|
{"current_steps": 1, "total_steps": 85, "loss": 1.2528, "lr": 4.998292650357558e-05, "epoch": 0.01167883211678832, "percentage": 1.18, "elapsed_time": "0:02:39", "remaining_time": "3:43:53", "throughput": 9835.11, "total_tokens": 1572864} |
|
{"current_steps": 2, "total_steps": 85, "loss": 1.1456, "lr": 4.993172933464471e-05, "epoch": 0.02335766423357664, "percentage": 2.35, "elapsed_time": "0:05:13", "remaining_time": "3:36:42", "throughput": 10039.91, "total_tokens": 3145728} |
|
{"current_steps": 3, "total_steps": 85, "loss": 1.0528, "lr": 4.984647842238185e-05, "epoch": 0.035036496350364967, "percentage": 3.53, "elapsed_time": "0:07:46", "remaining_time": "3:32:28", "throughput": 10116.78, "total_tokens": 4718592} |
|
{"current_steps": 4, "total_steps": 85, "loss": 0.9542, "lr": 4.972729020927865e-05, "epoch": 0.04671532846715328, "percentage": 4.71, "elapsed_time": "0:10:19", "remaining_time": "3:29:06", "throughput": 10154.68, "total_tokens": 6291456} |
|
{"current_steps": 5, "total_steps": 85, "loss": 0.8888, "lr": 4.957432749209755e-05, "epoch": 0.058394160583941604, "percentage": 5.88, "elapsed_time": "0:12:52", "remaining_time": "3:26:05", "throughput": 10175.92, "total_tokens": 7864320} |
|
{"current_steps": 6, "total_steps": 85, "loss": 0.8125, "lr": 4.938779919951092e-05, "epoch": 0.07007299270072993, "percentage": 7.06, "elapsed_time": "0:15:27", "remaining_time": "3:23:28", "throughput": 10177.83, "total_tokens": 9437184} |
|
{"current_steps": 7, "total_steps": 85, "loss": 0.7639, "lr": 4.916796010672969e-05, "epoch": 0.08175182481751825, "percentage": 8.24, "elapsed_time": "0:18:00", "remaining_time": "3:20:43", "throughput": 10187.1, "total_tokens": 11010048} |
|
{"current_steps": 8, "total_steps": 85, "loss": 0.7068, "lr": 4.891511048751102e-05, "epoch": 0.09343065693430656, "percentage": 9.41, "elapsed_time": "0:20:33", "remaining_time": "3:17:55", "throughput": 10197.99, "total_tokens": 12582912} |
|
{"current_steps": 9, "total_steps": 85, "loss": 0.6852, "lr": 4.862959570402049e-05, "epoch": 0.10510948905109489, "percentage": 10.59, "elapsed_time": "0:23:07", "remaining_time": "3:15:12", "throughput": 10205.83, "total_tokens": 14155776} |
|
{"current_steps": 10, "total_steps": 85, "loss": 0.6571, "lr": 4.8311805735108894e-05, "epoch": 0.11678832116788321, "percentage": 11.76, "elapsed_time": "0:25:40", "remaining_time": "3:12:32", "throughput": 10211.26, "total_tokens": 15728640} |
|
{"current_steps": 11, "total_steps": 85, "loss": 0.6347, "lr": 4.796217464364808e-05, "epoch": 0.12846715328467154, "percentage": 12.94, "elapsed_time": "0:28:13", "remaining_time": "3:09:52", "throughput": 10216.6, "total_tokens": 17301504} |
|
{"current_steps": 12, "total_steps": 85, "loss": 0.6191, "lr": 4.758117998365322e-05, "epoch": 0.14014598540145987, "percentage": 14.12, "elapsed_time": "0:30:46", "remaining_time": "3:07:13", "throughput": 10220.74, "total_tokens": 18874368} |
|
{"current_steps": 13, "total_steps": 85, "loss": 0.5761, "lr": 4.716934214800155e-05, "epoch": 0.15182481751824817, "percentage": 15.29, "elapsed_time": "0:33:19", "remaining_time": "3:04:36", "throughput": 10224.2, "total_tokens": 20447232} |
|
{"current_steps": 14, "total_steps": 85, "loss": 0.5772, "lr": 4.672722365763821e-05, "epoch": 0.1635036496350365, "percentage": 16.47, "elapsed_time": "0:35:53", "remaining_time": "3:01:59", "throughput": 10227.13, "total_tokens": 22020096} |
|
{"current_steps": 15, "total_steps": 85, "loss": 0.5579, "lr": 4.625542839324036e-05, "epoch": 0.17518248175182483, "percentage": 17.65, "elapsed_time": "0:38:26", "remaining_time": "2:59:22", "throughput": 10229.7, "total_tokens": 23592960} |
|
{"current_steps": 16, "total_steps": 85, "loss": 0.5674, "lr": 4.575460077038877e-05, "epoch": 0.18686131386861313, "percentage": 18.82, "elapsed_time": "0:40:59", "remaining_time": "2:56:45", "throughput": 10233.46, "total_tokens": 25165824} |
|
{"current_steps": 17, "total_steps": 85, "loss": 0.5767, "lr": 4.522542485937369e-05, "epoch": 0.19854014598540146, "percentage": 20.0, "elapsed_time": "0:43:32", "remaining_time": "2:54:09", "throughput": 10235.03, "total_tokens": 26738688} |
|
{"current_steps": 18, "total_steps": 85, "loss": 0.5559, "lr": 4.4668623450837085e-05, "epoch": 0.21021897810218979, "percentage": 21.18, "elapsed_time": "0:46:05", "remaining_time": "2:51:34", "throughput": 10236.83, "total_tokens": 28311552} |
|
{"current_steps": 19, "total_steps": 85, "loss": 0.5603, "lr": 4.408495706852758e-05, "epoch": 0.22189781021897811, "percentage": 22.35, "elapsed_time": "0:48:38", "remaining_time": "2:48:59", "throughput": 10238.16, "total_tokens": 29884416} |
|
{"current_steps": 20, "total_steps": 85, "loss": 0.5541, "lr": 4.347522293051648e-05, "epoch": 0.23357664233576642, "percentage": 23.53, "elapsed_time": "0:51:12", "remaining_time": "2:46:24", "throughput": 10239.41, "total_tokens": 31457280} |
|
{"current_steps": 21, "total_steps": 85, "loss": 0.5358, "lr": 4.284025386029381e-05, "epoch": 0.24525547445255474, "percentage": 24.71, "elapsed_time": "0:53:45", "remaining_time": "2:43:49", "throughput": 10240.84, "total_tokens": 33030144} |
|
{"current_steps": 22, "total_steps": 85, "loss": 0.529, "lr": 4.218091714923157e-05, "epoch": 0.2569343065693431, "percentage": 25.88, "elapsed_time": "0:56:18", "remaining_time": "2:41:14", "throughput": 10242.63, "total_tokens": 34603008} |
|
{"current_steps": 23, "total_steps": 85, "loss": 0.5391, "lr": 4.149811337196807e-05, "epoch": 0.2686131386861314, "percentage": 27.06, "elapsed_time": "0:58:51", "remaining_time": "2:38:39", "throughput": 10243.79, "total_tokens": 36175872} |
|
{"current_steps": 24, "total_steps": 85, "loss": 0.5368, "lr": 4.079277515633127e-05, "epoch": 0.28029197080291973, "percentage": 28.24, "elapsed_time": "1:01:24", "remaining_time": "2:36:05", "throughput": 10244.74, "total_tokens": 37748736} |
|
{"current_steps": 25, "total_steps": 85, "loss": 0.5226, "lr": 4.0065865909481417e-05, "epoch": 0.291970802919708, "percentage": 29.41, "elapsed_time": "1:03:57", "remaining_time": "2:33:31", "throughput": 10245.36, "total_tokens": 39321600} |
|
{"current_steps": 26, "total_steps": 85, "loss": 0.5181, "lr": 3.931837850201263e-05, "epoch": 0.30364963503649633, "percentage": 30.59, "elapsed_time": "1:06:31", "remaining_time": "2:30:57", "throughput": 10245.84, "total_tokens": 40894464} |
|
{"current_steps": 27, "total_steps": 85, "loss": 0.5368, "lr": 3.855133391181124e-05, "epoch": 0.31532846715328466, "percentage": 31.76, "elapsed_time": "1:09:04", "remaining_time": "2:28:23", "throughput": 10246.61, "total_tokens": 42467328} |
|
{"current_steps": 28, "total_steps": 85, "loss": 0.5143, "lr": 3.7765779829522675e-05, "epoch": 0.327007299270073, "percentage": 32.94, "elapsed_time": "1:11:37", "remaining_time": "2:25:49", "throughput": 10247.05, "total_tokens": 44040192} |
|
{"current_steps": 29, "total_steps": 85, "loss": 0.5084, "lr": 3.696278922753216e-05, "epoch": 0.3386861313868613, "percentage": 34.12, "elapsed_time": "1:14:11", "remaining_time": "2:23:15", "throughput": 10247.38, "total_tokens": 45613056} |
|
{"current_steps": 30, "total_steps": 85, "loss": 0.5026, "lr": 3.6143458894413465e-05, "epoch": 0.35036496350364965, "percentage": 35.29, "elapsed_time": "1:16:44", "remaining_time": "2:20:41", "throughput": 10247.73, "total_tokens": 47185920} |
|
{"current_steps": 31, "total_steps": 85, "loss": 0.53, "lr": 3.5308907936847594e-05, "epoch": 0.362043795620438, "percentage": 36.47, "elapsed_time": "1:19:17", "remaining_time": "2:18:07", "throughput": 10248.1, "total_tokens": 48758784} |
|
{"current_steps": 32, "total_steps": 85, "loss": 0.532, "lr": 3.446027625105776e-05, "epoch": 0.37372262773722625, "percentage": 37.65, "elapsed_time": "1:21:51", "remaining_time": "2:15:33", "throughput": 10248.71, "total_tokens": 50331648} |
|
{"current_steps": 33, "total_steps": 85, "loss": 0.5257, "lr": 3.3598722965848204e-05, "epoch": 0.3854014598540146, "percentage": 38.82, "elapsed_time": "1:24:24", "remaining_time": "2:13:00", "throughput": 10248.92, "total_tokens": 51904512} |
|
{"current_steps": 34, "total_steps": 85, "loss": 0.5078, "lr": 3.272542485937369e-05, "epoch": 0.3970802919708029, "percentage": 40.0, "elapsed_time": "1:26:57", "remaining_time": "2:10:26", "throughput": 10249.4, "total_tokens": 53477376} |
|
{"current_steps": 35, "total_steps": 85, "loss": 0.5012, "lr": 3.1841574751802076e-05, "epoch": 0.40875912408759124, "percentage": 41.18, "elapsed_time": "1:29:30", "remaining_time": "2:07:52", "throughput": 10249.82, "total_tokens": 55050240} |
|
{"current_steps": 36, "total_steps": 85, "loss": 0.5117, "lr": 3.094837987606547e-05, "epoch": 0.42043795620437957, "percentage": 42.35, "elapsed_time": "1:32:04", "remaining_time": "2:05:19", "throughput": 10250.03, "total_tokens": 56623104} |
|
{"current_steps": 37, "total_steps": 85, "loss": 0.516, "lr": 3.0047060228925256e-05, "epoch": 0.4321167883211679, "percentage": 43.53, "elapsed_time": "1:34:37", "remaining_time": "2:02:45", "throughput": 10250.39, "total_tokens": 58195968} |
|
{"current_steps": 38, "total_steps": 85, "loss": 0.5189, "lr": 2.913884690460325e-05, "epoch": 0.44379562043795623, "percentage": 44.71, "elapsed_time": "1:37:10", "remaining_time": "2:00:11", "throughput": 10250.64, "total_tokens": 59768832} |
|
{"current_steps": 39, "total_steps": 85, "loss": 0.4973, "lr": 2.8224980413255086e-05, "epoch": 0.4554744525547445, "percentage": 45.88, "elapsed_time": "1:39:43", "remaining_time": "1:57:37", "throughput": 10251.16, "total_tokens": 61341696} |
|
{"current_steps": 40, "total_steps": 85, "loss": 0.4942, "lr": 2.7306708986582553e-05, "epoch": 0.46715328467153283, "percentage": 47.06, "elapsed_time": "1:42:16", "remaining_time": "1:55:04", "throughput": 10251.77, "total_tokens": 62914560} |
|
{"current_steps": 41, "total_steps": 85, "loss": 0.5069, "lr": 2.638528687289925e-05, "epoch": 0.47883211678832116, "percentage": 48.24, "elapsed_time": "1:44:50", "remaining_time": "1:52:30", "throughput": 10252.24, "total_tokens": 64487424} |
|
{"current_steps": 42, "total_steps": 85, "loss": 0.5218, "lr": 2.5461972623978247e-05, "epoch": 0.4905109489051095, "percentage": 49.41, "elapsed_time": "1:47:23", "remaining_time": "1:49:56", "throughput": 10252.43, "total_tokens": 66060288} |
|
{"current_steps": 43, "total_steps": 85, "loss": 0.5003, "lr": 2.453802737602176e-05, "epoch": 0.5021897810218978, "percentage": 50.59, "elapsed_time": "1:49:56", "remaining_time": "1:47:23", "throughput": 10252.63, "total_tokens": 67633152} |
|
{"current_steps": 44, "total_steps": 85, "loss": 0.4997, "lr": 2.361471312710075e-05, "epoch": 0.5138686131386861, "percentage": 51.76, "elapsed_time": "1:52:29", "remaining_time": "1:44:49", "throughput": 10253.02, "total_tokens": 69206016} |
|
{"current_steps": 45, "total_steps": 85, "loss": 0.5045, "lr": 2.2693291013417453e-05, "epoch": 0.5255474452554745, "percentage": 52.94, "elapsed_time": "1:55:03", "remaining_time": "1:42:16", "throughput": 10253.25, "total_tokens": 70778880} |
|
{"current_steps": 46, "total_steps": 85, "loss": 0.4972, "lr": 2.1775019586744923e-05, "epoch": 0.5372262773722628, "percentage": 54.12, "elapsed_time": "1:57:36", "remaining_time": "1:39:42", "throughput": 10253.46, "total_tokens": 72351744} |
|
{"current_steps": 47, "total_steps": 85, "loss": 0.5174, "lr": 2.0861153095396748e-05, "epoch": 0.5489051094890511, "percentage": 55.29, "elapsed_time": "2:00:09", "remaining_time": "1:37:08", "throughput": 10253.76, "total_tokens": 73924608} |
|
{"current_steps": 48, "total_steps": 85, "loss": 0.5086, "lr": 1.995293977107475e-05, "epoch": 0.5605839416058395, "percentage": 56.47, "elapsed_time": "2:02:42", "remaining_time": "1:34:35", "throughput": 10254.17, "total_tokens": 75497472} |
|
{"current_steps": 49, "total_steps": 85, "loss": 0.4988, "lr": 1.9051620123934537e-05, "epoch": 0.5722627737226277, "percentage": 57.65, "elapsed_time": "2:05:15", "remaining_time": "1:32:01", "throughput": 10254.33, "total_tokens": 77070336} |
|
{"current_steps": 50, "total_steps": 85, "loss": 0.5047, "lr": 1.815842524819793e-05, "epoch": 0.583941605839416, "percentage": 58.82, "elapsed_time": "2:07:49", "remaining_time": "1:29:28", "throughput": 10254.36, "total_tokens": 78643200} |
|
{"current_steps": 51, "total_steps": 85, "loss": 0.4977, "lr": 1.7274575140626318e-05, "epoch": 0.5956204379562043, "percentage": 60.0, "elapsed_time": "2:10:22", "remaining_time": "1:26:55", "throughput": 10254.39, "total_tokens": 80216064} |
|
{"current_steps": 52, "total_steps": 85, "loss": 0.4775, "lr": 1.6401277034151798e-05, "epoch": 0.6072992700729927, "percentage": 61.18, "elapsed_time": "2:12:55", "remaining_time": "1:24:21", "throughput": 10254.65, "total_tokens": 81788928} |
|
{"current_steps": 53, "total_steps": 85, "loss": 0.519, "lr": 1.5539723748942245e-05, "epoch": 0.618978102189781, "percentage": 62.35, "elapsed_time": "2:15:29", "remaining_time": "1:21:48", "throughput": 10254.75, "total_tokens": 83361792} |
|
{"current_steps": 54, "total_steps": 85, "loss": 0.5102, "lr": 1.4691092063152417e-05, "epoch": 0.6306569343065693, "percentage": 63.53, "elapsed_time": "2:18:02", "remaining_time": "1:19:14", "throughput": 10254.76, "total_tokens": 84934656} |
|
{"current_steps": 55, "total_steps": 85, "loss": 0.4705, "lr": 1.3856541105586545e-05, "epoch": 0.6423357664233577, "percentage": 64.71, "elapsed_time": "2:20:35", "remaining_time": "1:16:41", "throughput": 10254.79, "total_tokens": 86507520} |
|
{"current_steps": 56, "total_steps": 85, "loss": 0.4965, "lr": 1.303721077246784e-05, "epoch": 0.654014598540146, "percentage": 65.88, "elapsed_time": "2:23:09", "remaining_time": "1:14:08", "throughput": 10254.68, "total_tokens": 88080384} |
|
{"current_steps": 57, "total_steps": 85, "loss": 0.503, "lr": 1.223422017047733e-05, "epoch": 0.6656934306569343, "percentage": 67.06, "elapsed_time": "2:25:42", "remaining_time": "1:11:34", "throughput": 10254.63, "total_tokens": 89653248} |
|
{"current_steps": 58, "total_steps": 85, "loss": 0.4921, "lr": 1.1448666088188764e-05, "epoch": 0.6773722627737226, "percentage": 68.24, "elapsed_time": "2:28:16", "remaining_time": "1:09:01", "throughput": 10254.63, "total_tokens": 91226112} |
|
{"current_steps": 59, "total_steps": 85, "loss": 0.5042, "lr": 1.068162149798737e-05, "epoch": 0.689051094890511, "percentage": 69.41, "elapsed_time": "2:30:49", "remaining_time": "1:06:27", "throughput": 10254.57, "total_tokens": 92798976} |
|
{"current_steps": 60, "total_steps": 85, "loss": 0.5145, "lr": 9.934134090518593e-06, "epoch": 0.7007299270072993, "percentage": 70.59, "elapsed_time": "2:33:22", "remaining_time": "1:03:54", "throughput": 10254.68, "total_tokens": 94371840} |
|
{"current_steps": 61, "total_steps": 85, "loss": 0.4897, "lr": 9.207224843668732e-06, "epoch": 0.7124087591240876, "percentage": 71.76, "elapsed_time": "2:35:56", "remaining_time": "1:01:21", "throughput": 10254.77, "total_tokens": 95944704} |
|
{"current_steps": 62, "total_steps": 85, "loss": 0.5033, "lr": 8.50188662803194e-06, "epoch": 0.724087591240876, "percentage": 72.94, "elapsed_time": "2:38:29", "remaining_time": "0:58:47", "throughput": 10254.85, "total_tokens": 97517568} |
|
{"current_steps": 63, "total_steps": 85, "loss": 0.473, "lr": 7.819082850768434e-06, "epoch": 0.7357664233576642, "percentage": 74.12, "elapsed_time": "2:41:02", "remaining_time": "0:56:14", "throughput": 10254.95, "total_tokens": 99090432} |
|
{"current_steps": 64, "total_steps": 85, "loss": 0.5298, "lr": 7.159746139706194e-06, "epoch": 0.7474452554744525, "percentage": 75.29, "elapsed_time": "2:43:35", "remaining_time": "0:53:40", "throughput": 10255.1, "total_tokens": 100663296} |
|
{"current_steps": 65, "total_steps": 85, "loss": 0.4685, "lr": 6.524777069483526e-06, "epoch": 0.7591240875912408, "percentage": 76.47, "elapsed_time": "2:46:09", "remaining_time": "0:51:07", "throughput": 10255.23, "total_tokens": 102236160} |
|
{"current_steps": 66, "total_steps": 85, "loss": 0.4931, "lr": 5.915042931472425e-06, "epoch": 0.7708029197080292, "percentage": 77.65, "elapsed_time": "2:48:42", "remaining_time": "0:48:34", "throughput": 10255.33, "total_tokens": 103809024} |
|
{"current_steps": 67, "total_steps": 85, "loss": 0.4957, "lr": 5.33137654916292e-06, "epoch": 0.7824817518248175, "percentage": 78.82, "elapsed_time": "2:51:15", "remaining_time": "0:46:00", "throughput": 10255.52, "total_tokens": 105381888} |
|
{"current_steps": 68, "total_steps": 85, "loss": 0.4924, "lr": 4.7745751406263165e-06, "epoch": 0.7941605839416058, "percentage": 80.0, "elapsed_time": "2:53:48", "remaining_time": "0:43:27", "throughput": 10255.76, "total_tokens": 106954752} |
|
{"current_steps": 69, "total_steps": 85, "loss": 0.5041, "lr": 4.245399229611238e-06, "epoch": 0.8058394160583942, "percentage": 81.18, "elapsed_time": "2:56:21", "remaining_time": "0:40:53", "throughput": 10255.93, "total_tokens": 108527616} |
|
{"current_steps": 70, "total_steps": 85, "loss": 0.4948, "lr": 3.7445716067596503e-06, "epoch": 0.8175182481751825, "percentage": 82.35, "elapsed_time": "2:58:55", "remaining_time": "0:38:20", "throughput": 10256.07, "total_tokens": 110100480} |
|
{"current_steps": 71, "total_steps": 85, "loss": 0.5085, "lr": 3.2727763423617913e-06, "epoch": 0.8291970802919708, "percentage": 83.53, "elapsed_time": "3:01:28", "remaining_time": "0:35:47", "throughput": 10256.08, "total_tokens": 111673344} |
|
{"current_steps": 72, "total_steps": 85, "loss": 0.5152, "lr": 2.8306578519984527e-06, "epoch": 0.8408759124087591, "percentage": 84.71, "elapsed_time": "3:04:01", "remaining_time": "0:33:13", "throughput": 10256.66, "total_tokens": 113246208} |
|
{"current_steps": 73, "total_steps": 85, "loss": 0.4905, "lr": 2.418820016346779e-06, "epoch": 0.8525547445255475, "percentage": 85.88, "elapsed_time": "3:06:34", "remaining_time": "0:30:40", "throughput": 10256.64, "total_tokens": 114819072} |
|
{"current_steps": 74, "total_steps": 85, "loss": 0.5023, "lr": 2.0378253563519247e-06, "epoch": 0.8642335766423358, "percentage": 87.06, "elapsed_time": "3:09:07", "remaining_time": "0:28:06", "throughput": 10256.67, "total_tokens": 116391936} |
|
{"current_steps": 75, "total_steps": 85, "loss": 0.4993, "lr": 1.6881942648911076e-06, "epoch": 0.8759124087591241, "percentage": 88.24, "elapsed_time": "3:11:41", "remaining_time": "0:25:33", "throughput": 10256.8, "total_tokens": 117964800} |
|
{"current_steps": 76, "total_steps": 85, "loss": 0.481, "lr": 1.3704042959795132e-06, "epoch": 0.8875912408759125, "percentage": 89.41, "elapsed_time": "3:14:14", "remaining_time": "0:23:00", "throughput": 10256.78, "total_tokens": 119537664} |
|
{"current_steps": 77, "total_steps": 85, "loss": 0.4806, "lr": 1.0848895124889818e-06, "epoch": 0.8992700729927007, "percentage": 90.59, "elapsed_time": "3:16:47", "remaining_time": "0:20:26", "throughput": 10256.76, "total_tokens": 121110528} |
|
{"current_steps": 78, "total_steps": 85, "loss": 0.4915, "lr": 8.320398932703144e-07, "epoch": 0.910948905109489, "percentage": 91.76, "elapsed_time": "3:19:20", "remaining_time": "0:17:53", "throughput": 10256.95, "total_tokens": 122683392} |
|
{"current_steps": 79, "total_steps": 85, "loss": 0.4937, "lr": 6.122008004890851e-07, "epoch": 0.9226277372262773, "percentage": 92.94, "elapsed_time": "3:21:54", "remaining_time": "0:15:20", "throughput": 10256.91, "total_tokens": 124256256} |
|
{"current_steps": 80, "total_steps": 85, "loss": 0.5152, "lr": 4.256725079024554e-07, "epoch": 0.9343065693430657, "percentage": 94.12, "elapsed_time": "3:24:27", "remaining_time": "0:12:46", "throughput": 10256.86, "total_tokens": 125829120} |
|
{"current_steps": 81, "total_steps": 85, "loss": 0.4832, "lr": 2.7270979072135104e-07, "epoch": 0.945985401459854, "percentage": 95.29, "elapsed_time": "3:27:00", "remaining_time": "0:10:13", "throughput": 10257.04, "total_tokens": 127401984} |
|
{"current_steps": 82, "total_steps": 85, "loss": 0.4975, "lr": 1.5352157761815977e-07, "epoch": 0.9576642335766423, "percentage": 96.47, "elapsed_time": "3:29:34", "remaining_time": "0:07:40", "throughput": 10257.12, "total_tokens": 128974848} |
|
{"current_steps": 83, "total_steps": 85, "loss": 0.4887, "lr": 6.827066535529946e-08, "epoch": 0.9693430656934306, "percentage": 97.65, "elapsed_time": "3:32:07", "remaining_time": "0:05:06", "throughput": 10257.16, "total_tokens": 130547712} |
|
{"current_steps": 84, "total_steps": 85, "loss": 0.4905, "lr": 1.7073496424427348e-08, "epoch": 0.981021897810219, "percentage": 98.82, "elapsed_time": "3:34:40", "remaining_time": "0:02:33", "throughput": 10257.17, "total_tokens": 132120576} |
|
{"current_steps": 85, "total_steps": 85, "loss": 0.5088, "lr": 0.0, "epoch": 0.9927007299270073, "percentage": 100.0, "elapsed_time": "3:37:14", "remaining_time": "0:00:00", "throughput": 10257.11, "total_tokens": 133693440} |
|
{"current_steps": 85, "total_steps": 85, "epoch": 0.9927007299270073, "percentage": 100.0, "elapsed_time": "3:37:36", "remaining_time": "0:00:00", "throughput": 10239.97, "total_tokens": 133693440} |
|
|