:21", "remaining_time": "1 day, 2:29:19", "throughput": 4711.9, "total_tokens": 18478208}
{"current_steps": 1585, "total_steps": 40000, "loss": 0.8655, "lr": 4.980678540792715e-05, "epoch": 0.40586390115869664, "percentage": 3.96, "elapsed_time": "1:05:29", "remaining_time": "1 day, 2:27:14", "throughput": 4717.26, "total_tokens": 18535808}
{"current_steps": 1590, "total_steps": 40000, "loss": 0.8607, "lr": 4.980556527974909e-05, "epoch": 0.4071442289226042, "percentage": 3.98, "elapsed_time": "1:05:37", "remaining_time": "1 day, 2:25:09", "throughput": 4722.88, "total_tokens": 18594368}
{"current_steps": 1595, "total_steps": 40000, "loss": 0.812, "lr": 4.980434132624114e-05, "epoch": 0.40842455668651173, "percentage": 3.99, "elapsed_time": "1:05:44", "remaining_time": "1 day, 2:23:03", "throughput": 4728.4, "total_tokens": 18652416}
{"current_steps": 1600, "total_steps": 40000, "loss": 0.8039, "lr": 4.980311354759205e-05, "epoch": 0.4097048844504193, "percentage": 4.0, "elapsed_time": "1:05:52", "remaining_time": "1 day, 2:20:57", "throughput": 4733.91, "total_tokens": 18710208}
{"current_steps": 1600, "total_steps": 40000, "eval_loss": 0.8767469525337219, "epoch": 0.4097048844504193, "percentage": 4.0, "elapsed_time": "1:09:24", "remaining_time": "1 day, 3:45:58", "throughput": 4492.29, "total_tokens": 18710208}
{"current_steps": 1605, "total_steps": 40000, "loss": 0.7968, "lr": 4.980188194399116e-05, "epoch": 0.4109852122143269, "percentage": 4.01, "elapsed_time": "1:09:35", "remaining_time": "1 day, 3:44:44", "throughput": 4494.94, "total_tokens": 18768192}
{"current_steps": 1610, "total_steps": 40000, "loss": 0.8309, "lr": 4.9800646515628384e-05, "epoch": 0.41226553997823445, "percentage": 4.03, "elapsed_time": "1:09:43", "remaining_time": "1 day, 3:42:23", "throughput": 4500.51, "total_tokens": 18825760}
{"current_steps": 1615, "total_steps": 40000, "loss": 0.8119, "lr": 4.979940726269426e-05, "epoch": 0.41354586774214197, "percentage": 4.04, "elapsed_time": "1:09:50", "remaining_time": "1 day, 3:40:03", "throughput": 4506.11, "total_tokens": 18883680}
{"current_steps": 1620, "total_steps": 40000, "loss": 0.8187, "lr": 4.979816418537988e-05, "epoch": 0.41482619550604954, "percentage": 4.05, "elapsed_time": "1:09:58", "remaining_time": "1 day, 3:37:43", "throughput": 4511.92, "total_tokens": 18942368}
{"current_steps": 1625, "total_steps": 40000, "loss": 0.8702, "lr": 4.979691728387696e-05, "epoch": 0.4161065232699571, "percentage": 4.06, "elapsed_time": "1:10:05", "remaining_time": "1 day, 3:35:24", "throughput": 4517.57, "total_tokens": 19000480}
{"current_steps": 1630, "total_steps": 40000, "loss": 0.8369, "lr": 4.979566655837776e-05, "epoch": 0.4173868510338647, "percentage": 4.08, "elapsed_time": "1:10:13", "remaining_time": "1 day, 3:33:06", "throughput": 4523.61, "total_tokens": 19060480}
{"current_steps": 1635, "total_steps": 40000, "loss": 0.9098, "lr": 4.9794412009075184e-05, "epoch": 0.4186671787977722, "percentage": 4.09, "elapsed_time": "1:10:21", "remaining_time": "1 day, 3:30:52", "throughput": 4529.3, "total_tokens": 19119648}
{"current_steps": 1640, "total_steps": 40000, "loss": 0.9181, "lr": 4.979315363616269e-05, "epoch": 0.4199475065616798, "percentage": 4.1, "elapsed_time": "1:10:29", "remaining_time": "1 day, 3:28:37", "throughput": 4534.8, "total_tokens": 19177696}
{"current_steps": 1645, "total_steps": 40000, "loss": 0.9493, "lr": 4.979189143983434e-05, "epoch": 0.42122783432558736, "percentage": 4.11, "elapsed_time": "1:10:36", "remaining_time": "1 day, 3:26:21", "throughput": 4540.12, "total_tokens": 19234720}
{"current_steps": 1650, "total_steps": 40000, "loss": 0.8796, "lr": 4.979062542028478e-05, "epoch": 0.42250816208949493, "percentage": 4.12, "elapsed_time": "1:10:44", "remaining_time": "1 day, 3:24:06", "throughput": 4545.56, "total_tokens": 19292448}
{"current_steps": 1655, "total_steps": 40000, "loss": 0.8681, "lr": 4.978935557770923e-05, "epoch": 0.42378848985340245, "percentage": 4.14, "elapsed_time": "1:10:51", "remaining_time": "1 day, 3:21:53", "throughput": 4551.52, "total_tokens": 19352608}
{"current_steps": 1660, "total_steps": 40000, "loss": 0.8936, "lr": 4.978808191230353e-05, "epoch": 0.42506881761731, "percentage": 4.15, "elapsed_time": "1:10:59", "remaining_time": "1 day, 3:19:39", "throughput": 4557.35, "total_tokens": 19412064}
{"current_steps": 1665, "total_steps": 40000, "loss": 0.9104, "lr": 4.9786804424264085e-05, "epoch": 0.4263491453812176, "percentage": 4.16, "elapsed_time": "1:11:07", "remaining_time": "1 day, 3:17:27", "throughput": 4562.82, "total_tokens": 19470304}
{"current_steps": 1670, "total_steps": 40000, "loss": 0.8059, "lr": 4.978552311378792e-05, "epoch": 0.42762947314512517, "percentage": 4.17, "elapsed_time": "1:11:14", "remaining_time": "1 day, 3:15:15", "throughput": 4568.04, "total_tokens": 19527456}
{"current_steps": 1675, "total_steps": 40000, "loss": 0.8133, "lr": 4.978423798107261e-05, "epoch": 0.4289098009090327, "percentage": 4.19, "elapsed_time": "1:11:22", "remaining_time": "1 day, 3:13:06", "throughput": 4573.34, "total_tokens": 19585312}
{"current_steps": 1680, "total_steps": 40000, "loss": 0.8056, "lr": 4.978294902631635e-05, "epoch": 0.43019012867294026, "percentage": 4.2, "elapsed_time": "1:11:30", "remaining_time": "1 day, 3:10:55", "throughput": 4579.26, "total_tokens": 19645632}
{"current_steps": 1685, "total_steps": 40000, "loss": 0.9442, "lr": 4.9781656249717914e-05, "epoch": 0.43147045643684784, "percentage": 4.21, "elapsed_time": "1:11:37", "remaining_time": "1 day, 3:08:47", "throughput": 4584.65, "total_tokens": 19704032}
{"current_steps": 1690, "total_steps": 40000, "loss": 0.7557, "lr": 4.9780359651476645e-05, "epoch": 0.4327507842007554, "percentage": 4.23, "elapsed_time": "1:11:45", "remaining_time": "1 day, 3:06:41", "throughput": 4590.07, "total_tokens": 19762816}
{"current_steps": 1695, "total_steps": 40000, "loss": 0.9129, "lr": 4.977905923179251e-05, "epoch": 0.43403111196466293, "percentage": 4.24, "elapsed_time": "1:11:53", "remaining_time": "1 day, 3:04:32", "throughput": 4595.72, "total_tokens": 19822112}
{"current_steps": 1700, "total_steps": 40000, "loss": 0.9153, "lr": 4.977775499086606e-05, "epoch": 0.4353114397285705, "percentage": 4.25, "elapsed_time": "1:12:00", "remaining_time": "1 day, 3:02:26", "throughput": 4600.83, "total_tokens": 19879456}
{"current_steps": 1705, "total_steps": 40000, "loss": 0.8735, "lr": 4.97764469288984e-05, "epoch": 0.4365917674924781, "percentage": 4.26, "elapsed_time": "1:12:08", "remaining_time": "1 day, 3:00:20", "throughput": 4606.02, "total_tokens": 19937248}
{"current_steps": 1710, "total_steps": 40000, "loss": 0.8348, "lr": 4.977513504609127e-05, "epoch": 0.43787209525638565, "percentage": 4.28, "elapsed_time": "1:12:16", "remaining_time": "1 day, 2:58:15", "throughput": 4611.72, "total_tokens": 19997280}
{"current_steps": 1715, "total_steps": 40000, "loss": 0.8649, "lr": 4.9773819342646965e-05, "epoch": 0.43915242302029317, "percentage": 4.29, "elapsed_time": "1:12:23", "remaining_time": "1 day, 2:56:10", "throughput": 4617.34, "total_tokens": 20056960}
{"current_steps": 1720, "total_steps": 40000, "loss": 0.8862, "lr": 4.97724998187684e-05, "epoch": 0.44043275078420074, "percentage": 4.3, "elapsed_time": "1:12:31", "remaining_time": "1 day, 2:54:05", "throughput": 4622.54, "total_tokens": 20114848}
{"current_steps": 1725, "total_steps": 40000, "loss": 0.8387, "lr": 4.9771176474659045e-05, "epoch": 0.4417130785481083, "percentage": 4.31, "elapsed_time": "1:12:39", "remaining_time": "1 day, 2:52:03", "throughput": 4627.73, "total_tokens": 20173088}
{"current_steps": 1730, "total_steps": 40000, "loss": 0.8766, "lr": 4.976984931052299e-05, "epoch": 0.4429934063120159, "percentage": 4.32, "elapsed_time": "1:12:46", "remaining_time": "1 day, 2:50:00", "throughput": 4633.26, "total_tokens": 20232640}
{"current_steps": 1735, "total_steps": 40000, "loss": 0.8449, "lr": 4.976851832656489e-05, "epoch": 0.4442737340759234, "percentage": 4.34, "elapsed_time": "1:12:54", "remaining_time": "1 day, 2:47:56", "throughput": 4638.44, "total_tokens": 20290432}
{"current_steps": 1740, "total_steps": 40000, "loss": 0.858, "lr": 4.9767183522990004e-05, "epoch": 0.445554061839831, "percentage": 4.35, "elapsed_time": "1:13:02", "remaining_time": "1 day, 2:45:55", "throughput": 4643.69, "total_tokens": 20348928}
{"current_steps": 1745, "total_steps": 40000, "loss": 0.8628, "lr": 4.9765844900004176e-05, "epoch": 0.44683438960373856, "percentage": 4.36, "elapsed_time": "1:13:09", "remaining_time": "1 day, 2:43:53", "throughput": 4649.16, "total_tokens": 20408416}
{"current_steps": 1750, "total_steps": 40000, "loss": 0.8317, "lr": 4.9764502457813834e-05, "epoch": 0.44811471736764613, "percentage": 4.38, "elapsed_time": "1:13:17", "remaining_time": "1 day, 2:41:54", "throughput": 4654.37, "total_tokens": 20467040}
{"current_steps": 1755, "total_steps": 40000, "loss": 0.8122, "lr": 4.9763156196626005e-05, "epoch": 0.4493950451315537, "percentage": 4.39, "elapsed_time": "1:13:25", "remaining_time": "1 day, 2:39:55", "throughput": 4659.48, "total_tokens": 20525280}
{"current_steps": 1760, "total_steps": 40000, "loss": 0.7844, "lr": 4.97618061166483e-05, "epoch": 0.4506753728954612, "percentage": 4.4, "elapsed_time": "1:13:32", "remaining_time": "1 day, 2:37:55", "throughput": 4664.59, "total_tokens": 20583360}
{"current_steps": 1765, "total_steps": 40000, "loss": 0.7901, "lr": 4.9760452218088915e-05, "epoch": 0.4519557006593688, "percentage": 4.41, "elapsed_time": "1:13:40", "remaining_time": "1 day, 2:35:57", "throughput": 4669.62, "total_tokens": 20641280}
{"current_steps": 1770, "total_steps": 40000, "loss": 0.9198, "lr": 4.975909450115663e-05, "epoch": 0.45323602842327637, "percentage": 4.42, "elapsed_time": "1:13:48", "remaining_time": "1 day, 2:33:59", "throughput": 4675.19, "total_tokens": 20701760}
{"current_steps": 1775, "total_steps": 40000, "loss": 0.8529, "lr": 4.975773296606084e-05, "epoch": 0.45451635618718395, "percentage": 4.44, "elapsed_time": "1:13:55", "remaining_time": "1 day, 2:32:03", "throughput": 4680.33, "total_tokens": 20760416}
{"current_steps": 1780, "total_steps": 40000, "loss": 0.8074, "lr": 4.97563676130115e-05, "epoch": 0.45579668395109146, "percentage": 4.45, "elapsed_time": "1:14:03", "remaining_time": "1 day, 2:30:07", "throughput": 4685.35, "total_tokens": 20818816}
{"current_steps": 1785, "total_steps": 40000, "loss": 0.9013, "lr": 4.9754998442219166e-05, "epoch": 0.45707701171499904, "percentage": 4.46, "elapsed_time": "1:14:11", "remaining_time": "1 day, 2:28:12", "throughput": 4690.28, "total_tokens": 20876672}
{"current_steps": 1790, "total_steps": 40000, "loss": 0.8983, "lr": 4.9753625453894984e-05, "epoch": 0.4583573394789066, "percentage": 4.47, "elapsed_time": "1:14:18", "remaining_time": "1 day, 2:26:18", "throughput": 4695.57, "total_tokens": 20936384}
{"current_steps": 1795, "total_steps": 40000, "loss": 0.8437, "lr": 4.975224864825068e-05, "epoch": 0.4596376672428142, "percentage": 4.49, "elapsed_time": "1:14:26", "remaining_time": "1 day, 2:24:22", "throughput": 4700.71, "total_tokens": 20995136}
{"current_steps": 1800, "total_steps": 40000, "loss": 0.9641, "lr": 4.9750868025498576e-05, "epoch": 0.4609179950067217, "percentage": 4.5, "elapsed_time": "1:14:34", "remaining_time": "1 day, 2:22:29", "throughput": 4705.8, "total_tokens": 21054016}
{"current_steps": 1800, "total_steps": 40000, "eval_loss": 0.8607687950134277, "epoch": 0.4609179950067217, "percentage": 4.5, "elapsed_time": "1:18:05", "remaining_time": "1 day, 3:37:26", "throughput": 4492.99, "total_tokens": 21054016}
{"current_steps": 1805, "total_steps": 40000, "loss": 0.8556, "lr": 4.974948358585158e-05, "epoch": 0.4621983227706293, "percentage": 4.51, "elapsed_time": "1:18:17", "remaining_time": "1 day, 3:36:36", "throughput": 4494.35, "total_tokens": 21111104}
{"current_steps": 1810, "total_steps": 40000, "loss": 0.8132, "lr": 4.9748095329523205e-05, "epoch": 0.46347865053453685, "percentage": 4.52, "elapsed_time": "1:18:24", "remaining_time": "1 day, 3:34:31", "throughput": 4499.3, "total_tokens": 21168800}
{"current_steps": 1815, "total_steps": 40000, "loss": 0.8261, "lr": 4.974670325672752e-05, "epoch": 0.4647589782984444, "percentage": 4.54, "elapsed_time": "1:18:32", "remaining_time": "1 day, 3:32:27", "throughput": 4504.29, "total_tokens": 21227200}
{"current_steps": 1820, "total_steps": 40000, "loss": 0.8416, "lr": 4.974530736767921e-05, "epoch": 0.46603930606235194, "percentage": 4.55, "elapsed_time": "1:18:40", "remaining_time": "1 day, 3:30:32", "throughput": 4510.65, "total_tokens": 21293856}
{"current_steps": 1825, "total_steps": 40000, "loss": 0.8371, "lr": 4.9743907662593524e-05, "epoch": 0.4673196338262595, "percentage": 4.56, "elapsed_time": "1:18:48", "remaining_time": "1 day, 3:28:29", "throughput": 4515.67, "total_tokens": 21352160}
{"current_steps": 1830, "total_steps": 40000, "loss": 0.9133, "lr": 4.974250414168633e-05, "epoch": 0.4685999615901671, "percentage": 4.58, "elapsed_time": "1:18:56", "remaining_time": "1 day, 3:26:25", "throughput": 4520.91, "total_tokens": 21411488}
{"current_steps": 1835, "total_steps": 40000, "loss": 0.7573, "lr": 4.974109680517407e-05, "epoch": 0.46988028935407467, "percentage": 4.59, "elapsed_time": "1:19:03", "remaining_time": "1 day, 3:24:23", "throughput": 4526.0, "total_tokens": 21470400}
{"current_steps": 1840, "total_steps": 40000, "loss": 0.7927, "lr": 4.973968565327376e-05, "epoch": 0.4711606171179822, "percentage": 4.6, "elapsed_time": "1:19:11", "remaining_time": "1 day, 3:22:20", "throughput": 4530.89, "total_tokens": 21528288}
{"current_steps": 1845, "total_steps": 40000, "loss": 0.8671, "lr": 4.973827068620303e-05, "epoch": 0.47244094488188976, "percentage": 4.61, "elapsed_time": "1:19:19", "remaining_time": "1 day, 3:20:19", "throughput": 4536.08, "total_tokens": 21587744}
{"current_steps": 1850, "total_steps": 40000, "loss": 0.8424, "lr": 4.973685190418008e-05, "epoch": 0.47372127264579733, "percentage": 4.62, "elapsed_time": "1:19:26", "remaining_time": "1 day, 3:18:17", "throughput": 4541.0, "total_tokens": 21645760}
{"current_steps": 1855, "total_steps": 40000, "loss": 0.7887, "lr": 4.97354293074237e-05, "epoch": 0.4750016004097049, "percentage": 4.64, "elapsed_time": "1:19:34", "remaining_time": "1 day, 3:16:19", "throughput": 4545.61, "total_tokens": 21702880}
{"current_steps": 1860, "total_steps": 40000, "loss": 0.7679, "lr": 4.9734002896153276e-05, "epoch": 0.4762819281736124, "percentage": 4.65, "elapsed_time": "1:19:42", "remaining_time": "1 day, 3:14:27", "throughput": 4550.13, "total_tokens": 21761152}
{"current_steps": 1865, "total_steps": 40000, "loss": 0.8619, "lr": 4.973257267058877e-05, "epoch": 0.47756225593752, "percentage": 4.66, "elapsed_time": "1:19:50", "remaining_time": "1 day, 3:12:28", "throughput": 4554.73, "total_tokens": 21818080}
{"current_steps": 1870, "total_steps": 40000, "loss": 0.8723, "lr": 4.973113863095076e-05, "epoch": 0.47884258370142757, "percentage": 4.67, "elapsed_time": "1:19:57", "remaining_time": "1 day, 3:10:30", "throughput": 4559.64, "total_tokens": 21876576}
{"current_steps": 1875, "total_steps": 40000, "loss": 0.8326, "lr": 4.9729700777460384e-05, "epoch": 0.48012291146533514, "percentage": 4.69, "elapsed_time": "1:20:05", "remaining_time": "1 day, 3:08:31", "throughput": 4564.36, "total_tokens": 21933984}
{"current_steps": 1880, "total_steps": 40000, "loss": 0.8259, "lr": 4.972825911033937e-05, "epoch": 0.48140323922924266, "percentage": 4.7, "elapsed_time": "1:20:13", "remaining_time": "1 day, 3:06:34", "throughput": 4568.94, "total_tokens": 21990976}
{"current_steps": 1885, "total_steps": 40000, "loss": 0.9173, "lr": 4.9726813629810056e-05, "epoch": 0.48268356699315024, "percentage": 4.71, "elapsed_time": "1:20:20", "remaining_time": "1 day, 3:04:38", "throughput": 4573.68, "total_tokens": 22048992}
{"current_steps": 1890, "total_steps": 40000, "loss": 0.8337, "lr": 4.9725364336095326e-05, "epoch": 0.4839638947570578, "percentage": 4.72, "elapsed_time": "1:20:28", "remaining_time": "1 day, 3:02:42", "throughput": 4578.45, "total_tokens": 22107136}
{"current_steps": 1895, "total_steps": 40000, "loss": 0.8633, "lr": 4.972391122941871e-05, "epoch": 0.4852442225209654, "percentage": 4.74, "elapsed_time": "1:20:36", "remaining_time": "1 day, 3:00:47", "throughput": 4583.68, "total_tokens": 22167584}
{"current_steps": 1900, "total_steps": 40000, "loss": 0.8815, "lr": 4.972245431000428e-05, "epoch": 0.4865245502848729, "percentage": 4.75, "elapsed_time": "1:20:43", "remaining_time": "1 day, 2:58:52", "throughput": 4588.33, "total_tokens": 22225408}
{"current_steps": 1905, "total_steps": 40000, "loss": 0.8738, "lr": 4.972099357807671e-05, "epoch": 0.4878048780487805, "percentage": 4.76, "elapsed_time": "1:20:51", "remaining_time": "1 day, 2:56:58", "throughput": 4593.14, "total_tokens": 22283872}
{"current_steps": 1910, "total_steps": 40000, "loss": 0.8426, "lr": 4.971952903386127e-05, "epoch": 0.48908520581268805, "percentage": 4.78, "elapsed_time": "1:20:59", "remaining_time": "1 day, 2:55:04", "throughput": 4597.82, "total_tokens": 22341920}
{"current_steps": 1915, "total_steps": 40000, "loss": 0.8801, "lr": 4.971806067758381e-05, "epoch": 0.4903655335765956, "percentage": 4.79, "elapsed_time": "1:21:06", "remaining_time": "1 day, 2:53:12", "throughput": 4602.71, "total_tokens": 22401184}
{"current_steps": 1920, "total_steps": 40000, "loss": 0.7453, "lr": 4.971658850947076e-05, "epoch": 0.49164586134050314, "percentage": 4.8, "elapsed_time": "1:21:14", "remaining_time": "1 day, 2:51:19", "throughput": 4607.34, "total_tokens": 22459040}
{"current_steps": 1925, "total_steps": 40000, "loss": 0.8202, "lr": 4.9715112529749165e-05, "epoch": 0.4929261891044107, "percentage": 4.81, "elapsed_time": "1:21:22", "remaining_time": "1 day, 2:49:28", "throughput": 4612.23, "total_tokens": 22518336}
{"current_steps": 1930, "total_steps": 40000, "loss": 0.8635, "lr": 4.9713632738646624e-05, "epoch": 0.4942065168683183, "percentage": 4.83, "elapsed_time": "1:21:30", "remaining_time": "1 day, 2:47:37", "throughput": 4617.05, "total_tokens": 22577440}
{"current_steps": 1935, "total_steps": 40000, "loss": 0.8979, "lr": 4.971214913639134e-05, "epoch": 0.49548684463222586, "percentage": 4.84, "elapsed_time": "1:21:37", "remaining_time": "1 day, 2:45:45", "throughput": 4621.57, "total_tokens": 22634752}
{"current_steps": 1940, "total_steps": 40000, "loss": 0.8239, "lr": 4.9710661723212104e-05, "epoch": 0.4967671723961334, "percentage": 4.85, "elapsed_time": "1:21:45", "remaining_time": "1 day, 2:43:54", "throughput": 4626.07, "total_tokens": 22692288}
{"current_steps": 1945, "total_steps": 40000, "loss": 0.9076, "lr": 4.9709170499338295e-05, "epoch": 0.49804750016004096, "percentage": 4.86, "elapsed_time": "1:21:52", "remaining_time": "1 day, 2:42:05", "throughput": 4630.97, "total_tokens": 22751904}
{"current_steps": 1950, "total_steps": 40000, "loss": 0.8442, "lr": 4.9707675464999895e-05, "epoch": 0.49932782792394853, "percentage": 4.88, "elapsed_time": "1:22:00", "remaining_time": "1 day, 2:40:15", "throughput": 4635.66, "total_tokens": 22810432}
{"current_steps": 1955, "total_steps": 40000, "loss": 0.8026, "lr": 4.970617662042743e-05, "epoch": 0.5006081556878561, "percentage": 4.89, "elapsed_time": "1:22:08", "remaining_time": "1 day, 2:38:26", "throughput": 4640.16, "total_tokens": 22868096}
{"current_steps": 1960, "total_steps": 40000, "loss": 0.8831, "lr": 4.970467396585206e-05, "epoch": 0.5018884834517636, "percentage": 4.9, "elapsed_time": "1:22:16", "remaining_time": "1 day, 2:36:39", "throughput": 4644.63, "total_tokens": 22926016}
{"current_steps": 1965, "total_steps": 40000, "loss": 0.8605, "lr": 4.97031675015055e-05, "epoch": 0.5031688112156713, "percentage": 4.91, "elapsed_time": "1:22:23", "remaining_time": "1 day, 2:34:51", "throughput": 4649.74, "total_tokens": 22986848}
{"current_steps": 1970, "total_steps": 40000, "loss": 0.8091, "lr": 4.9701657227620075e-05, "epoch": 0.5044491389795788, "percentage": 4.92, "elapsed_time": "1:22:31", "remaining_time": "1 day, 2:33:02", "throughput": 4654.23, "total_tokens": 23044544}
{"current_steps": 1975, "total_steps": 40000, "loss": 0.8057, "lr": 4.9700143144428685e-05, "epoch": 0.5057294667434863, "percentage": 4.94, "elapsed_time": "1:22:39", "remaining_time": "1 day, 2:31:16", "throughput": 4658.67, "total_tokens": 23102464}
{"current_steps": 1980, "total_steps": 40000, "loss": 0.7187, "lr": 4.969862525216482e-05, "epoch": 0.5070097945073939, "percentage": 4.95, "elapsed_time": "1:22:46", "remaining_time": "1 day, 2:29:30", "throughput": 4663.33, "total_tokens": 23161216}
{"current_steps": 1985, "total_steps": 40000, "loss": 0.8071, "lr": 4.9697103551062556e-05, "epoch": 0.5082901222713014, "percentage": 4.96, "elapsed_time": "1:22:54", "remaining_time": "1 day, 2:27:42", "throughput": 4667.84, "total_tokens": 23219104}
{"current_steps": 1990, "total_steps": 40000, "loss": 0.8223, "lr": 4.9695578041356565e-05, "epoch": 0.5095704500352091, "percentage": 4.98, "elapsed_time": "1:23:02", "remaining_time": "1 day, 2:25:58", "throughput": 4672.21, "total_tokens": 23277024}
{"current_steps": 1995, "total_steps": 40000, "loss": 0.8542, "lr": 4.969404872328209e-05, "epoch": 0.5108507777991166, "percentage": 4.99, "elapsed_time": "1:23:09", "remaining_time": "1 day, 2:24:12", "throughput": 4677.19, "total_tokens": 23337408}
{"current_steps": 2000, "total_steps": 40000, "loss": 0.8379, "lr": 4.969251559707498e-05, "epoch": 0.5121311055630241, "percentage": 5.0, "elapsed_time": "1:23:17", "remaining_time": "1 day, 2:22:28", "throughput": 4681.68, "total_tokens": 23395808}
{"current_steps": 2000, "total_steps": 40000, "eval_loss": 0.8482695817947388, "epoch": 0.5121311055630241, "percentage": 5.0, "elapsed_time": "1:26:49", "remaining_time": "1 day, 3:29:41", "throughput": 4490.94, "total_tokens": 23395808}
{"current_steps": 2005, "total_steps": 40000, "loss": 0.9527, "lr": 4.9690978662971674e-05, "epoch": 0.5134114333269317, "percentage": 5.01, "elapsed_time": "1:26:59", "remaining_time": "1 day, 3:28:37", "throughput": 4493.25, "total_tokens": 23454240}
{"current_steps": 2010, "total_steps": 40000, "loss": 0.8541, "lr": 4.968943792120916e-05, "epoch": 0.5146917610908393, "percentage": 5.03, "elapsed_time": "1:27:07", "remaining_time": "1 day, 3:26:42", "throughput": 4497.86, "total_tokens": 23512672}
{"current_steps": 2015, "total_steps": 40000, "loss": 0.8633, "lr": 4.9687893372025046e-05, "epoch": 0.5159720888547468, "percentage": 5.04, "elapsed_time": "1:27:15", "remaining_time": "1 day, 3:24:50", "throughput": 4502.43, "total_tokens": 23571392}
{"current_steps": 2020, "total_steps": 40000, "loss": 0.9557, "lr": 4.9686345015657535e-05, "epoch": 0.5172524166186544, "percentage": 5.05, "elapsed_time": "1:27:22", "remaining_time": "1 day, 3:22:57", "throughput": 4506.99, "total_tokens": 23629824}
{"current_steps": 2025, "total_steps": 40000, "loss": 0.8352, "lr": 4.968479285234538e-05, "epoch": 0.5185327443825619, "percentage": 5.06, "elapsed_time": "1:27:30", "remaining_time": "1 day, 3:21:05", "throughput": 4511.85, "total_tokens": 23689920}
{"current_steps": 2030, "total_steps": 40000, "loss": 0.8276, "lr": 4.9683236882327974e-05, "epoch": 0.5198130721464695, "percentage": 5.08, "elapsed_time": "1:27:38", "remaining_time": "1 day, 3:19:13", "throughput": 4516.52, "total_tokens": 23749184}
{"current_steps": 2035, "total_steps": 40000, "loss": 0.9339, "lr": 4.968167710584526e-05, "epoch": 0.5210933999103771, "percentage": 5.09, "elapsed_time": "1:27:45", "remaining_time": "1 day, 3:17:21", "throughput": 4521.02, "total_tokens": 23807424}
{"current_steps": 2040, "total_steps": 40000, "loss": 0.8121, "lr": 4.968011352313775e-05, "epoch": 0.5223737276742846, "percentage": 5.1, "elapsed_time": "1:27:53", "remaining_time": "1 day, 3:15:30", "throughput": 4525.52, "total_tokens": 23865920}
{"current_steps": 2045, "total_steps": 40000, "loss": 0.8088, "lr": 4.967854613444659e-05, "epoch": 0.5236540554381922, "percentage": 5.11, "elapsed_time": "1:28:01", "remaining_time": "1 day, 3:13:39", "throughput": 4529.88, "total_tokens": 23923488}
{"current_steps": 2050, "total_steps": 40000, "loss": 0.8478, "lr": 4.967697494001349e-05, "epoch": 0.5249343832020997, "percentage": 5.12, "elapsed_time": "1:28:08", "remaining_time": "1 day, 3:11:48", "throughput": 4534.38, "total_tokens": 23981824}
{"current_steps": 2055, "total_steps": 40000, "loss": 0.7955, "lr": 4.9675399940080736e-05, "epoch": 0.5262147109660072, "percentage": 5.14, "elapsed_time": "1:28:16", "remaining_time": "1 day, 3:10:00", "throughput": 4538.73, "total_tokens": 24039808}
{"current_steps": 2060, "total_steps": 40000, "loss": 0.9157, "lr": 4.9673821134891226e-05, "epoch": 0.5274950387299149, "percentage": 5.15, "elapsed_time": "1:28:24", "remaining_time": "1 day, 3:08:10", "throughput": 4543.34, "total_tokens": 24098944}
{"current_steps": 2065, "total_steps": 40000, "loss": 0.871, "lr": 4.967223852468842e-05, "epoch": 0.5287753664938224, "percentage": 5.16, "elapsed_time": "1:28:31", "remaining_time": "1 day, 3:06:22", "throughput": 4547.97, "total_tokens": 24158400}
{"current_steps": 2070, "total_steps": 40000, "loss": 0.8632, "lr": 4.967065210971639e-05, "epoch": 0.53005569425773, "percentage": 5.17, "elapsed_time": "1:28:39", "remaining_time": "1 day, 3:04:33", "throughput": 4552.42, "total_tokens": 24216736}
{"current_steps": 2075, "total_steps": 40000, "loss": 0.846, "lr": 4.966906189021977e-05, "epoch": 0.5313360220216375, "percentage": 5.19, "elapsed_time": "1:28:47", "remaining_time": "1 day, 3:02:46", "throughput": 4556.58, "total_tokens": 24273952}
{"current_steps": 2080, "total_steps": 40000, "loss": 0.8159, "lr": 4.966746786644379e-05, "epoch": 0.5326163497855451, "percentage": 5.2, "elapsed_time": "1:28:54", "remaining_time": "1 day, 3:00:57", "throughput": 4561.15, "total_tokens": 24332736}
{"current_steps": 2085, "total_steps": 40000, "loss": 0.8205, "lr": 4.966587003863429e-05, "epoch": 0.5338966775494527, "percentage": 5.21, "elapsed_time": "1:29:02", "remaining_time": "1 day, 2:59:10", "throughput": 4565.35, "total_tokens": 24390144}
{"current_steps": 2090, "total_steps": 40000, "loss": 0.8153, "lr": 4.966426840703765e-05, "epoch": 0.5351770053133602, "percentage": 5.22, "elapsed_time": "1:29:10", "remaining_time": "1 day, 2:57:23", "throughput": 4569.76, "total_tokens": 24448448}
{"current_steps": 2095, "total_steps": 40000, "loss": 0.7787, "lr": 4.9662662971900875e-05, "epoch": 0.5364573330772677, "percentage": 5.24, "elapsed_time": "1:29:17", "remaining_time": "1 day, 2:55:36", "throughput": 4573.89, "total_tokens": 24505280}
{"current_steps": 2100, "total_steps": 40000, "loss": 0.7865, "lr": 4.9661053733471534e-05, "epoch": 0.5377376608411754, "percentage": 5.25, "elapsed_time": "1:29:25", "remaining_time": "1 day, 2:53:52", "throughput": 4578.32, "total_tokens": 24564384}
{"current_steps": 2105, "total_steps": 40000, "loss": 0.78, "lr": 4.965944069199781e-05, "epoch": 0.5390179886050829, "percentage": 5.26, "elapsed_time": "1:29:33", "remaining_time": "1 day, 2:52:07", "throughput": 4582.52, "total_tokens": 24622080}
{"current_steps": 2110, "total_steps": 40000, "loss": 0.8497, "lr": 4.965782384772842e-05, "epoch": 0.5402983163689905, "percentage": 5.27, "elapsed_time": "1:29:40", "remaining_time": "1 day, 2:50:22", "throughput": 4587.09, "total_tokens": 24681536}
{"current_steps": 2115, "total_steps": 40000, "loss": 0.8523, "lr": 4.9656203200912734e-05, "epoch": 0.541578644132898, "percentage": 5.29, "elapsed_time": "1:29:48", "remaining_time": "1 day, 2:48:38", "throughput": 4591.39, "total_tokens": 24739936}
{"current_steps": 2120, "total_steps": 40000, "loss": 0.7365, "lr": 4.965457875180067e-05, "epoch": 0.5428589718968055, "percentage": 5.3, "elapsed_time": "1:29:55", "remaining_time": "1 day, 2:46:53", "throughput": 4595.82, "total_tokens": 24798656}
{"current_steps": 2125, "total_steps": 40000, "loss": 0.8093, "lr": 4.9652950500642724e-05, "epoch": 0.5441392996607132, "percentage": 5.31, "elapsed_time": "1:30:03", "remaining_time": "1 day, 2:45:09", "throughput": 4599.83, "total_tokens": 24855296}
{"current_steps": 2130, "total_steps": 40000, "loss": 0.9804, "lr": 4.965131844769001e-05, "epoch": 0.5454196274246207, "percentage": 5.33, "elapsed_time": "1:30:11", "remaining_time": "1 day, 2:43:26", "throughput": 4604.48, "total_tokens": 24915616}
{"current_steps": 2135, "total_steps": 40000, "loss": 0.7983, "lr": 4.96496825931942e-05, "epoch": 0.5466999551885282, "percentage": 5.34, "elapsed_time": "1:30:18", "remaining_time": "1 day, 2:41:45", "throughput": 4608.57, "total_tokens": 24973312}
{"current_steps": 2140, "total_steps": 40000, "loss": 0.7746, "lr": 4.9648042937407566e-05, "epoch": 0.5479802829524358, "percentage": 5.35, "elapsed_time": "1:30:26", "remaining_time": "1 day, 2:40:03", "throughput": 4612.53, "total_tokens": 25029824}
{"current_steps": 2145, "total_steps": 40000, "loss": 0.7661, "lr": 4.964639948058297e-05, "epoch": 0.5492606107163434, "percentage": 5.36, "elapsed_time": "1:30:34", "remaining_time": "1 day, 2:38:23", "throughput": 4616.92, "total_tokens": 25089408}
{"current_steps": 2150, "total_steps": 40000, "loss": 0.8329, "lr": 4.9644752222973846e-05, "epoch": 0.550540938480251, "percentage": 5.38, "elapsed_time": "1:30:41", "remaining_time": "1 day, 2:36:41", "throughput": 4621.59, "total_tokens": 25149920}
{"current_steps": 2155, "total_steps": 40000, "loss": 0.9842, "lr": 4.964310116483422e-05, "epoch": 0.5518212662441585, "percentage": 5.39, "elapsed_time": "1:30:49", "remaining_time": "1 day, 2:35:02", "throughput": 4625.71, "total_tokens": 25208000}
{"current_steps": 2160, "total_steps": 40000, "loss": 0.8024, "lr": 4.964144630641872e-05, "epoch": 0.553101594008066, "percentage": 5.4, "elapsed_time": "1:30:57", "remaining_time": "1 day, 2:33:21", "throughput": 4629.74, "total_tokens": 25265152}
{"current_steps": 2165, "total_steps": 40000, "loss": 0.806, "lr": 4.9639787647982525e-05, "epoch": 0.5543819217719737, "percentage": 5.41, "elapsed_time": "1:31:04", "remaining_time": "1 day, 2:31:42", "throughput": 4634.12, "total_tokens": 25324704}
{"current_steps": 2170, "total_steps": 40000, "loss": 0.8823, "lr": 4.963812518978143e-05, "epoch": 0.5556622495358812, "percentage": 5.42, "elapsed_time": "1:31:12", "remaining_time": "1 day, 2:30:02", "throughput": 4638.29, "total_tokens": 25382848}
{"current_steps": 2175, "total_steps": 40000, "loss": 0.8412, "lr": 4.963645893207182e-05, "epoch": 0.5569425772997888, "percentage": 5.44, "elapsed_time": "1:31:20", "remaining_time": "1 day, 2:28:24", "throughput": 4642.64, "total_tokens": 25442400}
{"current_steps": 2180, "total_steps": 40000, "loss": 0.8979, "lr": 4.963478887511063e-05, "epoch": 0.5582229050636963, "percentage": 5.45, "elapsed_time": "1:31:27", "remaining_time": "1 day, 2:26:45", "throughput": 4646.59, "total_tokens": 25499584}
{"current_steps": 2185, "total_steps": 40000, "loss": 0.8756, "lr": 4.963311501915542e-05, "epoch": 0.5595032328276038, "percentage": 5.46, "elapsed_time": "1:31:35", "remaining_time": "1 day, 2:25:07", "throughput": 4650.68, "total_tokens": 25557600}
{"current_steps": 2190, "total_steps": 40000, "loss": 0.8333, "lr": 4.963143736446432e-05, "epoch": 0.5607835605915115, "percentage": 5.47, "elapsed_time": "1:31:43", "remaining_time": "1 day, 2:23:29", "throughput": 4655.08, "total_tokens": 25617184}
{"current_steps": 2195, "total_steps": 40000, "loss": 0.8456, "lr": 4.962975591129603e-05, "epoch": 0.562063888355419, "percentage": 5.49, "elapsed_time": "1:31:50", "remaining_time": "1 day, 2:21:53", "throughput": 4659.05, "total_tokens": 25674912}
{"current_steps": 2200, "total_steps": 40000, "loss": 0.8537, "lr": 4.962807065990986e-05, "epoch": 0.5633442161193265, "percentage": 5.5, "elapsed_time": "1:31:58", "remaining_time": "1 day, 2:20:14", "throughput": 4663.02, "total_tokens": 25732032}
{"current_steps": 2200, "total_steps": 40000, "eval_loss": 0.8369344472885132, "epoch": 0.5633442161193265, "percentage": 5.5, "elapsed_time": "1:35:30", "remaining_time": "1 day, 3:21:04", "throughput": 4490.19, "total_tokens": 25732032}
{"current_steps": 2205, "total_steps": 40000, "loss": 0.8141, "lr": 4.9626381610565714e-05, "epoch": 0.5646245438832341, "percentage": 5.51, "elapsed_time": "1:35:40", "remaining_time": "1 day, 3:20:00", "throughput": 4492.38, "total_tokens": 25789824}
{"current_steps": 2210, "total_steps": 40000, "loss": 0.8311, "lr": 4.9624688763524043e-05, "epoch": 0.5659048716471416, "percentage": 5.53, "elapsed_time": "1:35:48", "remaining_time": "1 day, 3:18:16", "throughput": 4496.73, "total_tokens": 25849344}
{"current_steps": 2215, "total_steps": 40000, "loss": 0.7889, "lr": 4.962299211904591e-05, "epoch": 0.5671851994110493, "percentage": 5.54, "elapsed_time": "1:35:56", "remaining_time": "1 day, 3:16:31", "throughput": 4501.11, "total_tokens": 25908896}
{"current_steps": 2220, "total_steps": 40000, "loss": 0.8035, "lr": 4.962129167739296e-05, "epoch": 0.5684655271749568, "percentage": 5.55, "elapsed_time": "1:36:03", "remaining_time": "1 day, 3:14:47", "throughput": 4505.15, "total_tokens": 25966592}
{"current_steps": 2225, "total_steps": 40000, "loss": 0.829, "lr": 4.961958743882742e-05, "epoch": 0.5697458549388643, "percentage": 5.56, "elapsed_time": "1:36:11", "remaining_time": "1 day, 3:13:04", "throughput": 4509.42, "total_tokens": 26025632}
{"current_steps": 2230, "total_steps": 40000, "loss": 0.7394, "lr": 4.961787940361211e-05, "epoch": 0.571026182702772, "percentage": 5.58, "elapsed_time": "1:36:19", "remaining_time": "1 day, 3:11:21", "throughput": 4513.3, "total_tokens": 26082688}
{"current_steps": 2235, "total_steps": 40000, "loss": 0.8217, "lr": 4.961616757201043e-05, "epoch": 0.5723065104666795, "percentage": 5.59, "elapsed_time": "1:36:26", "remaining_time": "1 day, 3:09:39", "throughput": 4517.34, "total_tokens": 26140704}
{"current_steps": 2240, "total_steps": 40000, "loss": 0.8652, "lr": 4.961445194428637e-05, "epoch": 0.573586838230587, "percentage": 5.6, "elapsed_time": "1:36:34", "remaining_time": "1 day, 3:07:57", "throughput": 4521.4, "total_tokens": 26198912}
{"current_steps": 2245, "total_steps": 40000, "loss": 0.8775, "lr": 4.9612732520704486e-05, "epoch": 0.5748671659944946, "percentage": 5.61, "elapsed_time": "1:36:41", "remaining_time": "1 day, 3:06:14", "throughput": 4525.77, "total_tokens": 26258496}
{"current_steps": 2250, "total_steps": 40000, "loss": 0.781, "lr": 4.961100930152994e-05, "epoch": 0.5761474937584021, "percentage": 5.62, "elapsed_time": "1:36:49", "remaining_time": "1 day, 3:04:33", "throughput": 4529.76, "total_tokens": 26316320}
{"current_steps": 2255, "total_steps": 40000, "loss": 0.8041, "lr": 4.960928228702849e-05, "epoch": 0.5774278215223098, "percentage": 5.64, "elapsed_time": "1:36:57", "remaining_time": "1 day, 3:02:50", "throughput": 4534.61, "total_tokens": 26378880}
{"current_steps": 2260, "total_steps": 40000, "loss": 0.8479, "lr": 4.960755147746645e-05, "epoch": 0.5787081492862173, "percentage": 5.65, "elapsed_time": "1:37:04", "remaining_time": "1 day, 3:01:09", "throughput": 4538.69, "total_tokens": 26436992}
{"current_steps": 2265, "total_steps": 40000, "loss": 0.8039, "lr": 4.9605816873110736e-05, "epoch": 0.5799884770501248, "percentage": 5.66, "elapsed_time": "1:37:12", "remaining_time": "1 day, 2:59:28", "throughput": 4542.61, "total_tokens": 26494464}
{"current_steps": 2270, "total_steps": 40000, "loss": 0.8652, "lr": 4.960407847422883e-05, "epoch": 0.5812688048140324, "percentage": 5.67, "elapsed_time": "1:37:20", "remaining_time": "1 day, 2:57:48", "throughput": 4546.62, "total_tokens": 26552448}
{"current_steps": 2275, "total_steps": 40000, "loss": 0.8114, "lr": 4.960233628108885e-05, "epoch": 0.5825491325779399, "percentage": 5.69, "elapsed_time": "1:37:27", "remaining_time": "1 day, 2:56:08", "throughput": 4550.82, "total_tokens": 26611744}
{"current_steps": 2280, "total_steps": 40000, "loss": 0.7873, "lr": 4.960059029395942e-05, "epoch": 0.5838294603418475, "percentage": 5.7, "elapsed_time": "1:37:35", "remaining_time": "1 day, 2:54:28", "throughput": 4555.01, "total_tokens": 26670848}
{"current_steps": 2285, "total_steps": 40000, "loss": 0.8133, "lr": 4.959884051310983e-05, "epoch": 0.5851097881057551, "percentage": 5.71, "elapsed_time": "1:37:42", "remaining_time": "1 day, 2:52:50", "throughput": 4558.88, "total_tokens": 26728384}
{"current_steps": 2290, "total_steps": 40000, "loss": 0.8369, "lr": 4.959708693880991e-05, "epoch": 0.5863901158696626, "percentage": 5.73, "elapsed_time": "1:37:50", "remaining_time": "1 day, 2:51:12", "throughput": 4563.03, "total_tokens": 26787808}
{"current_steps": 2295, "total_steps": 40000, "loss": 0.8276, "lr": 4.9595329571330074e-05, "epoch": 0.5876704436335702, "percentage": 5.74, "elapsed_time": "1:37:58", "remaining_time": "1 day, 2:49:35", "throughput": 4567.15, "total_tokens": 26846976}
{"current_steps": 2300, "total_steps": 40000, "loss": 0.8808, "lr": 4.9593568410941326e-05, "epoch": 0.5889507713974778, "percentage": 5.75, "elapsed_time": "1:38:06", "remaining_time": "1 day, 2:47:59", "throughput": 4571.36, "total_tokens": 26907040}
{"current_steps": 2305, "total_steps": 40000, "loss": 0.7615, "lr": 4.959180345791528e-05, "epoch": 0.5902310991613853, "percentage": 5.76, "elapsed_time": "1:38:13", "remaining_time": "1 day, 2:46:22", "throughput": 4575.34, "total_tokens": 26965536}
{"current_steps": 2310, "total_steps": 40000, "loss": 0.8218, "lr": 4.9590034712524086e-05, "epoch": 0.5915114269252929, "percentage": 5.78, "elapsed_time": "1:38:21", "remaining_time": "1 day, 2:44:46", "throughput": 4579.53, "total_tokens": 27025408}
{"current_steps": 2315, "total_steps": 40000, "loss": 0.7525, "lr": 4.958826217504053e-05, "epoch": 0.5927917546892004, "percentage": 5.79, "elapsed_time": "1:38:29", "remaining_time": "1 day, 2:43:10", "throughput": 4583.49, "total_tokens": 27083840}
{"current_steps": 2320, "total_steps": 40000, "loss": 0.8771, "lr": 4.958648584573795e-05, "epoch": 0.5940720824531079, "percentage": 5.8, "elapsed_time": "1:38:36", "remaining_time": "1 day, 2:41:33", "throughput": 4587.41, "total_tokens": 27141888}
{"current_steps": 2325, "total_steps": 40000, "loss": 0.8654, "lr": 4.958470572489028e-05, "epoch": 0.5953524102170156, "percentage": 5.81, "elapsed_time": "1:38:44", "remaining_time": "1 day, 2:39:57", "throughput": 4591.45, "total_tokens": 27200544}
{"current_steps": 2330, "total_steps": 40000, "loss": 0.8041, "lr": 4.958292181277203e-05, "epoch": 0.5966327379809231, "percentage": 5.83, "elapsed_time": "1:38:51", "remaining_time": "1 day, 2:38:22", "throughput": 4595.37, "total_tokens": 27259072}
{"current_steps": 2335, "total_steps": 40000, "loss": 0.8121, "lr": 4.958113410965832e-05, "epoch": 0.5979130657448307, "percentage": 5.84, "elapsed_time": "1:38:59", "remaining_time": "1 day, 2:36:48", "throughput": 4599.17, "total_tokens": 27316832}
{"current_steps": 2340, "total_steps": 40000, "loss": 0.7849, "lr": 4.957934261582481e-05, "epoch": 0.5991933935087382, "percentage": 5.85, "elapsed_time": "1:39:07", "remaining_time": "1 day, 2:35:14", "throughput": 4603.11, "total_tokens": 27375552}
{"current_steps": 2345, "total_steps": 40000, "loss": 0.7989, "lr": 4.95775473315478e-05, "epoch": 0.6004737212726458, "percentage": 5.86, "elapsed_time": "1:39:14", "remaining_time": "1 day, 2:33:39", "throughput": 4607.02, "total_tokens": 27433760}
{"current_steps": 2350, "total_steps": 40000, "loss": 0.8671, "lr": 4.9575748257104124e-05, "epoch": 0.6017540490365534, "percentage": 5.88, "elapsed_time": "1:39:22", "remaining_time": "1 day, 2:32:05", "throughput": 4611.23, "total_tokens": 27494016}
{"current_steps": 2355, "total_steps": 40000, "loss": 0.8082, "lr": 4.9573945392771224e-05, "epoch": 0.6030343768004609, "percentage": 5.89, "elapsed_time": "1:39:30", "remaining_time": "1 day, 2:30:33", "throughput": 4615.19, "total_tokens": 27553184}
{"current_steps": 2360, "total_steps": 40000, "loss": 0.8846, "lr": 4.9572138738827134e-05, "epoch": 0.6043147045643685, "percentage": 5.9, "elapsed_time": "1:39:37", "remaining_time": "1 day, 2:28:58", "throughput": 4619.12, "total_tokens": 27611584}
{"current_steps": 2365, "total_steps": 40000, "loss": 0.9081, "lr": 4.957032829555046e-05, "epoch": 0.605595032328276, "percentage": 5.91, "elapsed_time": "1:39:45", "remaining_time": "1 day, 2:27:26", "throughput": 4623.06, "total_tokens": 27670560}
{"current_steps": 2370, "total_steps": 40000, "loss": 0.7595, "lr": 4.956851406322039e-05, "epoch": 0.6068753600921836, "percentage": 5.92, "elapsed_time": "1:39:52", "remaining_time": "1 day, 2:25:54", "throughput": 4627.02, "total_tokens": 27729536}
{"current_steps": 2375, "total_steps": 40000, "loss": 0.9099, "lr": 4.9566696042116704e-05, "epoch": 0.6081556878560912, "percentage": 5.94, "elapsed_time": "1:40:00", "remaining_time": "1 day, 2:24:22", "throughput": 4631.24, "total_tokens": 27790240}
{"current_steps": 2380, "total_steps": 40000, "loss": 0.7978, "lr": 4.9564874232519766e-05, "epoch": 0.6094360156199987, "percentage": 5.95, "elapsed_time": "1:40:08", "remaining_time": "1 day, 2:22:50", "throughput": 4635.23, "total_tokens": 27849568}
{"current_steps": 2385, "total_steps": 40000, "loss": 0.8106, "lr": 4.9563048634710516e-05, "epoch": 0.6107163433839062, "percentage": 5.96, "elapsed_time": "1:40:15", "remaining_time": "1 day, 2:21:19", "throughput": 4638.9, "total_tokens": 27907232}
{"current_steps": 2390, "total_steps": 40000, "loss": 0.8019, "lr": 4.956121924897049e-05, "epoch": 0.6119966711478139, "percentage": 5.97, "elapsed_time": "1:40:23", "remaining_time": "1 day, 2:19:48", "throughput": 4643.02, "total_tokens": 27967360}
{"current_steps": 2395, "total_steps": 40000, "loss": 0.8682, "lr": 4.955938607558181e-05, "epoch": 0.6132769989117214, "percentage": 5.99, "elapsed_time": "1:40:31", "remaining_time": "1 day, 2:18:18", "throughput": 4647.2, "total_tokens": 28028256}
{"current_steps": 2400, "total_steps": 40000, "loss": 0.8189, "lr": 4.955754911482715e-05, "epoch": 0.614557326675629, "percentage": 6.0, "elapsed_time": "1:40:38", "remaining_time": "1 day, 2:16:48", "throughput": 4651.28, "total_tokens": 28088288}
{"current_steps": 2400, "total_steps": 40000, "eval_loss": 0.8267553448677063, "epoch": 0.614557326675629, "percentage": 6.0, "elapsed_time": "1:44:10", "remaining_time": "1 day, 3:12:07", "throughput": 4493.61, "total_tokens": 28088288}
{"current_steps": 2405, "total_steps": 40000, "loss": 0.8325, "lr": 4.9555708366989804e-05, "epoch": 0.6158376544395365, "percentage": 6.01, "elapsed_time": "1:44:20", "remaining_time": "1 day, 3:11:07", "throughput": 4495.73, "total_tokens": 28146304}
{"current_steps": 2410, "total_steps": 40000, "loss": 0.8612, "lr": 4.9553863832353655e-05, "epoch": 0.617117982203444, "percentage": 6.02, "elapsed_time": "1:44:28", "remaining_time": "1 day, 3:09:30", "throughput": 4499.53, "total_tokens": 28204512}
{"current_steps": 2415, "total_steps": 40000, "loss": 0.859, "lr": 4.955201551120313e-05, "epoch": 0.6183983099673517, "percentage": 6.04, "elapsed_time": "1:44:35", "remaining_time": "1 day, 3:07:54", "throughput": 4503.3, "total_tokens": 28262688}
{"current_steps": 2420, "total_steps": 40000, "loss": 0.8646, "lr": 4.955016340382328e-05, "epoch": 0.6196786377312592, "percentage": 6.05, "elapsed_time": "1:44:43", "remaining_time": "1 day, 3:06:18", "throughput": 4507.36, "total_tokens": 28322688}
{"current_steps": 2425, "total_steps": 40000, "loss": 0.7648, "lr": 4.954830751049972e-05, "epoch": 0.6209589654951667, "percentage": 6.06, "elapsed_time": "1:44:51", "remaining_time": "1 day, 3:04:42", "throughput": 4510.68, "total_tokens": 28378080}
{"current_steps": 2430, "total_steps": 40000, "loss": 0.7412, "lr": 4.954644783151864e-05, "epoch": 0.6222392932590743, "percentage": 6.08, "elapsed_time": "1:44:58", "remaining_time": "1 day, 3:03:07", "throughput": 4514.45, "total_tokens": 28436320}
{"current_steps": 2435, "total_steps": 40000, "loss": 0.7845, "lr": 4.954458436716684e-05, "epoch": 0.6235196210229819, "percentage": 6.09, "elapsed_time": "1:45:06", "remaining_time": "1 day, 3:01:33", "throughput": 4518.2, "total_tokens": 28494688}
{"current_steps": 2440, "total_steps": 40000, "loss": 0.7869, "lr": 4.954271711773168e-05, "epoch": 0.6247999487868895, "percentage": 6.1, "elapsed_time": "1:45:14", "remaining_time": "1 day, 2:59:58", "throughput": 4521.71, "total_tokens": 28551360}
{"current_steps": 2445, "total_steps": 40000, "loss": 0.7778, "lr": 4.9540846083501115e-05, "epoch": 0.626080276550797, "percentage": 6.11, "elapsed_time": "1:45:21", "remaining_time": "1 day, 2:58:24", "throughput": 4525.67, "total_tokens": 28611040}
{"current_steps": 2450, "total_steps": 40000, "loss": 0.9037, "lr": 4.953897126476369e-05, "epoch": 0.6273606043147045, "percentage": 6.12, "elapsed_time": "1:45:29", "remaining_time": "1 day, 2:56:50", "throughput": 4529.35, "total_tokens": 28668800}
{"current_steps": 2455, "total_steps": 40000, "loss": 0.8804, "lr": 4.9537092661808514e-05, "epoch": 0.6286409320786122, "percentage": 6.14, "elapsed_time": "1:45:37", "remaining_time": "1 day, 2:55:16", "throughput": 4532.9, "total_tokens": 28725984}
{"current_steps": 2460, "total_steps": 40000, "loss": 0.8403, "lr": 4.9535210274925306e-05, "epoch": 0.6299212598425197, "percentage": 6.15, "elapsed_time": "1:45:45", "remaining_time": "1 day, 2:53:50", "throughput": 4536.11, "total_tokens": 28782976}
{"current_steps": 2465, "total_steps": 40000, "loss": 0.7881, "lr": 4.953332410440435e-05, "epoch": 0.6312015876064272, "percentage": 6.16, "elapsed_time": "1:45:52", "remaining_time": "1 day, 2:52:17", "throughput": 4539.88, "total_tokens": 28841760}
{"current_steps": 2470, "total_steps": 40000, "loss": 0.8063, "lr": 4.9531434150536496e-05, "epoch": 0.6324819153703348, "percentage": 6.17, "elapsed_time": "1:46:00", "remaining_time": "1 day, 2:50:45", "throughput": 4543.79, "total_tokens": 28901344}
{"current_steps": 2475, "total_steps": 40000, "loss": 0.8002, "lr": 4.952954041361322e-05, "epoch": 0.6337622431342423, "percentage": 6.19, "elapsed_time": "1:46:08", "remaining_time": "1 day, 2:49:13", "throughput": 4547.5, "total_tokens": 28959712}
{"current_steps": 2480, "total_steps": 40000, "loss": 0.7169, "lr": 4.952764289392655e-05, "epoch": 0.63504257089815, "percentage": 6.2, "elapsed_time": "1:46:15", "remaining_time": "1 day, 2:47:41", "throughput": 4550.79, "total_tokens": 29015552}
{"current_steps": 2485, "total_steps": 40000, "loss": 0.864, "lr": 4.952574159176912e-05, "epoch": 0.6363228986620575, "percentage": 6.21, "elapsed_time": "1:46:23", "remaining_time": "1 day, 2:46:10", "throughput": 4554.48, "total_tokens": 29073984}
{"current_steps": 2490, "total_steps": 40000, "loss": 0.7998, "lr": 4.952383650743413e-05, "epoch": 0.637603226425965, "percentage": 6.22, "elapsed_time": "1:46:31", "remaining_time": "1 day, 2:44:39", "throughput": 4558.1, "total_tokens": 29132032}
{"current_steps": 2495, "total_steps": 40000, "loss": 0.7963, "lr": 4.952192764121536e-05, "epoch": 0.6388835541898726, "percentage": 6.24, "elapsed_time": "1:46:38", "remaining_time": "1 day, 2:43:08", "throughput": 4562.04, "total_tokens": 29192000}
{"current_steps": 2500, "total_steps": 40000, "loss": 0.7641, "lr": 4.9520014993407185e-05, "epoch": 0.6401638819537802, "percentage": 6.25, "elapsed_time": "1:46:46", "remaining_time": "1 day, 2:41:38", "throughput": 4565.84, "total_tokens": 29251424}
{"current_steps": 2505, "total_steps": 40000, "loss": 0.8464, "lr": 4.951809856430456e-05, "epoch": 0.6414442097176877, "percentage": 6.26, "elapsed_time": "1:46:54", "remaining_time": "1 day, 2:40:08", "throughput": 4569.25, "total_tokens": 29308352}
{"current_steps": 2510, "total_steps": 40000, "loss": 0.833, "lr": 4.951617835420303e-05, "epoch": 0.6427245374815953, "percentage": 6.28, "elapsed_time": "1:47:01", "remaining_time": "1 day, 2:38:39", "throughput": 4572.86, "total_tokens": 29366432}
{"current_steps": 2515, "total_steps": 40000, "loss": 0.8623, "lr": 4.951425436339869e-05, "epoch": 0.6440048652455028, "percentage": 6.29, "elapsed_time": "1:47:09", "remaining_time": "1 day, 2:37:09", "throughput": 4576.6, "total_tokens": 29425344}
{"current_steps": 2520, "total_steps": 40000, "loss": 0.8706, "lr": 4.9512326592188274e-05, "epoch": 0.6452851930094105, "percentage": 6.3, "elapsed_time": "1:47:17", "remaining_time": "1 day, 2:35:40", "throughput": 4580.43, "total_tokens": 29485120}
{"current_steps": 2525, "total_steps": 40000, "loss": 0.82, "lr": 4.9510395040869054e-05, "epoch": 0.646565520773318, "percentage": 6.31, "elapsed_time": "1:47:24", "remaining_time": "1 day, 2:34:10", "throughput": 4584.15, "total_tokens": 29543776}
{"current_steps": 2530, "total_steps": 40000, "loss": 0.8449, "lr": 4.9508459709738905e-05, "epoch": 0.6478458485372255, "percentage": 6.33, "elapsed_time": "1:47:32", "remaining_time": "1 day, 2:32:42", "throughput": 4587.99, "total_tokens": 29603744}
{"current_steps": 2535, "total_steps": 40000, "loss": 0.765, "lr": 4.950652059909627e-05, "epoch": 0.6491261763011331, "percentage": 6.34, "elapsed_time": "1:47:40", "remaining_time": "1 day, 2:31:13", "throughput": 4591.69, "total_tokens": 29662496}
{"current_steps": 2540, "total_steps": 40000, "loss": 0.8569, "lr": 4.95045777092402e-05, "epoch": 0.6504065040650406, "percentage": 6.35, "elapsed_time": "1:47:47", "remaining_time": "1 day, 2:29:45", "throughput": 4595.41, "total_tokens": 29721664}
{"current_steps": 2545, "total_steps": 40000, "loss": 0.742, "lr": 4.950263104047031e-05, "epoch": 0.6516868318289483, "percentage": 6.36, "elapsed_time": "1:47:55", "remaining_time": "1 day, 2:28:17", "throughput": 4598.7, "total_tokens": 29777984}
{"current_steps": 2550, "total_steps": 40000, "loss": 0.838, "lr": 4.9500680593086775e-05, "epoch": 0.6529671595928558, "percentage": 6.38, "elapsed_time": "1:48:03", "remaining_time": "1 day, 2:26:51", "throughput": 4602.44, "total_tokens": 29837632}
{"current_steps": 2555, "total_steps": 40000, "loss": 0.8589, "lr": 4.94987263673904e-05, "epoch": 0.6542474873567633, "percentage": 6.39, "elapsed_time": "1:48:10", "remaining_time": "1 day, 2:25:24", "throughput": 4606.43, "total_tokens": 29898720}
{"current_steps": 2560, "total_steps": 40000, "loss": 0.8425, "lr": 4.949676836368256e-05, "epoch": 0.6555278151206709, "percentage": 6.4, "elapsed_time": "1:48:18", "remaining_time": "1 day, 2:23:58", "throughput": 4609.76, "total_tokens": 29955872}
{"current_steps": 2565, "total_steps": 40000, "loss": 0.831, "lr": 4.949480658226518e-05, "epoch": 0.6568081428845784, "percentage": 6.41, "elapsed_time": "1:48:26", "remaining_time": "1 day, 2:22:32", "throughput": 4613.04, "total_tokens": 30012544}
{"current_steps": 2570, "total_steps": 40000, "loss": 0.7986, "lr": 4.949284102344082e-05, "epoch": 0.658088470648486, "percentage": 6.42, "elapsed_time": "1:48:33", "remaining_time": "1 day, 2:21:06", "throughput": 4616.59, "total_tokens": 30070848}
{"current_steps": 2575, "total_steps": 40000, "loss": 0.7976, "lr": 4.9490871687512565e-05, "epoch": 0.6593687984123936, "percentage": 6.44, "elapsed_time": "1:48:41", "remaining_time": "1 day, 2:19:41", "throughput": 4620.01, "total_tokens": 30128640}
{"current_steps": 2580, "total_steps": 40000, "loss": 0.7957, "lr": 4.948889857478413e-05, "epoch": 0.6606491261763011, "percentage": 6.45, "elapsed_time": "1:48:49", "remaining_time": "1 day, 2:18:16", "throughput": 4623.49, "total_tokens": 30186944}
{"current_steps": 2585, "total_steps": 40000, "loss": 0.8869, "lr": 4.948692168555978e-05, "epoch": 0.6619294539402087, "percentage": 6.46, "elapsed_time": "1:48:56", "remaining_time": "1 day, 2:16:51", "throughput": 4626.78, "total_tokens": 30243840}
{"current_steps": 2590, "total_steps": 40000, "loss": 0.846, "lr": 4.94849410201444e-05, "epoch": 0.6632097817041163, "percentage": 6.48, "elapsed_time": "1:49:04", "remaining_time": "1 day, 2:15:27", "throughput": 4630.35, "total_tokens": 30302752}
{"current_steps": 2595, "total_steps": 40000, "loss": 0.8176, "lr": 4.948295657884341e-05, "epoch": 0.6644901094680238, "percentage": 6.49, "elapsed_time": "1:49:11", "remaining_time": "1 day, 2:14:01", "throughput": 4633.91, "total_tokens": 30361184}
{"current_steps": 2600, "total_steps": 40000, "loss": 0.814, "lr": 4.9480968361962835e-05, "epoch": 0.6657704372319314, "percentage": 6.5, "elapsed_time": "1:49:19", "remaining_time": "1 day, 2:12:38", "throughput": 4637.16, "total_tokens": 30418272}
{"current_steps": 2600, "total_steps": 40000, "eval_loss": 0.8187787532806396, "epoch": 0.6657704372319314, "percentage": 6.5, "elapsed_time": "1:52:51", "remaining_time": "1 day, 3:03:29", "throughput": 4491.93, "total_tokens": 30418272}
{"current_steps": 2605, "total_steps": 40000, "loss": 0.8414, "lr": 4.9478976369809305e-05, "epoch": 0.6670507649958389, "percentage": 6.51, "elapsed_time": "1:53:01", "remaining_time": "1 day, 3:02:31", "throughput": 4494.06, "total_tokens": 30477376}
{"current_steps": 2610, "total_steps": 40000, "loss": 0.8153, "lr": 4.947698060268999e-05, "epoch": 0.6683310927597464, "percentage": 6.53, "elapsed_time": "1:53:09", "remaining_time": "1 day, 3:01:02", "throughput": 4497.5, "total_tokens": 30535232}
{"current_steps": 2615, "total_steps": 40000, "loss": 0.7761, "lr": 4.9474981060912665e-05, "epoch": 0.6696114205236541, "percentage": 6.54, "elapsed_time": "1:53:17", "remaining_time": "1 day, 2:59:32", "throughput": 4500.99, "total_tokens": 30593280}
{"current_steps": 2620, "total_steps": 40000, "loss": 0.8717, "lr": 4.94729777447857e-05, "epoch": 0.6708917482875616, "percentage": 6.55, "elapsed_time": "1:53:24", "remaining_time": "1 day, 2:58:03", "throughput": 4504.62, "total_tokens": 30652544}
{"current_steps": 2625, "total_steps": 40000, "loss": 0.7944, "lr": 4.947097065461801e-05, "epoch": 0.6721720760514692, "percentage": 6.56, "elapsed_time": "1:53:32", "remaining_time": "1 day, 2:56:34", "throughput": 4508.18, "total_tokens": 30711168}
{"current_steps": 2630, "total_steps": 40000, "loss": 0.8277, "lr": 4.9468959790719125e-05, "epoch": 0.6734524038153767, "percentage": 6.58, "elapsed_time": "1:53:40", "remaining_time": "1 day, 2:55:06", "throughput": 4511.8, "total_tokens": 30770464}
{"current_steps": 2635, "total_steps": 40000, "loss": 0.8129, "lr": 4.9466945153399146e-05, "epoch": 0.6747327315792843, "percentage": 6.59, "elapsed_time": "1:53:47", "remaining_time": "1 day, 2:53:38", "throughput": 4515.26, "total_tokens": 30828928}
{"current_steps": 2640, "total_steps": 40000, "loss": 0.8557, "lr": 4.9464926742968755e-05, "epoch": 0.6760130593431919, "percentage": 6.6, "elapsed_time": "1:53:55", "remaining_time": "1 day, 2:52:10", "throughput": 4518.98, "total_tokens": 30888800}
{"current_steps": 2645, "total_steps": 40000, "loss": 0.8513, "lr": 4.946290455973921e-05, "epoch": 0.6772933871070994, "percentage": 6.61, "elapsed_time": "1:54:03", "remaining_time": "1 day, 2:50:43", "throughput": 4522.34, "total_tokens": 30946720}
{"current_steps": 2650, "total_steps": 40000, "loss": 0.8132, "lr": 4.9460878604022365e-05, "epoch": 0.6785737148710069, "percentage": 6.62, "elapsed_time": "1:54:10", "remaining_time": "1 day, 2:49:16", "throughput": 4525.71, "total_tokens": 31004416}
{"current_steps": 2655, "total_steps": 40000, "loss": 0.8655, "lr": 4.945884887613065e-05, "epoch": 0.6798540426349146, "percentage": 6.64, "elapsed_time": "1:54:18", "remaining_time": "1 day, 2:47:49", "throughput": 4529.36, "total_tokens": 31064160}
{"current_steps": 2660, "total_steps": 40000, "loss": 0.8482, "lr": 4.9456815376377055e-05, "epoch": 0.6811343703988221, "percentage": 6.65, "elapsed_time": "1:54:26", "remaining_time": "1 day, 2:46:23", "throughput": 4532.85, "total_tokens": 31122976}
{"current_steps": 2665, "total_steps": 40000, "loss": 0.8019, "lr": 4.9454778105075195e-05, "epoch": 0.6824146981627297, "percentage": 6.66, "elapsed_time": "1:54:33", "remaining_time": "1 day, 2:44:57", "throughput": 4536.02, "total_tokens": 31179488}
{"current_steps": 2670, "total_steps": 40000, "loss": 0.7691, "lr": 4.945273706253924e-05, "epoch": 0.6836950259266372, "percentage": 6.68, "elapsed_time": "1:54:41", "remaining_time": "1 day, 2:43:30", "throughput": 4539.39, "total_tokens": 31237248}
{"current_steps": 2675, "total_steps": 40000, "loss": 0.8102, "lr": 4.9450692249083925e-05, "epoch": 0.6849753536905447, "percentage": 6.69, "elapsed_time": "1:54:49", "remaining_time": "1 day, 2:42:05", "throughput": 4542.71, "total_tokens": 31295136}
{"current_steps": 2680, "total_steps": 40000, "loss": 0.7577, "lr": 4.9448643665024605e-05, "epoch": 0.6862556814544524, "percentage": 6.7, "elapsed_time": "1:54:56", "remaining_time": "1 day, 2:40:39", "throughput": 4546.36, "total_tokens": 31354944}
{"current_steps": 2685, "total_steps": 40000, "loss": 0.7449, "lr": 4.944659131067719e-05, "epoch": 0.6875360092183599, "percentage": 6.71, "elapsed_time": "1:55:04", "remaining_time": "1 day, 2:39:14", "throughput": 4549.85, "total_tokens": 31414112}
{"current_steps": 2690, "total_steps": 40000, "loss": 0.9003, "lr": 4.944453518635818e-05, "epoch": 0.6888163369822674, "percentage": 6.73, "elapsed_time": "1:55:12", "remaining_time": "1 day, 2:37:49", "throughput": 4553.27, "total_tokens": 31472448}
{"current_steps": 2695, "total_steps": 40000, "loss": 0.8246, "lr": 4.944247529238465e-05, "epoch": 0.690096664746175, "percentage": 6.74, "elapsed_time": "1:55:19", "remaining_time": "1 day, 2:36:25", "throughput": 4556.44, "total_tokens": 31529408}
{"current_steps": 2700, "total_steps": 40000, "loss": 0.7951, "lr": 4.944041162907427e-05, "epoch": 0.6913769925100826, "percentage": 6.75, "elapsed_time": "1:55:27", "remaining_time": "1 day, 2:35:00", "throughput": 4559.86, "total_tokens": 31588064}
{"current_steps": 2705, "total_steps": 40000, "loss": 0.7398, "lr": 4.943834419674529e-05, "epoch": 0.6926573202739902, "percentage": 6.76, "elapsed_time": "1:55:35", "remaining_time": "1 day, 2:33:36", "throughput": 4563.38, "total_tokens": 31647264}
{"current_steps": 2710, "total_steps": 40000, "loss": 0.7328, "lr": 4.9436272995716506e-05, "epoch": 0.6939376480378977, "percentage": 6.78, "elapsed_time": "1:55:42", "remaining_time": "1 day, 2:32:11", "throughput": 4566.86, "total_tokens": 31706080}
{"current_steps": 2715, "total_steps": 40000, "loss": 0.8014, "lr": 4.943419802630735e-05, "epoch": 0.6952179758018052, "percentage": 6.79, "elapsed_time": "1:55:50", "remaining_time": "1 day, 2:30:47", "throughput": 4569.94, "total_tokens": 31762400}
{"current_steps": 2720, "total_steps": 40000, "loss": 0.8368, "lr": 4.94321192888378e-05, "epoch": 0.6964983035657129, "percentage": 6.8, "elapsed_time": "1:55:57", "remaining_time": "1 day, 2:29:24", "throughput": 4573.78, "total_tokens": 31824128}
{"current_steps": 2725, "total_steps": 40000, "loss": 0.8822, "lr": 4.943003678362842e-05, "epoch": 0.6977786313296204, "percentage": 6.81, "elapsed_time": "1:56:05", "remaining_time": "1 day, 2:28:02", "throughput": 4577.36, "total_tokens": 31884384}
{"current_steps": 2730, "total_steps": 40000, "loss": 0.7728, "lr": 4.942795051100036e-05, "epoch": 0.699058959093528, "percentage": 6.83, "elapsed_time": "1:56:13", "remaining_time": "1 day, 2:26:39", "throughput": 4580.67, "total_tokens": 31942496}
{"current_steps": 2735, "total_steps": 40000, "loss": 0.7625, "lr": 4.942586047127536e-05, "epoch": 0.7003392868574355, "percentage": 6.84, "elapsed_time": "1:56:20", "remaining_time": "1 day, 2:25:17", "throughput": 4584.05, "total_tokens": 32001024}
{"current_steps": 2740, "total_steps": 40000, "loss": 0.8901, "lr": 4.942376666477571e-05, "epoch": 0.701619614621343, "percentage": 6.85, "elapsed_time": "1:56:28", "remaining_time": "1 day, 2:23:54", "throughput": 4587.59, "total_tokens": 32060608}
{"current_steps": 2745, "total_steps": 40000, "loss": 0.8255, "lr": 4.9421669091824304e-05, "epoch": 0.7028999423852507, "percentage": 6.86, "elapsed_time": "1:56:36", "remaining_time": "1 day, 2:22:32", "throughput": 4590.73, "total_tokens": 32117984}
{"current_steps": 2750, "total_steps": 40000, "loss": 0.8137, "lr": 4.9419567752744634e-05, "epoch": 0.7041802701491582, "percentage": 6.88, "elapsed_time": "1:56:43", "remaining_time": "1 day, 2:21:11", "throughput": 4594.45, "total_tokens": 32179072}
{"current_steps": 2755, "total_steps": 40000, "loss": 0.808, "lr": 4.941746264786074e-05, "epoch": 0.7054605979130657, "percentage": 6.89, "elapsed_time": "1:56:51", "remaining_time": "1 day, 2:19:49", "throughput": 4597.73, "total_tokens": 32237376}
{"current_steps": 2760, "total_steps": 40000, "loss": 0.8085, "lr": 4.9415353777497254e-05, "epoch": 0.7067409256769733, "percentage": 6.9, "elapsed_time": "1:56:59", "remaining_time": "1 day, 2:18:28", "throughput": 4601.06, "total_tokens": 32295744}
{"current_steps": 2765, "total_steps": 40000, "loss": 0.7094, "lr": 4.9413241141979394e-05, "epoch": 0.7080212534408808, "percentage": 6.91, "elapsed_time": "1:57:06", "remaining_time": "1 day, 2:17:06", "throughput": 4604.38, "total_tokens": 32354080}
{"current_steps": 2770, "total_steps": 40000, "loss": 0.8056, "lr": 4.9411124741632956e-05, "epoch": 0.7093015812047885, "percentage": 6.93, "elapsed_time": "1:57:14", "remaining_time": "1 day, 2:15:46", "throughput": 4607.59, "total_tokens": 32411904}
{"current_steps": 2775, "total_steps": 40000, "loss": 0.7913, "lr": 4.940900457678431e-05, "epoch": 0.710581908968696, "percentage": 6.94, "elapsed_time": "1:57:22", "remaining_time": "1 day, 2:14:26", "throughput": 4610.49, "total_tokens": 32467744}
{"current_steps": 2780, "total_steps": 40000, "loss": 0.7922, "lr": 4.9406880647760425e-05, "epoch": 0.7118622367326035, "percentage": 6.95, "elapsed_time": "1:57:29", "remaining_time": "1 day, 2:13:07", "throughput": 4613.73, "total_tokens": 32526144}
{"current_steps": 2785, "total_steps": 40000, "loss": 0.8262, "lr": 4.9404752954888824e-05, "epoch": 0.7131425644965111, "percentage": 6.96, "elapsed_time": "1:57:37", "remaining_time": "1 day, 2:11:47", "throughput": 4616.89, "total_tokens": 32583904}
{"current_steps": 2790, "total_steps": 40000, "loss": 0.82, "lr": 4.940262149849762e-05, "epoch": 0.7144228922604187, "percentage": 6.98, "elapsed_time": "1:57:45", "remaining_time": "1 day, 2:10:27", "throughput": 4620.06, "total_tokens": 32641568}
{"current_steps": 2795, "total_steps": 40000, "loss": 0.7846, "lr": 4.9400486278915526e-05, "epoch": 0.7157032200243262, "percentage": 6.99, "elapsed_time": "1:57:52", "remaining_time": "1 day, 2:09:07", "throughput": 4623.48, "total_tokens": 32700960}
{"current_steps": 2800, "total_steps": 40000, "loss": 0.789, "lr": 4.939834729647181e-05, "epoch": 0.7169835477882338, "percentage": 7.0, "elapsed_time": "1:58:00", "remaining_time": "1 day, 2:07:54", "throughput": 4626.84, "total_tokens": 32762272}
{"current_steps": 2800, "total_steps": 40000, "eval_loss": 0.8099365234375, "epoch": 0.7169835477882338, "percentage": 7.0, "elapsed_time": "2:01:32", "remaining_time": "1 day, 2:54:50", "throughput": 4492.39, "total_tokens": 32762272}
{"current_steps": 2805, "total_steps": 40000, "loss": 0.8437, "lr": 4.9396204551496326e-05, "epoch": 0.7182638755521413, "percentage": 7.01, "elapsed_time": "2:01:42", "remaining_time": "1 day, 2:53:58", "throughput": 4494.34, "total_tokens": 32821920}
{"current_steps": 2810, "total_steps": 40000, "loss": 0.7884, "lr": 4.939405804431952e-05, "epoch": 0.719544203316049, "percentage": 7.03, "elapsed_time": "2:01:50", "remaining_time": "1 day, 2:52:34", "throughput": 4497.57, "total_tokens": 32879968}
{"current_steps": 2815, "total_steps": 40000, "loss": 0.8236, "lr": 4.9391907775272414e-05, "epoch": 0.7208245310799565, "percentage": 7.04, "elapsed_time": "2:01:58", "remaining_time": "1 day, 2:51:10", "throughput": 4500.79, "total_tokens": 32937600}
{"current_steps": 2820, "total_steps": 40000, "loss": 0.8384, "lr": 4.9389753744686604e-05, "epoch": 0.722104858843864, "percentage": 7.05, "elapsed_time": "2:02:05", "remaining_time": "1 day, 2:49:47", "throughput": 4503.74, "total_tokens": 32993920}
{"current_steps": 2825, "total_steps": 40000, "loss": 0.7605, "lr": 4.938759595289426e-05, "epoch": 0.7233851866077716, "percentage": 7.06, "elapsed_time": "2:02:13", "remaining_time": "1 day, 2:48:24", "throughput": 4507.05, "total_tokens": 33052640}
{"current_steps": 2830, "total_steps": 40000, "loss": 0.8306, "lr": 4.938543440022815e-05, "epoch": 0.7246655143716791, "percentage": 7.07, "elapsed_time": "2:02:21", "remaining_time": "1 day, 2:47:01", "throughput": 4510.43, "total_tokens": 33111968}
{"current_steps": 2835, "total_steps": 40000, "loss": 0.7588, "lr": 4.938326908702161e-05, "epoch": 0.7259458421355867, "percentage": 7.09, "elapsed_time": "2:02:28", "remaining_time": "1 day, 2:45:38", "throughput": 4513.6, "total_tokens": 33169696}
{"current_steps": 2840, "total_steps": 40000, "loss": 0.829, "lr": 4.9381100013608554e-05, "epoch": 0.7272261698994943, "percentage": 7.1, "elapsed_time": "2:02:36", "remaining_time": "1 day, 2:44:16", "throughput": 4516.78, "total_tokens": 33227808}
{"current_steps": 2845, "total_steps": 40000, "loss": 0.7404, "lr": 4.9378927180323485e-05, "epoch": 0.7285064976634018, "percentage": 7.11, "elapsed_time": "2:02:44", "remaining_time": "1 day, 2:42:55", "throughput": 4520.2, "total_tokens": 33287872}
{"current_steps": 2850, "total_steps": 40000, "loss": 0.7854, "lr": 4.937675058750148e-05, "epoch": 0.7297868254273094, "percentage": 7.12, "elapsed_time": "2:02:51", "remaining_time": "1 day, 2:41:33", "throughput": 4523.62, "total_tokens": 33347648}
{"current_steps": 2855, "total_steps": 40000, "loss": 0.7742, "lr": 4.937457023547819e-05, "epoch": 0.731067153191217, "percentage": 7.14, "elapsed_time": "2:02:59", "remaining_time": "1 day, 2:40:11", "throughput": 4526.54, "total_tokens": 33403872}
{"current_steps": 2860, "total_steps": 40000, "loss": 0.7289, "lr": 4.9372386124589876e-05, "epoch": 0.7323474809551245, "percentage": 7.15, "elapsed_time": "2:03:07", "remaining_time": "1 day, 2:38:51", "throughput": 4529.72, "total_tokens": 33462208}
{"current_steps": 2865, "total_steps": 40000, "loss": 0.8278, "lr": 4.937019825517333e-05, "epoch": 0.7336278087190321, "percentage": 7.16, "elapsed_time": "2:03:14", "remaining_time": "1 day, 2:37:29", "throughput": 4532.85, "total_tokens": 33519808}
{"current_steps": 2870, "total_steps": 40000, "loss": 0.8236, "lr": 4.9368006627565954e-05, "epoch": 0.7349081364829396, "percentage": 7.17, "elapsed_time": "2:03:22", "remaining_time": "1 day, 2:36:08", "throughput": 4535.92, "total_tokens": 33577344}
{"current_steps": 2875, "total_steps": 40000, "loss": 0.811, "lr": 4.936581124210573e-05, "epoch": 0.7361884642468471, "percentage": 7.19, "elapsed_time": "2:03:30", "remaining_time": "1 day, 2:34:47", "throughput": 4539.1, "total_tokens": 33635328}
{"current_steps": 2880, "total_steps": 40000, "loss": 0.8612, "lr": 4.9363612099131216e-05, "epoch": 0.7374687920107548, "percentage": 7.2, "elapsed_time": "2:03:37", "remaining_time": "1 day, 2:33:27", "throughput": 4542.62, "total_tokens": 33696192}
{"current_steps": 2885, "total_steps": 40000, "loss": 0.7834, "lr": 4.936140919898155e-05, "epoch": 0.7387491197746623, "percentage": 7.21, "elapsed_time": "2:03:45", "remaining_time": "1 day, 2:32:07", "throughput": 4545.76, "total_tokens": 33754496}
{"current_steps": 2890, "total_steps": 40000, "loss": 0.8017, "lr": 4.9359202541996426e-05, "epoch": 0.7400294475385699, "percentage": 7.22, "elapsed_time": "2:03:53", "remaining_time": "1 day, 2:30:47", "throughput": 4548.68, "total_tokens": 33810912}
{"current_steps": 2895, "total_steps": 40000, "loss": 0.8008, "lr": 4.935699212851616e-05, "epoch": 0.7413097753024774, "percentage": 7.24, "elapsed_time": "2:04:00", "remaining_time": "1 day, 2:29:28", "throughput": 4551.69, "total_tokens": 33868352}
{"current_steps": 2900, "total_steps": 40000, "loss": 0.7984, "lr": 4.935477795888162e-05, "epoch": 0.742590103066385, "percentage": 7.25, "elapsed_time": "2:04:08", "remaining_time": "1 day, 2:28:09", "throughput": 4554.95, "total_tokens": 33927616}
{"current_steps": 2905, "total_steps": 40000, "loss": 0.8337, "lr": 4.935256003343426e-05, "epoch": 0.7438704308302926, "percentage": 7.26, "elapsed_time": "2:04:16", "remaining_time": "1 day, 2:26:50", "throughput": 4558.11, "total_tokens": 33986016}
{"current_steps": 2910, "total_steps": 40000, "loss": 0.8097, "lr": 4.93503383525161e-05, "epoch": 0.7451507585942001, "percentage": 7.27, "elapsed_time": "2:04:23", "remaining_time": "1 day, 2:25:30", "throughput": 4561.37, "total_tokens": 34044960}
{"current_steps": 2915, "total_steps": 40000, "loss": 0.847, "lr": 4.934811291646977e-05, "epoch": 0.7464310863581076, "percentage": 7.29, "elapsed_time": "2:04:31", "remaining_time": "1 day, 2:24:13", "throughput": 4564.63, "total_tokens": 34104512}
{"current_steps": 2920, "total_steps": 40000, "loss": 0.8186, "lr": 4.934588372563845e-05, "epoch": 0.7477114141220152, "percentage": 7.3, "elapsed_time": "2:04:39", "remaining_time": "1 day, 2:22:54", "throughput": 4567.93, "total_tokens": 34164000}
{"current_steps": 2925, "total_steps": 40000, "loss": 0.8284, "lr": 4.93436507803659e-05, "epoch": 0.7489917418859228, "percentage": 7.31, "elapsed_time": "2:04:46", "remaining_time": "1 day, 2:21:35", "throughput": 4571.24, "total_tokens": 34223520}
{"current_steps": 2930, "total_steps": 40000, "loss": 0.9035, "lr": 4.934141408099649e-05, "epoch": 0.7502720696498304, "percentage": 7.32, "elapsed_time": "2:04:54", "remaining_time": "1 day, 2:20:17", "throughput": 4574.22, "total_tokens": 34280704}
{"current_steps": 2935, "total_steps": 40000, "loss": 0.8352, "lr": 4.9339173627875135e-05, "epoch": 0.7515523974137379, "percentage": 7.34, "elapsed_time": "2:05:02", "remaining_time": "1 day, 2:19:00", "throughput": 4577.37, "total_tokens": 34339744}
{"current_steps": 2940, "total_steps": 40000, "loss": 0.8584, "lr": 4.9336929421347335e-05, "epoch": 0.7528327251776454, "percentage": 7.35, "elapsed_time": "2:05:09", "remaining_time": "1 day, 2:17:43", "throughput": 4580.58, "total_tokens": 34398848}
{"current_steps": 2945, "total_steps": 40000, "loss": 0.7964, "lr": 4.933468146175918e-05, "epoch": 0.7541130529415531, "percentage": 7.36, "elapsed_time": "2:05:17", "remaining_time": "1 day, 2:16:26", "throughput": 4584.02, "total_tokens": 34459840}
{"current_steps": 2950, "total_steps": 40000, "loss": 0.8903, "lr": 4.933242974945734e-05, "epoch": 0.7553933807054606, "percentage": 7.38, "elapsed_time": "2:05:25", "remaining_time": "1 day, 2:15:09", "throughput": 4587.22, "total_tokens": 34518912}
{"current_steps": 2955, "total_steps": 40000, "loss": 0.8113, "lr": 4.933017428478906e-05, "epoch": 0.7566737084693682, "percentage": 7.39, "elapsed_time": "2:05:32", "remaining_time": "1 day, 2:13:52", "throughput": 4590.28, "total_tokens": 34577056}
{"current_steps": 2960, "total_steps": 40000, "loss": 0.7567, "lr": 4.932791506810214e-05, "epoch": 0.7579540362332757, "percentage": 7.4, "elapsed_time": "2:05:40", "remaining_time": "1 day, 2:12:36", "throughput": 4593.2, "total_tokens": 34634240}
{"current_steps": 2965, "total_steps": 40000, "loss": 0.8356, "lr": 4.932565209974499e-05, "epoch": 0.7592343639971832, "percentage": 7.41, "elapsed_time": "2:05:48", "remaining_time": "1 day, 2:11:20", "throughput": 4596.15, "total_tokens": 34692096}
{"current_steps": 2970, "total_steps": 40000, "loss": 0.7723, "lr": 4.93233853800666e-05, "epoch": 0.7605146917610909, "percentage": 7.42, "elapsed_time": "2:05:55", "remaining_time": "1 day, 2:10:05", "throughput": 4599.21, "total_tokens": 34750432}
{"current_steps": 2975, "total_steps": 40000, "loss": 0.842, "lr": 4.932111490941651e-05, "epoch": 0.7617950195249984, "percentage": 7.44, "elapsed_time": "2:06:03", "remaining_time": "1 day, 2:08:48", "throughput": 4602.43, "total_tokens": 34809824}
{"current_steps": 2980, "total_steps": 40000, "loss": 0.8679, "lr": 4.9318840688144876e-05, "epoch": 0.7630753472889059, "percentage": 7.45, "elapsed_time": "2:06:10", "remaining_time": "1 day, 2:07:32", "throughput": 4605.69, "total_tokens": 34869472}
{"current_steps": 2985, "total_steps": 40000, "loss": 0.7811, "lr": 4.9316562716602387e-05, "epoch": 0.7643556750528135, "percentage": 7.46, "elapsed_time": "2:06:18", "remaining_time": "1 day, 2:06:17", "throughput": 4608.79, "total_tokens": 34928256}
{"current_steps": 2990, "total_steps": 40000, "loss": 0.7947, "lr": 4.9314280995140346e-05, "epoch": 0.7656360028167211, "percentage": 7.47, "elapsed_time": "2:06:26", "remaining_time": "1 day, 2:05:02", "throughput": 4611.91, "total_tokens": 34987168}
{"current_steps": 2995, "total_steps": 40000, "loss": 0.7945, "lr": 4.931199552411063e-05, "epoch": 0.7669163305806287, "percentage": 7.49, "elapsed_time": "2:06:33", "remaining_time": "1 day, 2:03:48", "throughput": 4614.78, "total_tokens": 35044512}
{"current_steps": 3000, "total_steps": 40000, "loss": 0.8074, "lr": 4.930970630386568e-05, "epoch": 0.7681966583445362, "percentage": 7.5, "elapsed_time": "2:06:41", "remaining_time": "1 day, 2:02:33", "throughput": 4617.83, "total_tokens": 35103200}
{"current_steps": 3000, "total_steps": 40000, "eval_loss": 0.803777813911438, "epoch": 0.7681966583445362, "percentage": 7.5, "elapsed_time": "2:10:17", "remaining_time": "1 day, 2:46:53", "throughput": 4490.43, "total_tokens": 35103200}
{"current_steps": 3005, "total_steps": 40000, "loss": 0.7873, "lr": 4.9307413334758524e-05, "epoch": 0.7694769861084437, "percentage": 7.51, "elapsed_time": "2:10:28", "remaining_time": "1 day, 2:46:22", "throughput": 4491.25, "total_tokens": 35161632}
{"current_steps": 3010, "total_steps": 40000, "loss": 0.7362, "lr": 4.930511661714276e-05, "epoch": 0.7707573138723514, "percentage": 7.52, "elapsed_time": "2:10:36", "remaining_time": "1 day, 2:45:04", "throughput": 4494.1, "total_tokens": 35218688}
{"current_steps": 3015, "total_steps": 40000, "loss": 0.8188, "lr": 4.9302816151372576e-05, "epoch": 0.7720376416362589, "percentage": 7.54, "elapsed_time": "2:10:44", "remaining_time": "1 day, 2:43:47", "throughput": 4497.16, "total_tokens": 35277536}
{"current_steps": 3020, "total_steps": 40000, "loss": 0.8488, "lr": 4.930051193780274e-05, "epoch": 0.7733179694001664, "percentage": 7.55, "elapsed_time": "2:10:52", "remaining_time": "1 day, 2:42:29", "throughput": 4500.29, "total_tokens": 35336768}
{"current_steps": 3025, "total_steps": 40000, "loss": 0.7329, "lr": 4.929820397678858e-05, "epoch": 0.774598297164074, "percentage": 7.56, "elapsed_time": "2:10:59", "remaining_time": "1 day, 2:41:11", "throughput": 4503.31, "total_tokens": 35395296}
{"current_steps": 3030, "total_steps": 40000, "loss": 0.8401, "lr": 4.9295892268686015e-05, "epoch": 0.7758786249279815, "percentage": 7.58, "elapsed_time": "2:11:07", "remaining_time": "1 day, 2:39:54", "throughput": 4506.3, "total_tokens": 35453440}
{"current_steps": 3035, "total_steps": 40000, "loss": 0.7546, "lr": 4.9293576813851536e-05, "epoch": 0.7771589526918892, "percentage": 7.59, "elapsed_time": "2:11:15", "remaining_time": "1 day, 2:38:37", "throughput": 4509.46, "total_tokens": 35513280}
{"current_steps": 3040, "total_steps": 40000, "loss": 0.7789, "lr": 4.929125761264223e-05, "epoch": 0.7784392804557967, "percentage": 7.6, "elapsed_time": "2:11:23", "remaining_time": "1 day, 2:37:21", "throughput": 4512.5, "total_tokens": 35572288}
{"current_steps": 3045, "total_steps": 40000, "loss": 0.7361, "lr": 4.928893466541573e-05, "epoch": 0.7797196082197042, "percentage": 7.61, "elapsed_time": "2:11:30", "remaining_time": "1 day, 2:36:04", "throughput": 4515.41, "total_tokens": 35630112}
{"current_steps": 3050, "total_steps": 40000, "loss": 0.7611, "lr": 4.928660797253027e-05, "epoch": 0.7809999359836118, "percentage": 7.62, "elapsed_time": "2:11:38", "remaining_time": "1 day, 2:34:48", "throughput": 4518.66, "total_tokens": 35690688}
{"current_steps": 3055, "total_steps": 40000, "loss": 0.7363, "lr": 4.928427753434467e-05, "epoch": 0.7822802637475194, "percentage": 7.64, "elapsed_time": "2:11:46", "remaining_time": "1 day, 2:33:32", "throughput": 4521.54, "total_tokens": 35748256}
{"current_steps": 3060, "total_steps": 40000, "loss": 0.7362, "lr": 4.9281943351218286e-05, "epoch": 0.7835605915114269, "percentage": 7.65, "elapsed_time": "2:11:53", "remaining_time": "1 day, 2:32:15", "throughput": 4524.53, "total_tokens": 35806656}
{"current_steps": 3065, "total_steps": 40000, "loss": 0.7539, "lr": 4.9279605423511095e-05, "epoch": 0.7848409192753345, "percentage": 7.66, "elapsed_time": "2:12:01", "remaining_time": "1 day, 2:31:00", "throughput": 4527.57, "total_tokens": 35865824}
{"current_steps": 3070, "total_steps": 40000, "loss": 0.8024, "lr": 4.927726375158363e-05, "epoch": 0.786121247039242, "percentage": 7.67, "elapsed_time": "2:12:09", "remaining_time": "1 day, 2:29:45", "throughput": 4530.43, "total_tokens": 35923680}
{"current_steps": 3075, "total_steps": 40000, "loss": 0.7572, "lr": 4.9274918335797004e-05, "epoch": 0.7874015748031497, "percentage": 7.69, "elapsed_time": "2:12:17", "remaining_time": "1 day, 2:28:29", "throughput": 4533.24, "total_tokens": 35980864}
{"current_steps": 3080, "total_steps": 40000, "loss": 0.7703, "lr": 4.927256917651292e-05, "epoch": 0.7886819025670572, "percentage": 7.7, "elapsed_time": "2:12:24", "remaining_time": "1 day, 2:27:15", "throughput": 4536.38, "total_tokens": 36041184}
{"current_steps": 3085, "total_steps": 40000, "loss": 0.8065, "lr": 4.927021627409364e-05, "epoch": 0.7899622303309647, "percentage": 7.71, "elapsed_time": "2:12:32", "remaining_time": "1 day, 2:26:02", "throughput": 4539.24, "total_tokens": 36099424}
{"current_steps": 3090, "total_steps": 40000, "loss": 0.8066, "lr": 4.9267859628902005e-05, "epoch": 0.7912425580948723, "percentage": 7.72, "elapsed_time": "2:12:40", "remaining_time": "1 day, 2:24:48", "throughput": 4542.06, "total_tokens": 36157312}
{"current_steps": 3095, "total_steps": 40000, "loss": 0.7515, "lr": 4.9265499241301454e-05, "epoch": 0.7925228858587798, "percentage": 7.74, "elapsed_time": "2:12:48", "remaining_time": "1 day, 2:23:34", "throughput": 4544.85, "total_tokens": 36214848}
{"current_steps": 3100, "total_steps": 40000, "loss": 0.7925, "lr": 4.926313511165598e-05, "epoch": 0.7938032136226874, "percentage": 7.75, "elapsed_time": "2:12:56", "remaining_time": "1 day, 2:22:20", "throughput": 4547.73, "total_tokens": 36272928}
{"current_steps": 3105, "total_steps": 40000, "loss": 0.9524, "lr": 4.926076724033016e-05, "epoch": 0.795083541386595, "percentage": 7.76, "elapsed_time": "2:13:03", "remaining_time": "1 day, 2:21:07", "throughput": 4550.71, "total_tokens": 36332096}
{"current_steps": 3110, "total_steps": 40000, "loss": 0.8088, "lr": 4.9258395627689146e-05, "epoch": 0.7963638691505025, "percentage": 7.78, "elapsed_time": "2:13:11", "remaining_time": "1 day, 2:19:53", "throughput": 4553.78, "total_tokens": 36391648}
{"current_steps": 3115, "total_steps": 40000, "loss": 0.7802, "lr": 4.925602027409868e-05, "epoch": 0.7976441969144101, "percentage": 7.79, "elapsed_time": "2:13:19", "remaining_time": "1 day, 2:18:40", "throughput": 4556.67, "total_tokens": 36450016}
{"current_steps": 3120, "total_steps": 40000, "loss": 0.7654, "lr": 4.925364117992507e-05, "epoch": 0.7989245246783176, "percentage": 7.8, "elapsed_time": "2:13:27", "remaining_time": "1 day, 2:17:27", "throughput": 4559.68, "total_tokens": 36509504}
{"current_steps": 3125, "total_steps": 40000, "loss": 0.8312, "lr": 4.92512583455352e-05, "epoch": 0.8002048524422252, "percentage": 7.81, "elapsed_time": "2:13:34", "remaining_time": "1 day, 2:16:14", "throughput": 4562.66, "total_tokens": 36568608}
{"current_steps": 3130, "total_steps": 40000, "loss": 0.7969, "lr": 4.9248871771296536e-05, "epoch": 0.8014851802061328, "percentage": 7.83, "elapsed_time": "2:13:42", "remaining_time": "1 day, 2:15:01", "throughput": 4565.64, "total_tokens": 36627776}
{"current_steps": 3135, "total_steps": 40000, "loss": 0.7989, "lr": 4.924648145757711e-05, "epoch": 0.8027655079700403, "percentage": 7.84, "elapsed_time": "2:13:50", "remaining_time": "1 day, 2:13:48", "throughput": 4568.41, "total_tokens": 36685344}
{"current_steps": 3140, "total_steps": 40000, "loss": 0.7553, "lr": 4.924408740474554e-05, "epoch": 0.804045835733948, "percentage": 7.85, "elapsed_time": "2:13:58", "remaining_time": "1 day, 2:12:37", "throughput": 4571.06, "total_tokens": 36742272}
{"current_steps": 3145, "total_steps": 40000, "loss": 0.8072, "lr": 4.924168961317103e-05, "epoch": 0.8053261634978555, "percentage": 7.86, "elapsed_time": "2:14:05", "remaining_time": "1 day, 2:11:24", "throughput": 4573.95, "total_tokens": 36800896}
{"current_steps": 3150, "total_steps": 40000, "loss": 0.7994, "lr": 4.9239288083223334e-05, "epoch": 0.806606491261763, "percentage": 7.88, "elapsed_time": "2:14:13", "remaining_time": "1 day, 2:10:13", "throughput": 4576.68, "total_tokens": 36858368}
{"current_steps": 3155, "total_steps": 40000, "loss": 0.8115, "lr": 4.9236882815272803e-05, "epoch": 0.8078868190256706, "percentage": 7.89, "elapsed_time": "2:14:21", "remaining_time": "1 day, 2:09:01", "throughput": 4579.55, "total_tokens": 36916992}
{"current_steps": 3160, "total_steps": 40000, "loss": 0.7375, "lr": 4.9234473809690365e-05, "epoch": 0.8091671467895781, "percentage": 7.9, "elapsed_time": "2:14:29", "remaining_time": "1 day, 2:07:50", "throughput": 4582.5, "total_tokens": 36976288}
{"current_steps": 3165, "total_steps": 40000, "loss": 0.746, "lr": 4.923206106684752e-05, "epoch": 0.8104474745534856, "percentage": 7.91, "elapsed_time": "2:14:36", "remaining_time": "1 day, 2:06:38", "throughput": 4585.19, "total_tokens": 37033280}
{"current_steps": 3170, "total_steps": 40000, "loss": 0.8177, "lr": 4.922964458711634e-05, "epoch": 0.8117278023173933, "percentage": 7.92, "elapsed_time": "2:14:44", "remaining_time": "1 day, 2:05:27", "throughput": 4588.1, "total_tokens": 37092352}
{"current_steps": 3175, "total_steps": 40000, "loss": 0.788, "lr": 4.9227224370869474e-05, "epoch": 0.8130081300813008, "percentage": 7.94, "elapsed_time": "2:14:52", "remaining_time": "1 day, 2:04:17", "throughput": 4591.18, "total_tokens": 37152864}
{"current_steps": 3180, "total_steps": 40000, "loss": 0.8352, "lr": 4.9224800418480155e-05, "epoch": 0.8142884578452084, "percentage": 7.95, "elapsed_time": "2:15:00", "remaining_time": "1 day, 2:03:06", "throughput": 4594.15, "total_tokens": 37212608}
{"current_steps": 3185, "total_steps": 40000, "loss": 0.7544, "lr": 4.9222372730322176e-05, "epoch": 0.8155687856091159, "percentage": 7.96, "elapsed_time": "2:15:07", "remaining_time": "1 day, 2:01:55", "throughput": 4597.03, "total_tokens": 37271200}
{"current_steps": 3190, "total_steps": 40000, "loss": 0.8434, "lr": 4.921994130676993e-05, "epoch": 0.8168491133730235, "percentage": 7.98, "elapsed_time": "2:15:15", "remaining_time": "1 day, 2:00:47", "throughput": 4599.63, "total_tokens": 37328832}
{"current_steps": 3195, "total_steps": 40000, "loss": 0.7445, "lr": 4.9217506148198366e-05, "epoch": 0.8181294411369311, "percentage": 7.99, "elapsed_time": "2:15:23", "remaining_time": "1 day, 1:59:38", "throughput": 4602.37, "total_tokens": 37386912}
{"current_steps": 3200, "total_steps": 40000, "loss": 0.792, "lr": 4.921506725498302e-05, "epoch": 0.8194097689008386, "percentage": 8.0, "elapsed_time": "2:15:31", "remaining_time": "1 day, 1:58:27", "throughput": 4605.29, "total_tokens": 37446112}
{"current_steps": 3200, "total_steps": 40000, "eval_loss": 0.7968230247497559, "epoch": 0.8194097689008386, "percentage": 8.0, "elapsed_time": "2:19:03", "remaining_time": "1 day, 2:39:11", "throughput": 4488.0, "total_tokens": 37446112}
{"current_steps": 3205, "total_steps": 40000, "loss": 0.824, "lr": 4.9212624627499994e-05, "epoch": 0.8206900966647461, "percentage": 8.01, "elapsed_time": "2:19:13", "remaining_time": "1 day, 2:38:23", "throughput": 4489.81, "total_tokens": 37506048}
{"current_steps": 3210, "total_steps": 40000, "loss": 0.8008, "lr": 4.921017826612597e-05, "epoch": 0.8219704244286538, "percentage": 8.03, "elapsed_time": "2:19:21", "remaining_time": "1 day, 2:37:08", "throughput": 4492.64, "total_tokens": 37564064}
{"current_steps": 3215, "total_steps": 40000, "loss": 0.7904, "lr": 4.9207728171238223e-05, "epoch": 0.8232507521925613, "percentage": 8.04, "elapsed_time": "2:19:28", "remaining_time": "1 day, 2:35:54", "throughput": 4495.51, "total_tokens": 37622464}
{"current_steps": 3220, "total_steps": 40000, "loss": 0.7933, "lr": 4.920527434321458e-05, "epoch": 0.8245310799564689, "percentage": 8.05, "elapsed_time": "2:19:36", "remaining_time": "1 day, 2:34:40", "throughput": 4498.29, "total_tokens": 37680288}
{"current_steps": 3225, "total_steps": 40000, "loss": 0.7549, "lr": 4.920281678243345e-05, "epoch": 0.8258114077203764, "percentage": 8.06, "elapsed_time": "2:19:44", "remaining_time": "1 day, 2:33:26", "throughput": 4501.36, "total_tokens": 37740448}
{"current_steps": 3230, "total_steps": 40000, "loss": 0.8536, "lr": 4.920035548927381e-05, "epoch": 0.8270917354842839, "percentage": 8.08, "elapsed_time": "2:19:51", "remaining_time": "1 day, 2:32:12", "throughput": 4504.05, "total_tokens": 37797664}
{"current_steps": 3235, "total_steps": 40000, "loss": 0.8406, "lr": 4.919789046411525e-05, "epoch": 0.8283720632481916, "percentage": 8.09, "elapsed_time": "2:19:59", "remaining_time": "1 day, 2:30:58", "throughput": 4506.89, "total_tokens": 37855840}
{"current_steps": 3240, "total_steps": 40000, "loss": 0.6978, "lr": 4.919542170733787e-05, "epoch": 0.8296523910120991, "percentage": 8.1, "elapsed_time": "2:20:07", "remaining_time": "1 day, 2:29:45", "throughput": 4509.83, "total_tokens": 37915296}
{"current_steps": 3245, "total_steps": 40000, "loss": 0.787, "lr": 4.919294921932242e-05, "epoch": 0.8309327187760066, "percentage": 8.11, "elapsed_time": "2:20:14", "remaining_time": "1 day, 2:28:33", "throughput": 4512.72, "total_tokens": 37974272}
{"current_steps": 3250, "total_steps": 40000, "loss": 0.841, "lr": 4.919047300045016e-05, "epoch": 0.8322130465399142, "percentage": 8.12, "elapsed_time": "2:20:22", "remaining_time": "1 day, 2:27:19", "throughput": 4515.5, "total_tokens": 38031968}
{"current_steps": 3255, "total_steps": 40000, "loss": 0.7002, "lr": 4.918799305110299e-05, "epoch": 0.8334933743038218, "percentage": 8.14, "elapsed_time": "2:20:30", "remaining_time": "1 day, 2:26:07", "throughput": 4518.18, "total_tokens": 38089408}
{"current_steps": 3260, "total_steps": 40000, "loss": 0.7806, "lr": 4.918550937166331e-05, "epoch": 0.8347737020677294, "percentage": 8.15, "elapsed_time": "2:20:37", "remaining_time": "1 day, 2:24:54", "throughput": 4521.02, "total_tokens": 38147904}
{"current_steps": 3265, "total_steps": 40000, "loss": 0.7361, "lr": 4.918302196251415e-05, "epoch": 0.8360540298316369, "percentage": 8.16, "elapsed_time": "2:20:45", "remaining_time": "1 day, 2:23:41", "throughput": 4523.94, "total_tokens": 38206976}
{"current_steps": 3270, "total_steps": 40000, "loss": 0.75, "lr": 4.91805308240391e-05, "epoch": 0.8373343575955444, "percentage": 8.18, "elapsed_time": "2:20:53", "remaining_time": "1 day, 2:22:29", "throughput": 4526.77, "total_tokens": 38265536}
{"current_steps": 3275, "total_steps": 40000, "loss": 0.7943, "lr": 4.9178035956622326e-05, "epoch": 0.838614685359452, "percentage": 8.19, "elapsed_time": "2:21:00", "remaining_time": "1 day, 2:21:17", "throughput": 4529.52, "total_tokens": 38323360}
{"current_steps": 3280, "total_steps": 40000, "loss": 0.7836, "lr": 4.917553736064857e-05, "epoch": 0.8398950131233596, "percentage": 8.2, "elapsed_time": "2:21:08", "remaining_time": "1 day, 2:20:05", "throughput": 4532.34, "total_tokens": 38382016}
{"current_steps": 3285, "total_steps": 40000, "loss": 0.7325, "lr": 4.917303503650314e-05, "epoch": 0.8411753408872671, "percentage": 8.21, "elapsed_time": "2:21:16", "remaining_time": "1 day, 2:18:53", "throughput": 4535.25, "total_tokens": 38441280}
{"current_steps": 3290, "total_steps": 40000, "loss": 0.7758, "lr": 4.917052898457194e-05, "epoch": 0.8424556686511747, "percentage": 8.22, "elapsed_time": "2:21:23", "remaining_time": "1 day, 2:17:41", "throughput": 4537.95, "total_tokens": 38498784}
{"current_steps": 3295, "total_steps": 40000, "loss": 0.8314, "lr": 4.916801920524141e-05, "epoch": 0.8437359964150822, "percentage": 8.24, "elapsed_time": "2:21:31", "remaining_time": "1 day, 2:16:30", "throughput": 4540.73, "total_tokens": 38557024}
{"current_steps": 3300, "total_steps": 40000, "loss": 0.8158, "lr": 4.916550569889862e-05, "epoch": 0.8450163241789899, "percentage": 8.25, "elapsed_time": "2:21:39", "remaining_time": "1 day, 2:15:19", "throughput": 4543.7, "total_tokens": 38617120}
{"current_steps": 3305, "total_steps": 40000, "loss": 0.804, "lr": 4.916298846593116e-05, "epoch": 0.8462966519428974, "percentage": 8.26, "elapsed_time": "2:21:46", "remaining_time": "1 day, 2:14:09", "throughput": 4546.22, "total_tokens": 38673408}
{"current_steps": 3310, "total_steps": 40000, "loss": 0.8981, "lr": 4.916046750672722e-05, "epoch": 0.8475769797068049, "percentage": 8.28, "elapsed_time": "2:21:54", "remaining_time": "1 day, 2:12:58", "throughput": 4548.94, "total_tokens": 38731264}
{"current_steps": 3315, "total_steps": 40000, "loss": 0.8397, "lr": 4.915794282167559e-05, "epoch": 0.8488573074707125, "percentage": 8.29, "elapsed_time": "2:22:01", "remaining_time": "1 day, 2:11:47", "throughput": 4551.66, "total_tokens": 38789216}
{"current_steps": 3320, "total_steps": 40000, "loss": 0.777, "lr": 4.915541441116558e-05, "epoch": 0.85013763523462, "percentage": 8.3, "elapsed_time": "2:22:09", "remaining_time": "1 day, 2:10:36", "throughput": 4554.42, "total_tokens": 38847424}
{"current_steps": 3325, "total_steps": 40000, "loss": 0.8523, "lr": 4.915288227558711e-05, "epoch": 0.8514179629985277, "percentage": 8.31, "elapsed_time": "2:22:17", "remaining_time": "1 day, 2:09:26", "throughput": 4557.11, "total_tokens": 38905248}
{"current_steps": 3330, "total_steps": 40000, "loss": 0.9021, "lr": 4.915034641533066e-05, "epoch": 0.8526982907624352, "percentage": 8.33, "elapsed_time": "2:22:24", "remaining_time": "1 day, 2:08:17", "throughput": 4559.88, "total_tokens": 38964064}
{"current_steps": 3335, "total_steps": 40000, "loss": 0.8874, "lr": 4.914780683078731e-05, "epoch": 0.8539786185263427, "percentage": 8.34, "elapsed_time": "2:22:32", "remaining_time": "1 day, 2:07:07", "throughput": 4562.62, "total_tokens": 39022400}
{"current_steps": 3340, "total_steps": 40000, "loss": 0.751, "lr": 4.9145263522348695e-05, "epoch": 0.8552589462902503, "percentage": 8.35, "elapsed_time": "2:22:40", "remaining_time": "1 day, 2:06:01", "throughput": 4565.17, "total_tokens": 39080704}
{"current_steps": 3345, "total_steps": 40000, "loss": 0.733, "lr": 4.9142716490407e-05, "epoch": 0.8565392740541579, "percentage": 8.36, "elapsed_time": "2:22:48", "remaining_time": "1 day, 2:04:53", "throughput": 4567.86, "total_tokens": 39139040}
{"current_steps": 3350, "total_steps": 40000, "loss": 0.7762, "lr": 4.914016573535504e-05, "epoch": 0.8578196018180654, "percentage": 8.38, "elapsed_time": "2:22:56", "remaining_time": "1 day, 2:03:44", "throughput": 4570.68, "total_tokens": 39198336}
{"current_steps": 3355, "total_steps": 40000, "loss": 0.8284, "lr": 4.9137611257586154e-05, "epoch": 0.859099929581973, "percentage": 8.39, "elapsed_time": "2:23:03", "remaining_time": "1 day, 2:02:35", "throughput": 4573.47, "total_tokens": 39257536}
{"current_steps": 3360, "total_steps": 40000, "loss": 0.8239, "lr": 4.9135053057494274e-05, "epoch": 0.8603802573458805, "percentage": 8.4, "elapsed_time": "2:23:11", "remaining_time": "1 day, 2:01:26", "throughput": 4576.25, "total_tokens": 39316224}
{"current_steps": 3365, "total_steps": 40000, "loss": 0.8161, "lr": 4.913249113547392e-05, "epoch": 0.8616605851097882, "percentage": 8.41, "elapsed_time": "2:23:19", "remaining_time": "1 day, 2:00:18", "throughput": 4579.06, "total_tokens": 39375360}
{"current_steps": 3370, "total_steps": 40000, "loss": 0.7919, "lr": 4.912992549192016e-05, "epoch": 0.8629409128736957, "percentage": 8.43, "elapsed_time": "2:23:26", "remaining_time": "1 day, 1:59:09", "throughput": 4581.8, "total_tokens": 39433984}
{"current_steps": 3375, "total_steps": 40000, "loss": 0.7565, "lr": 4.9127356127228665e-05, "epoch": 0.8642212406376032, "percentage": 8.44, "elapsed_time": "2:23:34", "remaining_time": "1 day, 1:58:00", "throughput": 4584.67, "total_tokens": 39493600}
{"current_steps": 3380, "total_steps": 40000, "loss": 0.7437, "lr": 4.912478304179564e-05, "epoch": 0.8655015684015108, "percentage": 8.45, "elapsed_time": "2:23:41", "remaining_time": "1 day, 1:56:52", "throughput": 4587.16, "total_tokens": 39550112}
{"current_steps": 3385, "total_steps": 40000, "loss": 0.7345, "lr": 4.9122206236017896e-05, "epoch": 0.8667818961654183, "percentage": 8.46, "elapsed_time": "2:23:49", "remaining_time": "1 day, 1:55:44", "throughput": 4589.74, "total_tokens": 39607520}
{"current_steps": 3390, "total_steps": 40000, "loss": 0.8217, "lr": 4.911962571029282e-05, "epoch": 0.8680622239293259, "percentage": 8.48, "elapsed_time": "2:23:57", "remaining_time": "1 day, 1:54:37", "throughput": 4592.35, "total_tokens": 39665216}
{"current_steps": 3395, "total_steps": 40000, "loss": 0.728, "lr": 4.9117041465018353e-05, "epoch": 0.8693425516932335, "percentage": 8.49, "elapsed_time": "2:24:04", "remaining_time": "1 day, 1:53:29", "throughput": 4595.09, "total_tokens": 39724128}
{"current_steps": 3400, "total_steps": 40000, "loss": 0.7444, "lr": 4.911445350059302e-05, "epoch": 0.870622879457141, "percentage": 8.5, "elapsed_time": "2:24:12", "remaining_time": "1 day, 1:52:22", "throughput": 4597.66, "total_tokens": 39781504}
{"current_steps": 3400, "total_steps": 40000, "eval_loss": 0.7906654477119446, "epoch": 0.870622879457141, "percentage": 8.5, "elapsed_time": "2:27:45", "remaining_time": "1 day, 2:30:32", "throughput": 4487.3, "total_tokens": 39781504}