Training in progress, step 36252
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +383 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 798032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9d7c84eea2dcd4d5a664aa0cb6dab4d500c635e8019de4beebf4c3e0bc9b102
|
| 3 |
size 798032
|
trainer_log.jsonl
CHANGED
|
@@ -6887,3 +6887,386 @@
|
|
| 6887 |
{"current_steps": 34345, "total_steps": 38160, "loss": 0.3954, "lr": 1.5076844803522922e-06, "epoch": 18.000524109014677, "percentage": 90.0, "elapsed_time": "1:44:39", "remaining_time": "0:11:37", "throughput": 3575.23, "total_tokens": 22452408}
|
| 6888 |
{"current_steps": 34350, "total_steps": 38160, "loss": 0.4604, "lr": 1.5037761818796236e-06, "epoch": 18.00314465408805, "percentage": 90.02, "elapsed_time": "1:44:40", "remaining_time": "0:11:36", "throughput": 3575.27, "total_tokens": 22456184}
|
| 6889 |
{"current_steps": 34355, "total_steps": 38160, "loss": 0.5645, "lr": 1.4998727985489235e-06, "epoch": 18.005765199161427, "percentage": 90.03, "elapsed_time": "1:44:41", "remaining_time": "0:11:35", "throughput": 3575.22, "total_tokens": 22458968}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6887 |
{"current_steps": 34345, "total_steps": 38160, "loss": 0.3954, "lr": 1.5076844803522922e-06, "epoch": 18.000524109014677, "percentage": 90.0, "elapsed_time": "1:44:39", "remaining_time": "0:11:37", "throughput": 3575.23, "total_tokens": 22452408}
|
| 6888 |
{"current_steps": 34350, "total_steps": 38160, "loss": 0.4604, "lr": 1.5037761818796236e-06, "epoch": 18.00314465408805, "percentage": 90.02, "elapsed_time": "1:44:40", "remaining_time": "0:11:36", "throughput": 3575.27, "total_tokens": 22456184}
|
| 6889 |
{"current_steps": 34355, "total_steps": 38160, "loss": 0.5645, "lr": 1.4998727985489235e-06, "epoch": 18.005765199161427, "percentage": 90.03, "elapsed_time": "1:44:41", "remaining_time": "0:11:35", "throughput": 3575.22, "total_tokens": 22458968}
|
| 6890 |
+
{"current_steps": 34360, "total_steps": 38160, "loss": 0.3859, "lr": 1.4959743311767249e-06, "epoch": 18.0083857442348, "percentage": 90.04, "elapsed_time": "1:44:42", "remaining_time": "0:11:34", "throughput": 3575.24, "total_tokens": 22462392}
|
| 6891 |
+
{"current_steps": 34365, "total_steps": 38160, "loss": 0.447, "lr": 1.4920807805785502e-06, "epoch": 18.011006289308177, "percentage": 90.06, "elapsed_time": "1:44:43", "remaining_time": "0:11:33", "throughput": 3575.33, "total_tokens": 22466360}
|
| 6892 |
+
{"current_steps": 34370, "total_steps": 38160, "loss": 0.475, "lr": 1.4881921475688815e-06, "epoch": 18.01362683438155, "percentage": 90.07, "elapsed_time": "1:44:44", "remaining_time": "0:11:33", "throughput": 3575.41, "total_tokens": 22470104}
|
| 6893 |
+
{"current_steps": 34375, "total_steps": 38160, "loss": 0.4503, "lr": 1.4843084329611844e-06, "epoch": 18.016247379454928, "percentage": 90.08, "elapsed_time": "1:44:45", "remaining_time": "0:11:32", "throughput": 3575.39, "total_tokens": 22473144}
|
| 6894 |
+
{"current_steps": 34380, "total_steps": 38160, "loss": 0.5231, "lr": 1.480429637567879e-06, "epoch": 18.0188679245283, "percentage": 90.09, "elapsed_time": "1:44:46", "remaining_time": "0:11:31", "throughput": 3575.33, "total_tokens": 22475640}
|
| 6895 |
+
{"current_steps": 34385, "total_steps": 38160, "loss": 0.4557, "lr": 1.4765557622003684e-06, "epoch": 18.021488469601678, "percentage": 90.11, "elapsed_time": "1:44:47", "remaining_time": "0:11:30", "throughput": 3575.33, "total_tokens": 22478712}
|
| 6896 |
+
{"current_steps": 34390, "total_steps": 38160, "loss": 0.5749, "lr": 1.4726868076690186e-06, "epoch": 18.02410901467505, "percentage": 90.12, "elapsed_time": "1:44:48", "remaining_time": "0:11:29", "throughput": 3575.31, "total_tokens": 22481624}
|
| 6897 |
+
{"current_steps": 34395, "total_steps": 38160, "loss": 0.4637, "lr": 1.4688227747831767e-06, "epoch": 18.02672955974843, "percentage": 90.13, "elapsed_time": "1:44:48", "remaining_time": "0:11:28", "throughput": 3575.3, "total_tokens": 22484664}
|
| 6898 |
+
{"current_steps": 34400, "total_steps": 38160, "loss": 0.4283, "lr": 1.4649636643511573e-06, "epoch": 18.029350104821802, "percentage": 90.15, "elapsed_time": "1:44:49", "remaining_time": "0:11:27", "throughput": 3575.16, "total_tokens": 22487128}
|
| 6899 |
+
{"current_steps": 34405, "total_steps": 38160, "loss": 0.5233, "lr": 1.4611094771802364e-06, "epoch": 18.03197064989518, "percentage": 90.16, "elapsed_time": "1:44:50", "remaining_time": "0:11:26", "throughput": 3575.02, "total_tokens": 22489528}
|
| 6900 |
+
{"current_steps": 34410, "total_steps": 38160, "loss": 0.5359, "lr": 1.457260214076664e-06, "epoch": 18.034591194968552, "percentage": 90.17, "elapsed_time": "1:44:51", "remaining_time": "0:11:25", "throughput": 3575.13, "total_tokens": 22493560}
|
| 6901 |
+
{"current_steps": 34415, "total_steps": 38160, "loss": 0.4641, "lr": 1.4534158758456623e-06, "epoch": 18.03721174004193, "percentage": 90.19, "elapsed_time": "1:44:52", "remaining_time": "0:11:24", "throughput": 3575.12, "total_tokens": 22496408}
|
| 6902 |
+
{"current_steps": 34420, "total_steps": 38160, "loss": 0.4087, "lr": 1.4495764632914271e-06, "epoch": 18.039832285115303, "percentage": 90.2, "elapsed_time": "1:44:53", "remaining_time": "0:11:23", "throughput": 3575.13, "total_tokens": 22500440}
|
| 6903 |
+
{"current_steps": 34425, "total_steps": 38160, "loss": 0.5347, "lr": 1.4457419772171215e-06, "epoch": 18.04245283018868, "percentage": 90.21, "elapsed_time": "1:44:54", "remaining_time": "0:11:22", "throughput": 3575.12, "total_tokens": 22503640}
|
| 6904 |
+
{"current_steps": 34430, "total_steps": 38160, "loss": 0.552, "lr": 1.4419124184248733e-06, "epoch": 18.045073375262053, "percentage": 90.23, "elapsed_time": "1:44:55", "remaining_time": "0:11:22", "throughput": 3575.25, "total_tokens": 22507768}
|
| 6905 |
+
{"current_steps": 34435, "total_steps": 38160, "loss": 0.4797, "lr": 1.4380877877157834e-06, "epoch": 18.04769392033543, "percentage": 90.24, "elapsed_time": "1:44:56", "remaining_time": "0:11:21", "throughput": 3575.3, "total_tokens": 22511256}
|
| 6906 |
+
{"current_steps": 34440, "total_steps": 38160, "loss": 0.5307, "lr": 1.4342680858899143e-06, "epoch": 18.050314465408807, "percentage": 90.25, "elapsed_time": "1:44:57", "remaining_time": "0:11:20", "throughput": 3575.37, "total_tokens": 22514872}
|
| 6907 |
+
{"current_steps": 34445, "total_steps": 38160, "loss": 0.38, "lr": 1.4304533137463134e-06, "epoch": 18.05293501048218, "percentage": 90.26, "elapsed_time": "1:44:58", "remaining_time": "0:11:19", "throughput": 3575.36, "total_tokens": 22518008}
|
| 6908 |
+
{"current_steps": 34450, "total_steps": 38160, "loss": 0.4295, "lr": 1.4266434720829808e-06, "epoch": 18.055555555555557, "percentage": 90.28, "elapsed_time": "1:44:58", "remaining_time": "0:11:18", "throughput": 3575.32, "total_tokens": 22520664}
|
| 6909 |
+
{"current_steps": 34455, "total_steps": 38160, "loss": 0.3669, "lr": 1.4228385616968987e-06, "epoch": 18.05817610062893, "percentage": 90.29, "elapsed_time": "1:44:59", "remaining_time": "0:11:17", "throughput": 3575.24, "total_tokens": 22523096}
|
| 6910 |
+
{"current_steps": 34460, "total_steps": 38160, "loss": 0.5175, "lr": 1.419038583384008e-06, "epoch": 18.060796645702307, "percentage": 90.3, "elapsed_time": "1:45:00", "remaining_time": "0:11:16", "throughput": 3575.28, "total_tokens": 22526616}
|
| 6911 |
+
{"current_steps": 34465, "total_steps": 38160, "loss": 0.4732, "lr": 1.4152435379392148e-06, "epoch": 18.06341719077568, "percentage": 90.32, "elapsed_time": "1:45:01", "remaining_time": "0:11:15", "throughput": 3575.25, "total_tokens": 22529560}
|
| 6912 |
+
{"current_steps": 34470, "total_steps": 38160, "loss": 0.4618, "lr": 1.411453426156406e-06, "epoch": 18.066037735849058, "percentage": 90.33, "elapsed_time": "1:45:02", "remaining_time": "0:11:14", "throughput": 3575.31, "total_tokens": 22533016}
|
| 6913 |
+
{"current_steps": 34475, "total_steps": 38160, "loss": 0.5546, "lr": 1.4076682488284282e-06, "epoch": 18.06865828092243, "percentage": 90.34, "elapsed_time": "1:45:03", "remaining_time": "0:11:13", "throughput": 3575.22, "total_tokens": 22535416}
|
| 6914 |
+
{"current_steps": 34480, "total_steps": 38160, "loss": 0.3588, "lr": 1.4038880067470978e-06, "epoch": 18.071278825995808, "percentage": 90.36, "elapsed_time": "1:45:04", "remaining_time": "0:11:12", "throughput": 3575.27, "total_tokens": 22538936}
|
| 6915 |
+
{"current_steps": 34485, "total_steps": 38160, "loss": 0.457, "lr": 1.400112700703196e-06, "epoch": 18.07389937106918, "percentage": 90.37, "elapsed_time": "1:45:04", "remaining_time": "0:11:11", "throughput": 3575.26, "total_tokens": 22541944}
|
| 6916 |
+
{"current_steps": 34490, "total_steps": 38160, "loss": 0.545, "lr": 1.3963423314864805e-06, "epoch": 18.07651991614256, "percentage": 90.38, "elapsed_time": "1:45:05", "remaining_time": "0:11:10", "throughput": 3575.2, "total_tokens": 22544568}
|
| 6917 |
+
{"current_steps": 34495, "total_steps": 38160, "loss": 0.4808, "lr": 1.3925768998856587e-06, "epoch": 18.079140461215932, "percentage": 90.4, "elapsed_time": "1:45:06", "remaining_time": "0:11:10", "throughput": 3575.22, "total_tokens": 22547768}
|
| 6918 |
+
{"current_steps": 34500, "total_steps": 38160, "loss": 0.467, "lr": 1.388816406688423e-06, "epoch": 18.08176100628931, "percentage": 90.41, "elapsed_time": "1:45:07", "remaining_time": "0:11:09", "throughput": 3575.2, "total_tokens": 22550776}
|
| 6919 |
+
{"current_steps": 34505, "total_steps": 38160, "loss": 0.3857, "lr": 1.3850608526814246e-06, "epoch": 18.084381551362682, "percentage": 90.42, "elapsed_time": "1:45:08", "remaining_time": "0:11:08", "throughput": 3575.24, "total_tokens": 22554392}
|
| 6920 |
+
{"current_steps": 34510, "total_steps": 38160, "loss": 0.5382, "lr": 1.3813102386502853e-06, "epoch": 18.08700209643606, "percentage": 90.44, "elapsed_time": "1:45:09", "remaining_time": "0:11:07", "throughput": 3575.22, "total_tokens": 22557304}
|
| 6921 |
+
{"current_steps": 34515, "total_steps": 38160, "loss": 0.4809, "lr": 1.3775645653795881e-06, "epoch": 18.089622641509433, "percentage": 90.45, "elapsed_time": "1:45:10", "remaining_time": "0:11:06", "throughput": 3575.24, "total_tokens": 22560536}
|
| 6922 |
+
{"current_steps": 34520, "total_steps": 38160, "loss": 0.3985, "lr": 1.373823833652882e-06, "epoch": 18.09224318658281, "percentage": 90.46, "elapsed_time": "1:45:11", "remaining_time": "0:11:05", "throughput": 3575.23, "total_tokens": 22563832}
|
| 6923 |
+
{"current_steps": 34525, "total_steps": 38160, "loss": 0.5053, "lr": 1.3700880442526876e-06, "epoch": 18.094863731656183, "percentage": 90.47, "elapsed_time": "1:45:11", "remaining_time": "0:11:04", "throughput": 3575.21, "total_tokens": 22566616}
|
| 6924 |
+
{"current_steps": 34530, "total_steps": 38160, "loss": 0.5143, "lr": 1.3663571979604884e-06, "epoch": 18.09748427672956, "percentage": 90.49, "elapsed_time": "1:45:12", "remaining_time": "0:11:03", "throughput": 3575.22, "total_tokens": 22569976}
|
| 6925 |
+
{"current_steps": 34535, "total_steps": 38160, "loss": 0.5951, "lr": 1.3626312955567406e-06, "epoch": 18.100104821802937, "percentage": 90.5, "elapsed_time": "1:45:13", "remaining_time": "0:11:02", "throughput": 3575.24, "total_tokens": 22573112}
|
| 6926 |
+
{"current_steps": 34540, "total_steps": 38160, "loss": 0.4664, "lr": 1.358910337820854e-06, "epoch": 18.10272536687631, "percentage": 90.51, "elapsed_time": "1:45:14", "remaining_time": "0:11:01", "throughput": 3575.24, "total_tokens": 22576152}
|
| 6927 |
+
{"current_steps": 34545, "total_steps": 38160, "loss": 0.4879, "lr": 1.3551943255312172e-06, "epoch": 18.105345911949687, "percentage": 90.53, "elapsed_time": "1:45:15", "remaining_time": "0:11:00", "throughput": 3575.3, "total_tokens": 22579672}
|
| 6928 |
+
{"current_steps": 34550, "total_steps": 38160, "loss": 0.465, "lr": 1.3514832594651694e-06, "epoch": 18.10796645702306, "percentage": 90.54, "elapsed_time": "1:45:16", "remaining_time": "0:10:59", "throughput": 3575.35, "total_tokens": 22583096}
|
| 6929 |
+
{"current_steps": 34555, "total_steps": 38160, "loss": 0.5961, "lr": 1.347777140399026e-06, "epoch": 18.110587002096437, "percentage": 90.55, "elapsed_time": "1:45:17", "remaining_time": "0:10:59", "throughput": 3575.48, "total_tokens": 22587256}
|
| 6930 |
+
{"current_steps": 34560, "total_steps": 38160, "loss": 0.6077, "lr": 1.344075969108069e-06, "epoch": 18.11320754716981, "percentage": 90.57, "elapsed_time": "1:45:18", "remaining_time": "0:10:58", "throughput": 3575.54, "total_tokens": 22591352}
|
| 6931 |
+
{"current_steps": 34565, "total_steps": 38160, "loss": 0.4883, "lr": 1.3403797463665352e-06, "epoch": 18.115828092243188, "percentage": 90.58, "elapsed_time": "1:45:19", "remaining_time": "0:10:57", "throughput": 3575.51, "total_tokens": 22594040}
|
| 6932 |
+
{"current_steps": 34570, "total_steps": 38160, "loss": 0.5717, "lr": 1.3366884729476365e-06, "epoch": 18.11844863731656, "percentage": 90.59, "elapsed_time": "1:45:20", "remaining_time": "0:10:56", "throughput": 3575.46, "total_tokens": 22597208}
|
| 6933 |
+
{"current_steps": 34575, "total_steps": 38160, "loss": 0.3564, "lr": 1.3330021496235467e-06, "epoch": 18.121069182389938, "percentage": 90.61, "elapsed_time": "1:45:21", "remaining_time": "0:10:55", "throughput": 3575.46, "total_tokens": 22600536}
|
| 6934 |
+
{"current_steps": 34580, "total_steps": 38160, "loss": 0.5264, "lr": 1.3293207771653965e-06, "epoch": 18.12368972746331, "percentage": 90.62, "elapsed_time": "1:45:21", "remaining_time": "0:10:54", "throughput": 3575.37, "total_tokens": 22603160}
|
| 6935 |
+
{"current_steps": 34585, "total_steps": 38160, "loss": 0.4511, "lr": 1.3256443563432891e-06, "epoch": 18.12631027253669, "percentage": 90.63, "elapsed_time": "1:45:22", "remaining_time": "0:10:53", "throughput": 3575.35, "total_tokens": 22606328}
|
| 6936 |
+
{"current_steps": 34590, "total_steps": 38160, "loss": 0.4379, "lr": 1.3219728879262956e-06, "epoch": 18.128930817610062, "percentage": 90.64, "elapsed_time": "1:45:23", "remaining_time": "0:10:52", "throughput": 3575.36, "total_tokens": 22609624}
|
| 6937 |
+
{"current_steps": 34595, "total_steps": 38160, "loss": 0.563, "lr": 1.3183063726824375e-06, "epoch": 18.13155136268344, "percentage": 90.66, "elapsed_time": "1:45:24", "remaining_time": "0:10:51", "throughput": 3575.34, "total_tokens": 22612728}
|
| 6938 |
+
{"current_steps": 34600, "total_steps": 38160, "loss": 0.5285, "lr": 1.3146448113787151e-06, "epoch": 18.134171907756812, "percentage": 90.67, "elapsed_time": "1:45:25", "remaining_time": "0:10:50", "throughput": 3575.26, "total_tokens": 22615640}
|
| 6939 |
+
{"current_steps": 34605, "total_steps": 38160, "loss": 0.5527, "lr": 1.3109882047810773e-06, "epoch": 18.13679245283019, "percentage": 90.68, "elapsed_time": "1:45:26", "remaining_time": "0:10:49", "throughput": 3575.21, "total_tokens": 22618360}
|
| 6940 |
+
{"current_steps": 34610, "total_steps": 38160, "loss": 0.5968, "lr": 1.307336553654448e-06, "epoch": 18.139412997903563, "percentage": 90.7, "elapsed_time": "1:45:27", "remaining_time": "0:10:49", "throughput": 3575.26, "total_tokens": 22621976}
|
| 6941 |
+
{"current_steps": 34615, "total_steps": 38160, "loss": 0.5633, "lr": 1.303689858762716e-06, "epoch": 18.14203354297694, "percentage": 90.71, "elapsed_time": "1:45:28", "remaining_time": "0:10:48", "throughput": 3575.34, "total_tokens": 22626008}
|
| 6942 |
+
{"current_steps": 34620, "total_steps": 38160, "loss": 0.4219, "lr": 1.3000481208687188e-06, "epoch": 18.144654088050313, "percentage": 90.72, "elapsed_time": "1:45:29", "remaining_time": "0:10:47", "throughput": 3575.35, "total_tokens": 22629368}
|
| 6943 |
+
{"current_steps": 34625, "total_steps": 38160, "loss": 0.4171, "lr": 1.2964113407342743e-06, "epoch": 18.14727463312369, "percentage": 90.74, "elapsed_time": "1:45:30", "remaining_time": "0:10:46", "throughput": 3575.35, "total_tokens": 22632440}
|
| 6944 |
+
{"current_steps": 34630, "total_steps": 38160, "loss": 0.4555, "lr": 1.292779519120152e-06, "epoch": 18.149895178197063, "percentage": 90.75, "elapsed_time": "1:45:30", "remaining_time": "0:10:45", "throughput": 3575.31, "total_tokens": 22635160}
|
| 6945 |
+
{"current_steps": 34635, "total_steps": 38160, "loss": 0.5536, "lr": 1.2891526567860856e-06, "epoch": 18.15251572327044, "percentage": 90.76, "elapsed_time": "1:45:31", "remaining_time": "0:10:44", "throughput": 3575.48, "total_tokens": 22639896}
|
| 6946 |
+
{"current_steps": 34640, "total_steps": 38160, "loss": 0.4848, "lr": 1.2855307544907825e-06, "epoch": 18.155136268343817, "percentage": 90.78, "elapsed_time": "1:45:32", "remaining_time": "0:10:43", "throughput": 3575.48, "total_tokens": 22642968}
|
| 6947 |
+
{"current_steps": 34645, "total_steps": 38160, "loss": 0.3258, "lr": 1.281913812991889e-06, "epoch": 18.15775681341719, "percentage": 90.79, "elapsed_time": "1:45:33", "remaining_time": "0:10:42", "throughput": 3575.52, "total_tokens": 22646456}
|
| 6948 |
+
{"current_steps": 34650, "total_steps": 38160, "loss": 0.5136, "lr": 1.2783018330460389e-06, "epoch": 18.160377358490567, "percentage": 90.8, "elapsed_time": "1:45:34", "remaining_time": "0:10:41", "throughput": 3575.65, "total_tokens": 22650648}
|
| 6949 |
+
{"current_steps": 34655, "total_steps": 38160, "loss": 0.3634, "lr": 1.2746948154088111e-06, "epoch": 18.16299790356394, "percentage": 90.81, "elapsed_time": "1:45:35", "remaining_time": "0:10:40", "throughput": 3575.67, "total_tokens": 22654296}
|
| 6950 |
+
{"current_steps": 34660, "total_steps": 38160, "loss": 0.3615, "lr": 1.2710927608347605e-06, "epoch": 18.165618448637318, "percentage": 90.83, "elapsed_time": "1:45:36", "remaining_time": "0:10:39", "throughput": 3575.72, "total_tokens": 22658072}
|
| 6951 |
+
{"current_steps": 34665, "total_steps": 38160, "loss": 0.3587, "lr": 1.2674956700773872e-06, "epoch": 18.16823899371069, "percentage": 90.84, "elapsed_time": "1:45:37", "remaining_time": "0:10:38", "throughput": 3575.71, "total_tokens": 22661752}
|
| 6952 |
+
{"current_steps": 34670, "total_steps": 38160, "loss": 0.6807, "lr": 1.2639035438891666e-06, "epoch": 18.170859538784068, "percentage": 90.85, "elapsed_time": "1:45:38", "remaining_time": "0:10:38", "throughput": 3575.75, "total_tokens": 22665112}
|
| 6953 |
+
{"current_steps": 34675, "total_steps": 38160, "loss": 0.4012, "lr": 1.260316383021526e-06, "epoch": 18.17348008385744, "percentage": 90.87, "elapsed_time": "1:45:39", "remaining_time": "0:10:37", "throughput": 3575.68, "total_tokens": 22667640}
|
| 6954 |
+
{"current_steps": 34680, "total_steps": 38160, "loss": 0.478, "lr": 1.2567341882248645e-06, "epoch": 18.17610062893082, "percentage": 90.88, "elapsed_time": "1:45:40", "remaining_time": "0:10:36", "throughput": 3575.68, "total_tokens": 22670840}
|
| 6955 |
+
{"current_steps": 34685, "total_steps": 38160, "loss": 0.493, "lr": 1.2531569602485305e-06, "epoch": 18.178721174004192, "percentage": 90.89, "elapsed_time": "1:45:41", "remaining_time": "0:10:35", "throughput": 3575.65, "total_tokens": 22673720}
|
| 6956 |
+
{"current_steps": 34690, "total_steps": 38160, "loss": 0.5115, "lr": 1.2495846998408445e-06, "epoch": 18.18134171907757, "percentage": 90.91, "elapsed_time": "1:45:41", "remaining_time": "0:10:34", "throughput": 3575.71, "total_tokens": 22676984}
|
| 6957 |
+
{"current_steps": 34695, "total_steps": 38160, "loss": 0.4559, "lr": 1.246017407749084e-06, "epoch": 18.183962264150942, "percentage": 90.92, "elapsed_time": "1:45:42", "remaining_time": "0:10:33", "throughput": 3575.76, "total_tokens": 22680216}
|
| 6958 |
+
{"current_steps": 34700, "total_steps": 38160, "loss": 0.4473, "lr": 1.2424550847194739e-06, "epoch": 18.18658280922432, "percentage": 90.93, "elapsed_time": "1:45:43", "remaining_time": "0:10:32", "throughput": 3575.78, "total_tokens": 22683448}
|
| 6959 |
+
{"current_steps": 34705, "total_steps": 38160, "loss": 0.45, "lr": 1.2388977314972238e-06, "epoch": 18.189203354297693, "percentage": 90.95, "elapsed_time": "1:45:45", "remaining_time": "0:10:31", "throughput": 3575.94, "total_tokens": 22689912}
|
| 6960 |
+
{"current_steps": 34710, "total_steps": 38160, "loss": 0.3264, "lr": 1.235345348826486e-06, "epoch": 18.19182389937107, "percentage": 90.96, "elapsed_time": "1:45:45", "remaining_time": "0:10:30", "throughput": 3575.91, "total_tokens": 22692696}
|
| 6961 |
+
{"current_steps": 34715, "total_steps": 38160, "loss": 0.4693, "lr": 1.2317979374503825e-06, "epoch": 18.194444444444443, "percentage": 90.97, "elapsed_time": "1:45:46", "remaining_time": "0:10:29", "throughput": 3575.78, "total_tokens": 22695032}
|
| 6962 |
+
{"current_steps": 34720, "total_steps": 38160, "loss": 0.4799, "lr": 1.228255498110989e-06, "epoch": 18.19706498951782, "percentage": 90.99, "elapsed_time": "1:45:47", "remaining_time": "0:10:28", "throughput": 3575.83, "total_tokens": 22698712}
|
| 6963 |
+
{"current_steps": 34725, "total_steps": 38160, "loss": 0.5588, "lr": 1.224718031549338e-06, "epoch": 18.199685534591197, "percentage": 91.0, "elapsed_time": "1:45:48", "remaining_time": "0:10:28", "throughput": 3575.85, "total_tokens": 22702200}
|
| 6964 |
+
{"current_steps": 34730, "total_steps": 38160, "loss": 0.4509, "lr": 1.2211855385054344e-06, "epoch": 18.20230607966457, "percentage": 91.01, "elapsed_time": "1:45:49", "remaining_time": "0:10:27", "throughput": 3575.79, "total_tokens": 22704888}
|
| 6965 |
+
{"current_steps": 34735, "total_steps": 38160, "loss": 0.3856, "lr": 1.217658019718232e-06, "epoch": 18.204926624737947, "percentage": 91.02, "elapsed_time": "1:45:50", "remaining_time": "0:10:26", "throughput": 3575.79, "total_tokens": 22708280}
|
| 6966 |
+
{"current_steps": 34740, "total_steps": 38160, "loss": 0.5577, "lr": 1.2141354759256484e-06, "epoch": 18.20754716981132, "percentage": 91.04, "elapsed_time": "1:45:51", "remaining_time": "0:10:25", "throughput": 3575.78, "total_tokens": 22711384}
|
| 6967 |
+
{"current_steps": 34745, "total_steps": 38160, "loss": 0.4163, "lr": 1.2106179078645641e-06, "epoch": 18.210167714884697, "percentage": 91.05, "elapsed_time": "1:45:52", "remaining_time": "0:10:24", "throughput": 3575.82, "total_tokens": 22714712}
|
| 6968 |
+
{"current_steps": 34750, "total_steps": 38160, "loss": 0.5246, "lr": 1.2071053162708096e-06, "epoch": 18.21278825995807, "percentage": 91.06, "elapsed_time": "1:45:53", "remaining_time": "0:10:23", "throughput": 3575.77, "total_tokens": 22717432}
|
| 6969 |
+
{"current_steps": 34755, "total_steps": 38160, "loss": 0.4705, "lr": 1.203597701879175e-06, "epoch": 18.215408805031448, "percentage": 91.08, "elapsed_time": "1:45:53", "remaining_time": "0:10:22", "throughput": 3575.75, "total_tokens": 22720312}
|
| 6970 |
+
{"current_steps": 34760, "total_steps": 38160, "loss": 0.395, "lr": 1.2000950654234177e-06, "epoch": 18.21802935010482, "percentage": 91.09, "elapsed_time": "1:45:55", "remaining_time": "0:10:21", "throughput": 3575.97, "total_tokens": 22727928}
|
| 6971 |
+
{"current_steps": 34765, "total_steps": 38160, "loss": 0.4351, "lr": 1.1965974076362491e-06, "epoch": 18.220649895178198, "percentage": 91.1, "elapsed_time": "1:45:56", "remaining_time": "0:10:20", "throughput": 3575.87, "total_tokens": 22730456}
|
| 6972 |
+
{"current_steps": 34770, "total_steps": 38160, "loss": 0.4725, "lr": 1.193104729249342e-06, "epoch": 18.22327044025157, "percentage": 91.12, "elapsed_time": "1:45:57", "remaining_time": "0:10:19", "throughput": 3575.83, "total_tokens": 22733240}
|
| 6973 |
+
{"current_steps": 34775, "total_steps": 38160, "loss": 0.4182, "lr": 1.189617030993323e-06, "epoch": 18.22589098532495, "percentage": 91.13, "elapsed_time": "1:45:58", "remaining_time": "0:10:18", "throughput": 3575.81, "total_tokens": 22736344}
|
| 6974 |
+
{"current_steps": 34780, "total_steps": 38160, "loss": 0.5031, "lr": 1.1861343135977753e-06, "epoch": 18.228511530398322, "percentage": 91.14, "elapsed_time": "1:45:59", "remaining_time": "0:10:18", "throughput": 3575.82, "total_tokens": 22739320}
|
| 6975 |
+
{"current_steps": 34785, "total_steps": 38160, "loss": 0.4186, "lr": 1.182656577791244e-06, "epoch": 18.2311320754717, "percentage": 91.16, "elapsed_time": "1:46:00", "remaining_time": "0:10:17", "throughput": 3575.87, "total_tokens": 22743000}
|
| 6976 |
+
{"current_steps": 34790, "total_steps": 38160, "loss": 0.5279, "lr": 1.1791838243012359e-06, "epoch": 18.233752620545072, "percentage": 91.17, "elapsed_time": "1:46:00", "remaining_time": "0:10:16", "throughput": 3575.82, "total_tokens": 22745752}
|
| 6977 |
+
{"current_steps": 34795, "total_steps": 38160, "loss": 0.6417, "lr": 1.1757160538542117e-06, "epoch": 18.23637316561845, "percentage": 91.18, "elapsed_time": "1:46:01", "remaining_time": "0:10:15", "throughput": 3575.8, "total_tokens": 22748504}
|
| 6978 |
+
{"current_steps": 34800, "total_steps": 38160, "loss": 0.4735, "lr": 1.1722532671755882e-06, "epoch": 18.238993710691823, "percentage": 91.19, "elapsed_time": "1:46:02", "remaining_time": "0:10:14", "throughput": 3575.81, "total_tokens": 22751704}
|
| 6979 |
+
{"current_steps": 34805, "total_steps": 38160, "loss": 0.4426, "lr": 1.168795464989736e-06, "epoch": 18.2416142557652, "percentage": 91.21, "elapsed_time": "1:46:03", "remaining_time": "0:10:13", "throughput": 3575.86, "total_tokens": 22755256}
|
| 6980 |
+
{"current_steps": 34810, "total_steps": 38160, "loss": 0.6527, "lr": 1.165342648019993e-06, "epoch": 18.244234800838573, "percentage": 91.22, "elapsed_time": "1:46:04", "remaining_time": "0:10:12", "throughput": 3575.9, "total_tokens": 22758616}
|
| 6981 |
+
{"current_steps": 34815, "total_steps": 38160, "loss": 0.3536, "lr": 1.1618948169886457e-06, "epoch": 18.24685534591195, "percentage": 91.23, "elapsed_time": "1:46:05", "remaining_time": "0:10:11", "throughput": 3575.85, "total_tokens": 22761432}
|
| 6982 |
+
{"current_steps": 34820, "total_steps": 38160, "loss": 0.5857, "lr": 1.1584519726169446e-06, "epoch": 18.249475890985323, "percentage": 91.25, "elapsed_time": "1:46:06", "remaining_time": "0:10:10", "throughput": 3575.85, "total_tokens": 22764376}
|
| 6983 |
+
{"current_steps": 34825, "total_steps": 38160, "loss": 0.4826, "lr": 1.1550141156250942e-06, "epoch": 18.2520964360587, "percentage": 91.26, "elapsed_time": "1:46:07", "remaining_time": "0:10:09", "throughput": 3575.92, "total_tokens": 22768056}
|
| 6984 |
+
{"current_steps": 34830, "total_steps": 38160, "loss": 0.6138, "lr": 1.1515812467322556e-06, "epoch": 18.254716981132077, "percentage": 91.27, "elapsed_time": "1:46:07", "remaining_time": "0:10:08", "throughput": 3575.94, "total_tokens": 22771128}
|
| 6985 |
+
{"current_steps": 34835, "total_steps": 38160, "loss": 0.3394, "lr": 1.1481533666565375e-06, "epoch": 18.25733752620545, "percentage": 91.29, "elapsed_time": "1:46:08", "remaining_time": "0:10:07", "throughput": 3575.97, "total_tokens": 22774360}
|
| 6986 |
+
{"current_steps": 34840, "total_steps": 38160, "loss": 0.3831, "lr": 1.144730476115019e-06, "epoch": 18.259958071278827, "percentage": 91.3, "elapsed_time": "1:46:09", "remaining_time": "0:10:06", "throughput": 3576.1, "total_tokens": 22778712}
|
| 6987 |
+
{"current_steps": 34845, "total_steps": 38160, "loss": 0.4273, "lr": 1.1413125758237304e-06, "epoch": 18.2625786163522, "percentage": 91.31, "elapsed_time": "1:46:10", "remaining_time": "0:10:06", "throughput": 3576.04, "total_tokens": 22781368}
|
| 6988 |
+
{"current_steps": 34850, "total_steps": 38160, "loss": 0.3631, "lr": 1.1378996664976577e-06, "epoch": 18.265199161425578, "percentage": 91.33, "elapsed_time": "1:46:11", "remaining_time": "0:10:05", "throughput": 3575.99, "total_tokens": 22784120}
|
| 6989 |
+
{"current_steps": 34855, "total_steps": 38160, "loss": 0.3536, "lr": 1.134491748850741e-06, "epoch": 18.26781970649895, "percentage": 91.34, "elapsed_time": "1:46:12", "remaining_time": "0:10:04", "throughput": 3575.96, "total_tokens": 22787160}
|
| 6990 |
+
{"current_steps": 34860, "total_steps": 38160, "loss": 0.5013, "lr": 1.13108882359588e-06, "epoch": 18.270440251572328, "percentage": 91.35, "elapsed_time": "1:46:13", "remaining_time": "0:10:03", "throughput": 3576.0, "total_tokens": 22790584}
|
| 6991 |
+
{"current_steps": 34865, "total_steps": 38160, "loss": 0.4758, "lr": 1.127690891444924e-06, "epoch": 18.2730607966457, "percentage": 91.37, "elapsed_time": "1:46:14", "remaining_time": "0:10:02", "throughput": 3576.06, "total_tokens": 22794168}
|
| 6992 |
+
{"current_steps": 34870, "total_steps": 38160, "loss": 0.5366, "lr": 1.1242979531086829e-06, "epoch": 18.27568134171908, "percentage": 91.38, "elapsed_time": "1:46:14", "remaining_time": "0:10:01", "throughput": 3575.95, "total_tokens": 22796600}
|
| 6993 |
+
{"current_steps": 34875, "total_steps": 38160, "loss": 0.5438, "lr": 1.1209100092969244e-06, "epoch": 18.278301886792452, "percentage": 91.39, "elapsed_time": "1:46:15", "remaining_time": "0:10:00", "throughput": 3575.96, "total_tokens": 22799896}
|
| 6994 |
+
{"current_steps": 34880, "total_steps": 38160, "loss": 0.5764, "lr": 1.1175270607183625e-06, "epoch": 18.28092243186583, "percentage": 91.4, "elapsed_time": "1:46:16", "remaining_time": "0:09:59", "throughput": 3576.0, "total_tokens": 22803416}
|
| 6995 |
+
{"current_steps": 34885, "total_steps": 38160, "loss": 0.5688, "lr": 1.114149108080678e-06, "epoch": 18.283542976939202, "percentage": 91.42, "elapsed_time": "1:46:17", "remaining_time": "0:09:58", "throughput": 3576.03, "total_tokens": 22806552}
|
| 6996 |
+
{"current_steps": 34890, "total_steps": 38160, "loss": 0.4559, "lr": 1.1107761520904925e-06, "epoch": 18.28616352201258, "percentage": 91.43, "elapsed_time": "1:46:18", "remaining_time": "0:09:57", "throughput": 3576.01, "total_tokens": 22809496}
|
| 6997 |
+
{"current_steps": 34895, "total_steps": 38160, "loss": 0.3862, "lr": 1.1074081934533908e-06, "epoch": 18.288784067085953, "percentage": 91.44, "elapsed_time": "1:46:19", "remaining_time": "0:09:56", "throughput": 3576.0, "total_tokens": 22812664}
|
| 6998 |
+
{"current_steps": 34900, "total_steps": 38160, "loss": 0.3734, "lr": 1.1040452328739153e-06, "epoch": 18.29140461215933, "percentage": 91.46, "elapsed_time": "1:46:20", "remaining_time": "0:09:55", "throughput": 3576.01, "total_tokens": 22815992}
|
| 6999 |
+
{"current_steps": 34905, "total_steps": 38160, "loss": 0.4606, "lr": 1.1006872710555615e-06, "epoch": 18.294025157232703, "percentage": 91.47, "elapsed_time": "1:46:21", "remaining_time": "0:09:55", "throughput": 3576.0, "total_tokens": 22818968}
|
| 7000 |
+
{"current_steps": 34910, "total_steps": 38160, "loss": 0.4235, "lr": 1.0973343087007703e-06, "epoch": 18.29664570230608, "percentage": 91.48, "elapsed_time": "1:46:21", "remaining_time": "0:09:54", "throughput": 3575.94, "total_tokens": 22821624}
|
| 7001 |
+
{"current_steps": 34915, "total_steps": 38160, "loss": 0.6249, "lr": 1.0939863465109473e-06, "epoch": 18.299266247379457, "percentage": 91.5, "elapsed_time": "1:46:22", "remaining_time": "0:09:53", "throughput": 3575.95, "total_tokens": 22824696}
|
| 7002 |
+
{"current_steps": 34920, "total_steps": 38160, "loss": 0.4522, "lr": 1.0906433851864433e-06, "epoch": 18.30188679245283, "percentage": 91.51, "elapsed_time": "1:46:23", "remaining_time": "0:09:52", "throughput": 3575.94, "total_tokens": 22827864}
|
| 7003 |
+
{"current_steps": 34925, "total_steps": 38160, "loss": 0.6838, "lr": 1.0873054254265713e-06, "epoch": 18.304507337526207, "percentage": 91.52, "elapsed_time": "1:46:24", "remaining_time": "0:09:51", "throughput": 3575.97, "total_tokens": 22831384}
|
| 7004 |
+
{"current_steps": 34930, "total_steps": 38160, "loss": 0.5716, "lr": 1.0839724679295976e-06, "epoch": 18.30712788259958, "percentage": 91.54, "elapsed_time": "1:46:25", "remaining_time": "0:09:50", "throughput": 3576.09, "total_tokens": 22835928}
|
| 7005 |
+
{"current_steps": 34935, "total_steps": 38160, "loss": 0.55, "lr": 1.0806445133927311e-06, "epoch": 18.309748427672957, "percentage": 91.55, "elapsed_time": "1:46:26", "remaining_time": "0:09:49", "throughput": 3576.05, "total_tokens": 22838776}
|
| 7006 |
+
{"current_steps": 34940, "total_steps": 38160, "loss": 0.4543, "lr": 1.0773215625121457e-06, "epoch": 18.31236897274633, "percentage": 91.56, "elapsed_time": "1:46:27", "remaining_time": "0:09:48", "throughput": 3576.05, "total_tokens": 22842008}
|
| 7007 |
+
{"current_steps": 34945, "total_steps": 38160, "loss": 0.5504, "lr": 1.0740036159829715e-06, "epoch": 18.314989517819708, "percentage": 91.57, "elapsed_time": "1:46:28", "remaining_time": "0:09:47", "throughput": 3576.17, "total_tokens": 22846040}
|
| 7008 |
+
{"current_steps": 34950, "total_steps": 38160, "loss": 0.3854, "lr": 1.0706906744992724e-06, "epoch": 18.31761006289308, "percentage": 91.59, "elapsed_time": "1:46:29", "remaining_time": "0:09:46", "throughput": 3576.23, "total_tokens": 22850328}
|
| 7009 |
+
{"current_steps": 34955, "total_steps": 38160, "loss": 0.5786, "lr": 1.0673827387540857e-06, "epoch": 18.320230607966458, "percentage": 91.6, "elapsed_time": "1:46:30", "remaining_time": "0:09:45", "throughput": 3576.24, "total_tokens": 22853624}
|
| 7010 |
+
{"current_steps": 34960, "total_steps": 38160, "loss": 0.6421, "lr": 1.0640798094393916e-06, "epoch": 18.32285115303983, "percentage": 91.61, "elapsed_time": "1:46:31", "remaining_time": "0:09:45", "throughput": 3576.29, "total_tokens": 22857240}
|
| 7011 |
+
{"current_steps": 34965, "total_steps": 38160, "loss": 0.416, "lr": 1.060781887246126e-06, "epoch": 18.32547169811321, "percentage": 91.63, "elapsed_time": "1:46:32", "remaining_time": "0:09:44", "throughput": 3576.28, "total_tokens": 22860216}
|
| 7012 |
+
{"current_steps": 34970, "total_steps": 38160, "loss": 0.3453, "lr": 1.057488972864179e-06, "epoch": 18.328092243186582, "percentage": 91.64, "elapsed_time": "1:46:33", "remaining_time": "0:09:43", "throughput": 3576.34, "total_tokens": 22864920}
|
| 7013 |
+
{"current_steps": 34975, "total_steps": 38160, "loss": 0.5024, "lr": 1.0542010669823855e-06, "epoch": 18.33071278825996, "percentage": 91.65, "elapsed_time": "1:46:34", "remaining_time": "0:09:42", "throughput": 3576.32, "total_tokens": 22867928}
|
| 7014 |
+
{"current_steps": 34980, "total_steps": 38160, "loss": 0.4994, "lr": 1.0509181702885395e-06, "epoch": 18.333333333333332, "percentage": 91.67, "elapsed_time": "1:46:35", "remaining_time": "0:09:41", "throughput": 3576.36, "total_tokens": 22871256}
|
| 7015 |
+
{"current_steps": 34985, "total_steps": 38160, "loss": 0.5738, "lr": 1.047640283469392e-06, "epoch": 18.33595387840671, "percentage": 91.68, "elapsed_time": "1:46:36", "remaining_time": "0:09:40", "throughput": 3576.48, "total_tokens": 22875544}
|
| 7016 |
+
{"current_steps": 34990, "total_steps": 38160, "loss": 0.5409, "lr": 1.0443674072106308e-06, "epoch": 18.338574423480082, "percentage": 91.69, "elapsed_time": "1:46:36", "remaining_time": "0:09:39", "throughput": 3576.48, "total_tokens": 22878456}
|
| 7017 |
+
{"current_steps": 34995, "total_steps": 38160, "loss": 0.5867, "lr": 1.041099542196905e-06, "epoch": 18.34119496855346, "percentage": 91.71, "elapsed_time": "1:46:37", "remaining_time": "0:09:38", "throughput": 3576.54, "total_tokens": 22882168}
|
| 7018 |
+
{"current_steps": 35000, "total_steps": 38160, "loss": 0.4293, "lr": 1.0378366891118234e-06, "epoch": 18.343815513626833, "percentage": 91.72, "elapsed_time": "1:46:38", "remaining_time": "0:09:37", "throughput": 3576.45, "total_tokens": 22884824}
|
| 7019 |
+
{"current_steps": 35005, "total_steps": 38160, "loss": 0.4807, "lr": 1.0345788486379265e-06, "epoch": 18.34643605870021, "percentage": 91.73, "elapsed_time": "1:46:39", "remaining_time": "0:09:36", "throughput": 3576.46, "total_tokens": 22887864}
|
| 7020 |
+
{"current_steps": 35010, "total_steps": 38160, "loss": 0.5737, "lr": 1.0313260214567272e-06, "epoch": 18.349056603773583, "percentage": 91.75, "elapsed_time": "1:46:40", "remaining_time": "0:09:35", "throughput": 3576.56, "total_tokens": 22892184}
|
| 7021 |
+
{"current_steps": 35015, "total_steps": 38160, "loss": 0.5277, "lr": 1.0280782082486729e-06, "epoch": 18.35167714884696, "percentage": 91.76, "elapsed_time": "1:46:41", "remaining_time": "0:09:34", "throughput": 3576.54, "total_tokens": 22895096}
|
| 7022 |
+
{"current_steps": 35020, "total_steps": 38160, "loss": 0.4892, "lr": 1.02483540969317e-06, "epoch": 18.354297693920337, "percentage": 91.77, "elapsed_time": "1:46:42", "remaining_time": "0:09:34", "throughput": 3576.54, "total_tokens": 22898168}
|
| 7023 |
+
{"current_steps": 35025, "total_steps": 38160, "loss": 0.4718, "lr": 1.0215976264685763e-06, "epoch": 18.35691823899371, "percentage": 91.78, "elapsed_time": "1:46:43", "remaining_time": "0:09:33", "throughput": 3576.56, "total_tokens": 22901368}
|
| 7024 |
+
{"current_steps": 35030, "total_steps": 38160, "loss": 0.5924, "lr": 1.0183648592522021e-06, "epoch": 18.359538784067087, "percentage": 91.8, "elapsed_time": "1:46:44", "remaining_time": "0:09:32", "throughput": 3576.6, "total_tokens": 22905048}
|
| 7025 |
+
{"current_steps": 35035, "total_steps": 38160, "loss": 0.4939, "lr": 1.0151371087203015e-06, "epoch": 18.36215932914046, "percentage": 91.81, "elapsed_time": "1:46:44", "remaining_time": "0:09:31", "throughput": 3576.56, "total_tokens": 22907800}
|
| 7026 |
+
{"current_steps": 35040, "total_steps": 38160, "loss": 0.5045, "lr": 1.0119143755480815e-06, "epoch": 18.364779874213838, "percentage": 91.82, "elapsed_time": "1:46:45", "remaining_time": "0:09:30", "throughput": 3576.59, "total_tokens": 22911480}
|
| 7027 |
+
{"current_steps": 35045, "total_steps": 38160, "loss": 0.4024, "lr": 1.0086966604097026e-06, "epoch": 18.36740041928721, "percentage": 91.84, "elapsed_time": "1:46:46", "remaining_time": "0:09:29", "throughput": 3576.64, "total_tokens": 22914936}
|
| 7028 |
+
{"current_steps": 35050, "total_steps": 38160, "loss": 0.7257, "lr": 1.0054839639782766e-06, "epoch": 18.370020964360588, "percentage": 91.85, "elapsed_time": "1:46:47", "remaining_time": "0:09:28", "throughput": 3576.68, "total_tokens": 22918424}
|
| 7029 |
+
{"current_steps": 35055, "total_steps": 38160, "loss": 0.5147, "lr": 1.00227628692586e-06, "epoch": 18.37264150943396, "percentage": 91.86, "elapsed_time": "1:46:48", "remaining_time": "0:09:27", "throughput": 3576.59, "total_tokens": 22921112}
|
| 7030 |
+
{"current_steps": 35060, "total_steps": 38160, "loss": 0.4996, "lr": 9.990736299234692e-07, "epoch": 18.37526205450734, "percentage": 91.88, "elapsed_time": "1:46:49", "remaining_time": "0:09:26", "throughput": 3576.58, "total_tokens": 22924024}
|
| 7031 |
+
{"current_steps": 35065, "total_steps": 38160, "loss": 0.3625, "lr": 9.958759936410573e-07, "epoch": 18.377882599580712, "percentage": 91.89, "elapsed_time": "1:46:50", "remaining_time": "0:09:25", "throughput": 3576.57, "total_tokens": 22927128}
|
| 7032 |
+
{"current_steps": 35070, "total_steps": 38160, "loss": 0.33, "lr": 9.926833787475304e-07, "epoch": 18.38050314465409, "percentage": 91.9, "elapsed_time": "1:46:51", "remaining_time": "0:09:24", "throughput": 3576.55, "total_tokens": 22929912}
|
| 7033 |
+
{"current_steps": 35075, "total_steps": 38160, "loss": 0.4341, "lr": 9.89495785910749e-07, "epoch": 18.383123689727462, "percentage": 91.92, "elapsed_time": "1:46:51", "remaining_time": "0:09:23", "throughput": 3576.5, "total_tokens": 22932504}
|
| 7034 |
+
{"current_steps": 35080, "total_steps": 38160, "loss": 0.384, "lr": 9.86313215797524e-07, "epoch": 18.38574423480084, "percentage": 91.93, "elapsed_time": "1:46:52", "remaining_time": "0:09:23", "throughput": 3576.61, "total_tokens": 22936600}
|
| 7035 |
+
{"current_steps": 35085, "total_steps": 38160, "loss": 0.4732, "lr": 9.831356690736149e-07, "epoch": 18.388364779874212, "percentage": 91.94, "elapsed_time": "1:46:53", "remaining_time": "0:09:22", "throughput": 3576.62, "total_tokens": 22939864}
|
| 7036 |
+
{"current_steps": 35090, "total_steps": 38160, "loss": 0.6091, "lr": 9.799631464037256e-07, "epoch": 18.39098532494759, "percentage": 91.95, "elapsed_time": "1:46:54", "remaining_time": "0:09:21", "throughput": 3576.68, "total_tokens": 22943480}
|
| 7037 |
+
{"current_steps": 35095, "total_steps": 38160, "loss": 0.5458, "lr": 9.76795648451509e-07, "epoch": 18.393605870020963, "percentage": 91.97, "elapsed_time": "1:46:55", "remaining_time": "0:09:20", "throughput": 3576.73, "total_tokens": 22946712}
|
| 7038 |
+
{"current_steps": 35100, "total_steps": 38160, "loss": 0.5107, "lr": 9.73633175879568e-07, "epoch": 18.39622641509434, "percentage": 91.98, "elapsed_time": "1:46:56", "remaining_time": "0:09:19", "throughput": 3576.79, "total_tokens": 22950392}
|
| 7039 |
+
{"current_steps": 35105, "total_steps": 38160, "loss": 0.5007, "lr": 9.704757293494627e-07, "epoch": 18.398846960167713, "percentage": 91.99, "elapsed_time": "1:46:57", "remaining_time": "0:09:18", "throughput": 3576.86, "total_tokens": 22954264}
|
| 7040 |
+
{"current_steps": 35110, "total_steps": 38160, "loss": 0.4014, "lr": 9.673233095216922e-07, "epoch": 18.40146750524109, "percentage": 92.01, "elapsed_time": "1:46:58", "remaining_time": "0:09:17", "throughput": 3576.93, "total_tokens": 22958232}
|
| 7041 |
+
{"current_steps": 35115, "total_steps": 38160, "loss": 0.67, "lr": 9.641759170557068e-07, "epoch": 18.404088050314467, "percentage": 92.02, "elapsed_time": "1:46:59", "remaining_time": "0:09:16", "throughput": 3576.95, "total_tokens": 22961208}
|
| 7042 |
+
{"current_steps": 35120, "total_steps": 38160, "loss": 0.3628, "lr": 9.610335526099024e-07, "epoch": 18.40670859538784, "percentage": 92.03, "elapsed_time": "1:47:00", "remaining_time": "0:09:15", "throughput": 3577.09, "total_tokens": 22966296}
|
| 7043 |
+
{"current_steps": 35125, "total_steps": 38160, "loss": 0.4562, "lr": 9.578962168416278e-07, "epoch": 18.409329140461217, "percentage": 92.05, "elapsed_time": "1:47:01", "remaining_time": "0:09:14", "throughput": 3577.04, "total_tokens": 22968856}
|
| 7044 |
+
{"current_steps": 35130, "total_steps": 38160, "loss": 0.3192, "lr": 9.547639104071775e-07, "epoch": 18.41194968553459, "percentage": 92.06, "elapsed_time": "1:47:02", "remaining_time": "0:09:13", "throughput": 3577.07, "total_tokens": 22972056}
|
| 7045 |
+
{"current_steps": 35135, "total_steps": 38160, "loss": 0.3711, "lr": 9.516366339617944e-07, "epoch": 18.414570230607968, "percentage": 92.07, "elapsed_time": "1:47:02", "remaining_time": "0:09:12", "throughput": 3577.05, "total_tokens": 22974840}
|
| 7046 |
+
{"current_steps": 35140, "total_steps": 38160, "loss": 0.5327, "lr": 9.485143881596714e-07, "epoch": 18.41719077568134, "percentage": 92.09, "elapsed_time": "1:47:03", "remaining_time": "0:09:12", "throughput": 3577.11, "total_tokens": 22978520}
|
| 7047 |
+
{"current_steps": 35145, "total_steps": 38160, "loss": 0.4524, "lr": 9.453971736539447e-07, "epoch": 18.419811320754718, "percentage": 92.1, "elapsed_time": "1:47:04", "remaining_time": "0:09:11", "throughput": 3577.15, "total_tokens": 22982136}
|
| 7048 |
+
{"current_steps": 35150, "total_steps": 38160, "loss": 0.4697, "lr": 9.42284991096698e-07, "epoch": 18.42243186582809, "percentage": 92.11, "elapsed_time": "1:47:05", "remaining_time": "0:09:10", "throughput": 3577.16, "total_tokens": 22985304}
|
| 7049 |
+
{"current_steps": 35155, "total_steps": 38160, "loss": 0.444, "lr": 9.391778411389634e-07, "epoch": 18.42505241090147, "percentage": 92.13, "elapsed_time": "1:47:06", "remaining_time": "0:09:09", "throughput": 3577.19, "total_tokens": 22988856}
|
| 7050 |
+
{"current_steps": 35160, "total_steps": 38160, "loss": 0.4057, "lr": 9.360757244307267e-07, "epoch": 18.427672955974842, "percentage": 92.14, "elapsed_time": "1:47:07", "remaining_time": "0:09:08", "throughput": 3577.19, "total_tokens": 22991896}
|
| 7051 |
+
{"current_steps": 35165, "total_steps": 38160, "loss": 0.4598, "lr": 9.329786416209157e-07, "epoch": 18.43029350104822, "percentage": 92.15, "elapsed_time": "1:47:08", "remaining_time": "0:09:07", "throughput": 3577.18, "total_tokens": 22994808}
|
| 7052 |
+
{"current_steps": 35170, "total_steps": 38160, "loss": 0.4823, "lr": 9.298865933574014e-07, "epoch": 18.432914046121592, "percentage": 92.16, "elapsed_time": "1:47:09", "remaining_time": "0:09:06", "throughput": 3577.13, "total_tokens": 22997560}
|
| 7053 |
+
{"current_steps": 35175, "total_steps": 38160, "loss": 0.5996, "lr": 9.267995802870022e-07, "epoch": 18.43553459119497, "percentage": 92.18, "elapsed_time": "1:47:09", "remaining_time": "0:09:05", "throughput": 3577.12, "total_tokens": 23000696}
|
| 7054 |
+
{"current_steps": 35180, "total_steps": 38160, "loss": 0.4745, "lr": 9.237176030554878e-07, "epoch": 18.438155136268342, "percentage": 92.19, "elapsed_time": "1:47:10", "remaining_time": "0:09:04", "throughput": 3577.07, "total_tokens": 23003320}
|
| 7055 |
+
{"current_steps": 35185, "total_steps": 38160, "loss": 0.5135, "lr": 9.206406623075758e-07, "epoch": 18.44077568134172, "percentage": 92.2, "elapsed_time": "1:47:11", "remaining_time": "0:09:03", "throughput": 3577.09, "total_tokens": 23006456}
|
| 7056 |
+
{"current_steps": 35190, "total_steps": 38160, "loss": 0.4353, "lr": 9.175687586869292e-07, "epoch": 18.443396226415093, "percentage": 92.22, "elapsed_time": "1:47:12", "remaining_time": "0:09:02", "throughput": 3577.17, "total_tokens": 23010712}
|
| 7057 |
+
{"current_steps": 35195, "total_steps": 38160, "loss": 0.4854, "lr": 9.145018928361476e-07, "epoch": 18.44601677148847, "percentage": 92.23, "elapsed_time": "1:47:13", "remaining_time": "0:09:01", "throughput": 3577.25, "total_tokens": 23014232}
|
| 7058 |
+
{"current_steps": 35200, "total_steps": 38160, "loss": 0.4428, "lr": 9.114400653967903e-07, "epoch": 18.448637316561843, "percentage": 92.24, "elapsed_time": "1:47:14", "remaining_time": "0:09:01", "throughput": 3577.23, "total_tokens": 23016952}
|
| 7059 |
+
{"current_steps": 35205, "total_steps": 38160, "loss": 0.4645, "lr": 9.083832770093531e-07, "epoch": 18.45125786163522, "percentage": 92.26, "elapsed_time": "1:47:15", "remaining_time": "0:09:00", "throughput": 3577.23, "total_tokens": 23019832}
|
| 7060 |
+
{"current_steps": 35210, "total_steps": 38160, "loss": 0.5517, "lr": 9.053315283132802e-07, "epoch": 18.453878406708597, "percentage": 92.27, "elapsed_time": "1:47:15", "remaining_time": "0:08:59", "throughput": 3577.16, "total_tokens": 23022264}
|
| 7061 |
+
{"current_steps": 35215, "total_steps": 38160, "loss": 0.3976, "lr": 9.022848199469663e-07, "epoch": 18.45649895178197, "percentage": 92.28, "elapsed_time": "1:47:16", "remaining_time": "0:08:58", "throughput": 3577.21, "total_tokens": 23025912}
|
| 7062 |
+
{"current_steps": 35220, "total_steps": 38160, "loss": 0.3996, "lr": 8.992431525477518e-07, "epoch": 18.459119496855347, "percentage": 92.3, "elapsed_time": "1:47:17", "remaining_time": "0:08:57", "throughput": 3577.3, "total_tokens": 23029560}
|
| 7063 |
+
{"current_steps": 35225, "total_steps": 38160, "loss": 0.4938, "lr": 8.962065267519082e-07, "epoch": 18.46174004192872, "percentage": 92.31, "elapsed_time": "1:47:18", "remaining_time": "0:08:56", "throughput": 3577.4, "total_tokens": 23033176}
|
| 7064 |
+
{"current_steps": 35230, "total_steps": 38160, "loss": 0.4625, "lr": 8.931749431946718e-07, "epoch": 18.464360587002098, "percentage": 92.32, "elapsed_time": "1:47:19", "remaining_time": "0:08:55", "throughput": 3577.41, "total_tokens": 23036568}
|
| 7065 |
+
{"current_steps": 35235, "total_steps": 38160, "loss": 0.5316, "lr": 8.901484025102103e-07, "epoch": 18.46698113207547, "percentage": 92.33, "elapsed_time": "1:47:20", "remaining_time": "0:08:54", "throughput": 3577.39, "total_tokens": 23039448}
|
| 7066 |
+
{"current_steps": 35240, "total_steps": 38160, "loss": 0.4954, "lr": 8.871269053316422e-07, "epoch": 18.469601677148848, "percentage": 92.35, "elapsed_time": "1:47:21", "remaining_time": "0:08:53", "throughput": 3577.48, "total_tokens": 23043384}
|
| 7067 |
+
{"current_steps": 35245, "total_steps": 38160, "loss": 0.595, "lr": 8.841104522910343e-07, "epoch": 18.47222222222222, "percentage": 92.36, "elapsed_time": "1:47:22", "remaining_time": "0:08:52", "throughput": 3577.55, "total_tokens": 23047128}
|
| 7068 |
+
{"current_steps": 35250, "total_steps": 38160, "loss": 0.5177, "lr": 8.8109904401939e-07, "epoch": 18.4748427672956, "percentage": 92.37, "elapsed_time": "1:47:22", "remaining_time": "0:08:51", "throughput": 3577.56, "total_tokens": 23050072}
|
| 7069 |
+
{"current_steps": 35255, "total_steps": 38160, "loss": 0.486, "lr": 8.780926811466639e-07, "epoch": 18.47746331236897, "percentage": 92.39, "elapsed_time": "1:47:23", "remaining_time": "0:08:50", "throughput": 3577.66, "total_tokens": 23053688}
|
| 7070 |
+
{"current_steps": 35260, "total_steps": 38160, "loss": 0.4018, "lr": 8.7509136430175e-07, "epoch": 18.48008385744235, "percentage": 92.4, "elapsed_time": "1:47:24", "remaining_time": "0:08:50", "throughput": 3577.63, "total_tokens": 23056440}
|
| 7071 |
+
{"current_steps": 35265, "total_steps": 38160, "loss": 0.4344, "lr": 8.720950941124877e-07, "epoch": 18.482704402515722, "percentage": 92.41, "elapsed_time": "1:47:25", "remaining_time": "0:08:49", "throughput": 3577.72, "total_tokens": 23060120}
|
| 7072 |
+
{"current_steps": 35270, "total_steps": 38160, "loss": 0.5524, "lr": 8.691038712056732e-07, "epoch": 18.4853249475891, "percentage": 92.43, "elapsed_time": "1:47:26", "remaining_time": "0:08:48", "throughput": 3577.77, "total_tokens": 23063544}
|
| 7073 |
+
{"current_steps": 35275, "total_steps": 38160, "loss": 0.394, "lr": 8.66117696207025e-07, "epoch": 18.487945492662472, "percentage": 92.44, "elapsed_time": "1:47:27", "remaining_time": "0:08:47", "throughput": 3577.85, "total_tokens": 23067096}
|
| 7074 |
+
{"current_steps": 35280, "total_steps": 38160, "loss": 0.3864, "lr": 8.631365697412186e-07, "epoch": 18.49056603773585, "percentage": 92.45, "elapsed_time": "1:47:28", "remaining_time": "0:08:46", "throughput": 3577.86, "total_tokens": 23070328}
|
| 7075 |
+
{"current_steps": 35285, "total_steps": 38160, "loss": 0.5685, "lr": 8.601604924318802e-07, "epoch": 18.493186582809223, "percentage": 92.47, "elapsed_time": "1:47:29", "remaining_time": "0:08:45", "throughput": 3577.98, "total_tokens": 23074648}
|
| 7076 |
+
{"current_steps": 35290, "total_steps": 38160, "loss": 0.4489, "lr": 8.571894649015588e-07, "epoch": 18.4958071278826, "percentage": 92.48, "elapsed_time": "1:47:29", "remaining_time": "0:08:44", "throughput": 3577.9, "total_tokens": 23077400}
|
| 7077 |
+
{"current_steps": 35295, "total_steps": 38160, "loss": 0.5857, "lr": 8.542234877717686e-07, "epoch": 18.498427672955973, "percentage": 92.49, "elapsed_time": "1:47:30", "remaining_time": "0:08:43", "throughput": 3577.83, "total_tokens": 23079992}
|
| 7078 |
+
{"current_steps": 35300, "total_steps": 38160, "loss": 0.413, "lr": 8.512625616629549e-07, "epoch": 18.50104821802935, "percentage": 92.51, "elapsed_time": "1:47:31", "remaining_time": "0:08:42", "throughput": 3577.83, "total_tokens": 23082936}
|
| 7079 |
+
{"current_steps": 35305, "total_steps": 38160, "loss": 0.4488, "lr": 8.483066871945083e-07, "epoch": 18.503668763102727, "percentage": 92.52, "elapsed_time": "1:47:32", "remaining_time": "0:08:41", "throughput": 3577.74, "total_tokens": 23085528}
|
| 7080 |
+
{"current_steps": 35310, "total_steps": 38160, "loss": 0.4908, "lr": 8.453558649847676e-07, "epoch": 18.5062893081761, "percentage": 92.53, "elapsed_time": "1:47:33", "remaining_time": "0:08:40", "throughput": 3577.78, "total_tokens": 23089016}
|
| 7081 |
+
{"current_steps": 35315, "total_steps": 38160, "loss": 0.4617, "lr": 8.424100956510112e-07, "epoch": 18.508909853249477, "percentage": 92.54, "elapsed_time": "1:47:34", "remaining_time": "0:08:39", "throughput": 3577.69, "total_tokens": 23091512}
|
| 7082 |
+
{"current_steps": 35320, "total_steps": 38160, "loss": 0.6718, "lr": 8.394693798094544e-07, "epoch": 18.51153039832285, "percentage": 92.56, "elapsed_time": "1:47:35", "remaining_time": "0:08:39", "throughput": 3577.73, "total_tokens": 23095096}
|
| 7083 |
+
{"current_steps": 35325, "total_steps": 38160, "loss": 0.4831, "lr": 8.365337180752691e-07, "epoch": 18.514150943396228, "percentage": 92.57, "elapsed_time": "1:47:36", "remaining_time": "0:08:38", "throughput": 3577.79, "total_tokens": 23098904}
|
| 7084 |
+
{"current_steps": 35330, "total_steps": 38160, "loss": 0.3937, "lr": 8.336031110625558e-07, "epoch": 18.5167714884696, "percentage": 92.58, "elapsed_time": "1:47:37", "remaining_time": "0:08:37", "throughput": 3577.77, "total_tokens": 23101944}
|
| 7085 |
+
{"current_steps": 35335, "total_steps": 38160, "loss": 0.4363, "lr": 8.306775593843657e-07, "epoch": 18.519392033542978, "percentage": 92.6, "elapsed_time": "1:47:38", "remaining_time": "0:08:36", "throughput": 3577.78, "total_tokens": 23105816}
|
| 7086 |
+
{"current_steps": 35340, "total_steps": 38160, "loss": 0.4513, "lr": 8.277570636526955e-07, "epoch": 18.52201257861635, "percentage": 92.61, "elapsed_time": "1:47:39", "remaining_time": "0:08:35", "throughput": 3577.81, "total_tokens": 23109304}
|
| 7087 |
+
{"current_steps": 35345, "total_steps": 38160, "loss": 0.4345, "lr": 8.24841624478473e-07, "epoch": 18.52463312368973, "percentage": 92.62, "elapsed_time": "1:47:40", "remaining_time": "0:08:34", "throughput": 3577.83, "total_tokens": 23112984}
|
| 7088 |
+
{"current_steps": 35350, "total_steps": 38160, "loss": 0.4219, "lr": 8.219312424715825e-07, "epoch": 18.5272536687631, "percentage": 92.64, "elapsed_time": "1:47:40", "remaining_time": "0:08:33", "throughput": 3577.79, "total_tokens": 23115832}
|
| 7089 |
+
{"current_steps": 35355, "total_steps": 38160, "loss": 0.5102, "lr": 8.190259182408345e-07, "epoch": 18.52987421383648, "percentage": 92.65, "elapsed_time": "1:47:41", "remaining_time": "0:08:32", "throughput": 3577.73, "total_tokens": 23118872}
|
| 7090 |
+
{"current_steps": 35360, "total_steps": 38160, "loss": 0.6024, "lr": 8.161256523939925e-07, "epoch": 18.532494758909852, "percentage": 92.66, "elapsed_time": "1:47:42", "remaining_time": "0:08:31", "throughput": 3577.74, "total_tokens": 23121880}
|
| 7091 |
+
{"current_steps": 35365, "total_steps": 38160, "loss": 0.4903, "lr": 8.132304455377576e-07, "epoch": 18.53511530398323, "percentage": 92.68, "elapsed_time": "1:47:43", "remaining_time": "0:08:30", "throughput": 3577.8, "total_tokens": 23125528}
|
| 7092 |
+
{"current_steps": 35370, "total_steps": 38160, "loss": 0.5947, "lr": 8.103402982777813e-07, "epoch": 18.537735849056602, "percentage": 92.69, "elapsed_time": "1:47:44", "remaining_time": "0:08:29", "throughput": 3577.97, "total_tokens": 23130360}
|
| 7093 |
+
{"current_steps": 35375, "total_steps": 38160, "loss": 0.4047, "lr": 8.07455211218644e-07, "epoch": 18.54035639412998, "percentage": 92.7, "elapsed_time": "1:47:45", "remaining_time": "0:08:29", "throughput": 3578.03, "total_tokens": 23133912}
|
| 7094 |
+
{"current_steps": 35380, "total_steps": 38160, "loss": 0.5035, "lr": 8.045751849638738e-07, "epoch": 18.542976939203353, "percentage": 92.71, "elapsed_time": "1:47:46", "remaining_time": "0:08:28", "throughput": 3577.96, "total_tokens": 23136440}
|
| 7095 |
+
{"current_steps": 35385, "total_steps": 38160, "loss": 0.4814, "lr": 8.017002201159363e-07, "epoch": 18.54559748427673, "percentage": 92.73, "elapsed_time": "1:47:47", "remaining_time": "0:08:27", "throughput": 3577.97, "total_tokens": 23139544}
|
| 7096 |
+
{"current_steps": 35390, "total_steps": 38160, "loss": 0.4079, "lr": 7.988303172762418e-07, "epoch": 18.548218029350103, "percentage": 92.74, "elapsed_time": "1:47:48", "remaining_time": "0:08:26", "throughput": 3578.16, "total_tokens": 23144408}
|
| 7097 |
+
{"current_steps": 35395, "total_steps": 38160, "loss": 0.5361, "lr": 7.959654770451463e-07, "epoch": 18.55083857442348, "percentage": 92.75, "elapsed_time": "1:47:49", "remaining_time": "0:08:25", "throughput": 3578.21, "total_tokens": 23147960}
|
| 7098 |
+
{"current_steps": 35400, "total_steps": 38160, "loss": 0.4295, "lr": 7.9310570002194e-07, "epoch": 18.553459119496857, "percentage": 92.77, "elapsed_time": "1:47:49", "remaining_time": "0:08:24", "throughput": 3578.24, "total_tokens": 23151096}
|
| 7099 |
+
{"current_steps": 35405, "total_steps": 38160, "loss": 0.4769, "lr": 7.902509868048552e-07, "epoch": 18.55607966457023, "percentage": 92.78, "elapsed_time": "1:47:50", "remaining_time": "0:08:23", "throughput": 3578.28, "total_tokens": 23154424}
|
| 7100 |
+
{"current_steps": 35410, "total_steps": 38160, "loss": 0.3535, "lr": 7.874013379910616e-07, "epoch": 18.558700209643607, "percentage": 92.79, "elapsed_time": "1:47:51", "remaining_time": "0:08:22", "throughput": 3578.19, "total_tokens": 23157048}
|
| 7101 |
+
{"current_steps": 35415, "total_steps": 38160, "loss": 0.3748, "lr": 7.845567541766769e-07, "epoch": 18.56132075471698, "percentage": 92.81, "elapsed_time": "1:47:52", "remaining_time": "0:08:21", "throughput": 3578.22, "total_tokens": 23160792}
|
| 7102 |
+
{"current_steps": 35420, "total_steps": 38160, "loss": 0.4829, "lr": 7.817172359567526e-07, "epoch": 18.563941299790358, "percentage": 92.82, "elapsed_time": "1:47:53", "remaining_time": "0:08:20", "throughput": 3578.2, "total_tokens": 23164248}
|
| 7103 |
+
{"current_steps": 35425, "total_steps": 38160, "loss": 0.598, "lr": 7.788827839252888e-07, "epoch": 18.56656184486373, "percentage": 92.83, "elapsed_time": "1:47:54", "remaining_time": "0:08:19", "throughput": 3578.23, "total_tokens": 23167832}
|
| 7104 |
+
{"current_steps": 35430, "total_steps": 38160, "loss": 0.4055, "lr": 7.760533986752222e-07, "epoch": 18.569182389937108, "percentage": 92.85, "elapsed_time": "1:47:55", "remaining_time": "0:08:18", "throughput": 3578.35, "total_tokens": 23172152}
|
| 7105 |
+
{"current_steps": 35435, "total_steps": 38160, "loss": 0.4386, "lr": 7.732290807984155e-07, "epoch": 18.57180293501048, "percentage": 92.86, "elapsed_time": "1:47:56", "remaining_time": "0:08:18", "throughput": 3578.33, "total_tokens": 23175000}
|
| 7106 |
+
{"current_steps": 35440, "total_steps": 38160, "loss": 0.4927, "lr": 7.704098308856933e-07, "epoch": 18.57442348008386, "percentage": 92.87, "elapsed_time": "1:47:57", "remaining_time": "0:08:17", "throughput": 3578.34, "total_tokens": 23177976}
|
| 7107 |
+
{"current_steps": 35445, "total_steps": 38160, "loss": 0.4589, "lr": 7.675956495268088e-07, "epoch": 18.57704402515723, "percentage": 92.89, "elapsed_time": "1:47:58", "remaining_time": "0:08:16", "throughput": 3578.32, "total_tokens": 23180792}
|
| 7108 |
+
{"current_steps": 35450, "total_steps": 38160, "loss": 0.6853, "lr": 7.647865373104551e-07, "epoch": 18.57966457023061, "percentage": 92.9, "elapsed_time": "1:47:59", "remaining_time": "0:08:15", "throughput": 3578.38, "total_tokens": 23184344}
|
| 7109 |
+
{"current_steps": 35455, "total_steps": 38160, "loss": 0.4811, "lr": 7.619824948242732e-07, "epoch": 18.582285115303982, "percentage": 92.91, "elapsed_time": "1:47:59", "remaining_time": "0:08:14", "throughput": 3578.42, "total_tokens": 23187640}
|
| 7110 |
+
{"current_steps": 35460, "total_steps": 38160, "loss": 0.6901, "lr": 7.5918352265483e-07, "epoch": 18.58490566037736, "percentage": 92.92, "elapsed_time": "1:48:00", "remaining_time": "0:08:13", "throughput": 3578.47, "total_tokens": 23191256}
|
| 7111 |
+
{"current_steps": 35465, "total_steps": 38160, "loss": 0.5452, "lr": 7.563896213876348e-07, "epoch": 18.587526205450732, "percentage": 92.94, "elapsed_time": "1:48:01", "remaining_time": "0:08:12", "throughput": 3578.41, "total_tokens": 23193944}
|
| 7112 |
+
{"current_steps": 35470, "total_steps": 38160, "loss": 0.5506, "lr": 7.53600791607148e-07, "epoch": 18.59014675052411, "percentage": 92.95, "elapsed_time": "1:48:02", "remaining_time": "0:08:11", "throughput": 3578.47, "total_tokens": 23197464}
|
| 7113 |
+
{"current_steps": 35475, "total_steps": 38160, "loss": 0.4011, "lr": 7.508170338967585e-07, "epoch": 18.592767295597483, "percentage": 92.96, "elapsed_time": "1:48:03", "remaining_time": "0:08:10", "throughput": 3578.4, "total_tokens": 23200024}
|
| 7114 |
+
{"current_steps": 35480, "total_steps": 38160, "loss": 0.4914, "lr": 7.480383488387976e-07, "epoch": 18.59538784067086, "percentage": 92.98, "elapsed_time": "1:48:04", "remaining_time": "0:08:09", "throughput": 3578.41, "total_tokens": 23202968}
|
| 7115 |
+
{"current_steps": 35485, "total_steps": 38160, "loss": 0.4438, "lr": 7.452647370145338e-07, "epoch": 18.598008385744233, "percentage": 92.99, "elapsed_time": "1:48:05", "remaining_time": "0:08:08", "throughput": 3578.44, "total_tokens": 23206296}
|
| 7116 |
+
{"current_steps": 35490, "total_steps": 38160, "loss": 0.4851, "lr": 7.424961990041696e-07, "epoch": 18.60062893081761, "percentage": 93.0, "elapsed_time": "1:48:05", "remaining_time": "0:08:07", "throughput": 3578.41, "total_tokens": 23209304}
|
| 7117 |
+
{"current_steps": 35495, "total_steps": 38160, "loss": 0.38, "lr": 7.397327353868583e-07, "epoch": 18.603249475890987, "percentage": 93.02, "elapsed_time": "1:48:06", "remaining_time": "0:08:07", "throughput": 3578.5, "total_tokens": 23213080}
|
| 7118 |
+
{"current_steps": 35500, "total_steps": 38160, "loss": 0.4583, "lr": 7.369743467406848e-07, "epoch": 18.60587002096436, "percentage": 93.03, "elapsed_time": "1:48:07", "remaining_time": "0:08:06", "throughput": 3578.48, "total_tokens": 23215928}
|
| 7119 |
+
{"current_steps": 35505, "total_steps": 38160, "loss": 0.4974, "lr": 7.34221033642668e-07, "epoch": 18.608490566037737, "percentage": 93.04, "elapsed_time": "1:48:08", "remaining_time": "0:08:05", "throughput": 3578.54, "total_tokens": 23219320}
|
| 7120 |
+
{"current_steps": 35510, "total_steps": 38160, "loss": 0.4262, "lr": 7.314727966687751e-07, "epoch": 18.61111111111111, "percentage": 93.06, "elapsed_time": "1:48:09", "remaining_time": "0:08:04", "throughput": 3578.54, "total_tokens": 23222296}
|
| 7121 |
+
{"current_steps": 35515, "total_steps": 38160, "loss": 0.5021, "lr": 7.287296363939045e-07, "epoch": 18.613731656184488, "percentage": 93.07, "elapsed_time": "1:48:10", "remaining_time": "0:08:03", "throughput": 3578.41, "total_tokens": 23224728}
|
| 7122 |
+
{"current_steps": 35520, "total_steps": 38160, "loss": 0.4221, "lr": 7.259915533918888e-07, "epoch": 18.61635220125786, "percentage": 93.08, "elapsed_time": "1:48:11", "remaining_time": "0:08:02", "throughput": 3578.46, "total_tokens": 23228248}
|
| 7123 |
+
{"current_steps": 35525, "total_steps": 38160, "loss": 0.47, "lr": 7.232585482355086e-07, "epoch": 18.618972746331238, "percentage": 93.09, "elapsed_time": "1:48:12", "remaining_time": "0:08:01", "throughput": 3578.61, "total_tokens": 23232600}
|
| 7124 |
+
{"current_steps": 35530, "total_steps": 38160, "loss": 0.5163, "lr": 7.205306214964736e-07, "epoch": 18.62159329140461, "percentage": 93.11, "elapsed_time": "1:48:12", "remaining_time": "0:08:00", "throughput": 3578.58, "total_tokens": 23235384}
|
| 7125 |
+
{"current_steps": 35535, "total_steps": 38160, "loss": 0.4619, "lr": 7.178077737454436e-07, "epoch": 18.62421383647799, "percentage": 93.12, "elapsed_time": "1:48:13", "remaining_time": "0:07:59", "throughput": 3578.59, "total_tokens": 23238744}
|
| 7126 |
+
{"current_steps": 35540, "total_steps": 38160, "loss": 0.4641, "lr": 7.150900055519993e-07, "epoch": 18.62683438155136, "percentage": 93.13, "elapsed_time": "1:48:14", "remaining_time": "0:07:58", "throughput": 3578.58, "total_tokens": 23241720}
|
| 7127 |
+
{"current_steps": 35545, "total_steps": 38160, "loss": 0.5143, "lr": 7.123773174846693e-07, "epoch": 18.62945492662474, "percentage": 93.15, "elapsed_time": "1:48:15", "remaining_time": "0:07:57", "throughput": 3578.57, "total_tokens": 23244696}
|
| 7128 |
+
{"current_steps": 35550, "total_steps": 38160, "loss": 0.3664, "lr": 7.096697101109134e-07, "epoch": 18.632075471698112, "percentage": 93.16, "elapsed_time": "1:48:16", "remaining_time": "0:07:56", "throughput": 3578.68, "total_tokens": 23248536}
|
| 7129 |
+
{"current_steps": 35555, "total_steps": 38160, "loss": 0.4322, "lr": 7.069671839971371e-07, "epoch": 18.63469601677149, "percentage": 93.17, "elapsed_time": "1:48:17", "remaining_time": "0:07:56", "throughput": 3578.67, "total_tokens": 23251352}
|
| 7130 |
+
{"current_steps": 35560, "total_steps": 38160, "loss": 0.4098, "lr": 7.042697397086795e-07, "epoch": 18.637316561844862, "percentage": 93.19, "elapsed_time": "1:48:18", "remaining_time": "0:07:55", "throughput": 3578.7, "total_tokens": 23254520}
|
| 7131 |
+
{"current_steps": 35565, "total_steps": 38160, "loss": 0.5812, "lr": 7.015773778098089e-07, "epoch": 18.63993710691824, "percentage": 93.2, "elapsed_time": "1:48:19", "remaining_time": "0:07:54", "throughput": 3578.92, "total_tokens": 23261752}
|
| 7132 |
+
{"current_steps": 35570, "total_steps": 38160, "loss": 0.5625, "lr": 6.988900988637415e-07, "epoch": 18.642557651991613, "percentage": 93.21, "elapsed_time": "1:48:20", "remaining_time": "0:07:53", "throughput": 3578.99, "total_tokens": 23265176}
|
| 7133 |
+
{"current_steps": 35575, "total_steps": 38160, "loss": 0.4588, "lr": 6.962079034326218e-07, "epoch": 18.64517819706499, "percentage": 93.23, "elapsed_time": "1:48:21", "remaining_time": "0:07:52", "throughput": 3578.95, "total_tokens": 23267800}
|
| 7134 |
+
{"current_steps": 35580, "total_steps": 38160, "loss": 0.4087, "lr": 6.935307920775346e-07, "epoch": 18.647798742138363, "percentage": 93.24, "elapsed_time": "1:48:22", "remaining_time": "0:07:51", "throughput": 3578.92, "total_tokens": 23270488}
|
| 7135 |
+
{"current_steps": 35585, "total_steps": 38160, "loss": 0.5108, "lr": 6.90858765358507e-07, "epoch": 18.65041928721174, "percentage": 93.25, "elapsed_time": "1:48:22", "remaining_time": "0:07:50", "throughput": 3578.97, "total_tokens": 23274008}
|
| 7136 |
+
{"current_steps": 35590, "total_steps": 38160, "loss": 0.3167, "lr": 6.881918238344915e-07, "epoch": 18.653039832285117, "percentage": 93.27, "elapsed_time": "1:48:23", "remaining_time": "0:07:49", "throughput": 3579.0, "total_tokens": 23277240}
|
| 7137 |
+
{"current_steps": 35595, "total_steps": 38160, "loss": 0.5475, "lr": 6.855299680633808e-07, "epoch": 18.65566037735849, "percentage": 93.28, "elapsed_time": "1:48:24", "remaining_time": "0:07:48", "throughput": 3578.93, "total_tokens": 23279768}
|
| 7138 |
+
{"current_steps": 35600, "total_steps": 38160, "loss": 0.5637, "lr": 6.828731986020104e-07, "epoch": 18.658280922431867, "percentage": 93.29, "elapsed_time": "1:48:25", "remaining_time": "0:07:47", "throughput": 3578.92, "total_tokens": 23283128}
|
| 7139 |
+
{"current_steps": 35605, "total_steps": 38160, "loss": 0.4306, "lr": 6.802215160061381e-07, "epoch": 18.66090146750524, "percentage": 93.3, "elapsed_time": "1:48:26", "remaining_time": "0:07:46", "throughput": 3578.94, "total_tokens": 23286424}
|
| 7140 |
+
{"current_steps": 35610, "total_steps": 38160, "loss": 0.5598, "lr": 6.775749208304704e-07, "epoch": 18.663522012578618, "percentage": 93.32, "elapsed_time": "1:48:27", "remaining_time": "0:07:45", "throughput": 3578.97, "total_tokens": 23289880}
|
| 7141 |
+
{"current_steps": 35615, "total_steps": 38160, "loss": 0.4934, "lr": 6.749334136286478e-07, "epoch": 18.66614255765199, "percentage": 93.33, "elapsed_time": "1:48:28", "remaining_time": "0:07:45", "throughput": 3579.0, "total_tokens": 23293528}
|
| 7142 |
+
{"current_steps": 35620, "total_steps": 38160, "loss": 0.3559, "lr": 6.722969949532365e-07, "epoch": 18.668763102725368, "percentage": 93.34, "elapsed_time": "1:48:29", "remaining_time": "0:07:44", "throughput": 3579.06, "total_tokens": 23296952}
|
| 7143 |
+
{"current_steps": 35625, "total_steps": 38160, "loss": 0.4485, "lr": 6.69665665355751e-07, "epoch": 18.67138364779874, "percentage": 93.36, "elapsed_time": "1:48:30", "remaining_time": "0:07:43", "throughput": 3578.96, "total_tokens": 23299384}
|
| 7144 |
+
{"current_steps": 35630, "total_steps": 38160, "loss": 0.4796, "lr": 6.670394253866314e-07, "epoch": 18.67400419287212, "percentage": 93.37, "elapsed_time": "1:48:31", "remaining_time": "0:07:42", "throughput": 3579.21, "total_tokens": 23306232}
|
| 7145 |
+
{"current_steps": 35635, "total_steps": 38160, "loss": 0.5896, "lr": 6.644182755952605e-07, "epoch": 18.67662473794549, "percentage": 93.38, "elapsed_time": "1:48:32", "remaining_time": "0:07:41", "throughput": 3579.21, "total_tokens": 23309144}
|
| 7146 |
+
{"current_steps": 35640, "total_steps": 38160, "loss": 0.4343, "lr": 6.618022165299526e-07, "epoch": 18.67924528301887, "percentage": 93.4, "elapsed_time": "1:48:33", "remaining_time": "0:07:40", "throughput": 3579.23, "total_tokens": 23312472}
|
| 7147 |
+
{"current_steps": 35645, "total_steps": 38160, "loss": 0.3926, "lr": 6.591912487379531e-07, "epoch": 18.681865828092242, "percentage": 93.41, "elapsed_time": "1:48:34", "remaining_time": "0:07:39", "throughput": 3579.2, "total_tokens": 23315320}
|
| 7148 |
+
{"current_steps": 35650, "total_steps": 38160, "loss": 0.4866, "lr": 6.565853727654503e-07, "epoch": 18.68448637316562, "percentage": 93.42, "elapsed_time": "1:48:34", "remaining_time": "0:07:38", "throughput": 3579.19, "total_tokens": 23318360}
|
| 7149 |
+
{"current_steps": 35655, "total_steps": 38160, "loss": 0.4276, "lr": 6.539845891575636e-07, "epoch": 18.687106918238992, "percentage": 93.44, "elapsed_time": "1:48:35", "remaining_time": "0:07:37", "throughput": 3579.12, "total_tokens": 23320824}
|
| 7150 |
+
{"current_steps": 35660, "total_steps": 38160, "loss": 0.534, "lr": 6.513888984583466e-07, "epoch": 18.68972746331237, "percentage": 93.45, "elapsed_time": "1:48:36", "remaining_time": "0:07:36", "throughput": 3579.19, "total_tokens": 23324216}
|
| 7151 |
+
{"current_steps": 35665, "total_steps": 38160, "loss": 0.5073, "lr": 6.487983012107873e-07, "epoch": 18.692348008385743, "percentage": 93.46, "elapsed_time": "1:48:37", "remaining_time": "0:07:35", "throughput": 3579.15, "total_tokens": 23326840}
|
| 7152 |
+
{"current_steps": 35670, "total_steps": 38160, "loss": 0.5034, "lr": 6.462127979568133e-07, "epoch": 18.69496855345912, "percentage": 93.47, "elapsed_time": "1:48:38", "remaining_time": "0:07:35", "throughput": 3579.06, "total_tokens": 23329464}
|
| 7153 |
+
{"current_steps": 35675, "total_steps": 38160, "loss": 0.6048, "lr": 6.436323892372781e-07, "epoch": 18.697589098532493, "percentage": 93.49, "elapsed_time": "1:48:39", "remaining_time": "0:07:34", "throughput": 3579.05, "total_tokens": 23332280}
|
| 7154 |
+
{"current_steps": 35680, "total_steps": 38160, "loss": 0.4714, "lr": 6.410570755919721e-07, "epoch": 18.70020964360587, "percentage": 93.5, "elapsed_time": "1:48:39", "remaining_time": "0:07:33", "throughput": 3579.06, "total_tokens": 23335384}
|
| 7155 |
+
{"current_steps": 35685, "total_steps": 38160, "loss": 0.4276, "lr": 6.384868575596281e-07, "epoch": 18.702830188679247, "percentage": 93.51, "elapsed_time": "1:48:40", "remaining_time": "0:07:32", "throughput": 3579.11, "total_tokens": 23338776}
|
| 7156 |
+
{"current_steps": 35690, "total_steps": 38160, "loss": 0.5786, "lr": 6.359217356779024e-07, "epoch": 18.70545073375262, "percentage": 93.53, "elapsed_time": "1:48:41", "remaining_time": "0:07:31", "throughput": 3579.04, "total_tokens": 23341624}
|
| 7157 |
+
{"current_steps": 35695, "total_steps": 38160, "loss": 0.4833, "lr": 6.333617104833878e-07, "epoch": 18.708071278825997, "percentage": 93.54, "elapsed_time": "1:48:42", "remaining_time": "0:07:30", "throughput": 3579.05, "total_tokens": 23345144}
|
| 7158 |
+
{"current_steps": 35700, "total_steps": 38160, "loss": 0.3572, "lr": 6.308067825116142e-07, "epoch": 18.71069182389937, "percentage": 93.55, "elapsed_time": "1:48:43", "remaining_time": "0:07:29", "throughput": 3579.21, "total_tokens": 23350328}
|
| 7159 |
+
{"current_steps": 35705, "total_steps": 38160, "loss": 0.3921, "lr": 6.282569522970433e-07, "epoch": 18.713312368972748, "percentage": 93.57, "elapsed_time": "1:48:44", "remaining_time": "0:07:28", "throughput": 3579.19, "total_tokens": 23353240}
|
| 7160 |
+
{"current_steps": 35710, "total_steps": 38160, "loss": 0.5621, "lr": 6.257122203730731e-07, "epoch": 18.71593291404612, "percentage": 93.58, "elapsed_time": "1:48:45", "remaining_time": "0:07:27", "throughput": 3579.16, "total_tokens": 23356120}
|
| 7161 |
+
{"current_steps": 35715, "total_steps": 38160, "loss": 0.605, "lr": 6.231725872720251e-07, "epoch": 18.718553459119498, "percentage": 93.59, "elapsed_time": "1:48:46", "remaining_time": "0:07:26", "throughput": 3579.15, "total_tokens": 23359032}
|
| 7162 |
+
{"current_steps": 35720, "total_steps": 38160, "loss": 0.4971, "lr": 6.206380535251716e-07, "epoch": 18.72117400419287, "percentage": 93.61, "elapsed_time": "1:48:47", "remaining_time": "0:07:25", "throughput": 3579.24, "total_tokens": 23363064}
|
| 7163 |
+
{"current_steps": 35725, "total_steps": 38160, "loss": 0.5284, "lr": 6.181086196626995e-07, "epoch": 18.72379454926625, "percentage": 93.62, "elapsed_time": "1:48:48", "remaining_time": "0:07:24", "throughput": 3579.16, "total_tokens": 23365432}
|
| 7164 |
+
{"current_steps": 35730, "total_steps": 38160, "loss": 0.5327, "lr": 6.155842862137384e-07, "epoch": 18.72641509433962, "percentage": 93.63, "elapsed_time": "1:48:49", "remaining_time": "0:07:24", "throughput": 3579.12, "total_tokens": 23368120}
|
| 7165 |
+
{"current_steps": 35735, "total_steps": 38160, "loss": 0.5206, "lr": 6.130650537063548e-07, "epoch": 18.729035639413, "percentage": 93.65, "elapsed_time": "1:48:49", "remaining_time": "0:07:23", "throughput": 3579.13, "total_tokens": 23371576}
|
| 7166 |
+
{"current_steps": 35740, "total_steps": 38160, "loss": 0.4509, "lr": 6.105509226675438e-07, "epoch": 18.731656184486372, "percentage": 93.66, "elapsed_time": "1:48:50", "remaining_time": "0:07:22", "throughput": 3579.28, "total_tokens": 23376216}
|
| 7167 |
+
{"current_steps": 35745, "total_steps": 38160, "loss": 0.4069, "lr": 6.08041893623229e-07, "epoch": 18.73427672955975, "percentage": 93.67, "elapsed_time": "1:48:51", "remaining_time": "0:07:21", "throughput": 3579.26, "total_tokens": 23379256}
|
| 7168 |
+
{"current_steps": 35750, "total_steps": 38160, "loss": 0.4567, "lr": 6.055379670982713e-07, "epoch": 18.736897274633122, "percentage": 93.68, "elapsed_time": "1:48:52", "remaining_time": "0:07:20", "throughput": 3579.2, "total_tokens": 23381912}
|
| 7169 |
+
{"current_steps": 35755, "total_steps": 38160, "loss": 0.4599, "lr": 6.030391436164628e-07, "epoch": 18.7395178197065, "percentage": 93.7, "elapsed_time": "1:48:53", "remaining_time": "0:07:19", "throughput": 3579.15, "total_tokens": 23384568}
|
| 7170 |
+
{"current_steps": 35760, "total_steps": 38160, "loss": 0.4536, "lr": 6.005454237005298e-07, "epoch": 18.742138364779873, "percentage": 93.71, "elapsed_time": "1:48:54", "remaining_time": "0:07:18", "throughput": 3579.12, "total_tokens": 23387320}
|
| 7171 |
+
{"current_steps": 35765, "total_steps": 38160, "loss": 0.4297, "lr": 5.980568078721327e-07, "epoch": 18.74475890985325, "percentage": 93.72, "elapsed_time": "1:48:55", "remaining_time": "0:07:17", "throughput": 3579.11, "total_tokens": 23390168}
|
| 7172 |
+
{"current_steps": 35770, "total_steps": 38160, "loss": 0.5082, "lr": 5.955732966518606e-07, "epoch": 18.747379454926623, "percentage": 93.74, "elapsed_time": "1:48:56", "remaining_time": "0:07:16", "throughput": 3579.08, "total_tokens": 23393080}
|
| 7173 |
+
{"current_steps": 35775, "total_steps": 38160, "loss": 0.3648, "lr": 5.930948905592343e-07, "epoch": 18.75, "percentage": 93.75, "elapsed_time": "1:48:56", "remaining_time": "0:07:15", "throughput": 3579.05, "total_tokens": 23395800}
|
| 7174 |
+
{"current_steps": 35780, "total_steps": 38160, "loss": 0.4177, "lr": 5.906215901127054e-07, "epoch": 18.752620545073377, "percentage": 93.76, "elapsed_time": "1:48:57", "remaining_time": "0:07:14", "throughput": 3579.0, "total_tokens": 23398424}
|
| 7175 |
+
{"current_steps": 35785, "total_steps": 38160, "loss": 0.4712, "lr": 5.881533958296631e-07, "epoch": 18.75524109014675, "percentage": 93.78, "elapsed_time": "1:48:58", "remaining_time": "0:07:13", "throughput": 3578.94, "total_tokens": 23400984}
|
| 7176 |
+
{"current_steps": 35790, "total_steps": 38160, "loss": 0.4536, "lr": 5.856903082264248e-07, "epoch": 18.757861635220127, "percentage": 93.79, "elapsed_time": "1:48:59", "remaining_time": "0:07:13", "throughput": 3579.03, "total_tokens": 23404952}
|
| 7177 |
+
{"current_steps": 35795, "total_steps": 38160, "loss": 0.5044, "lr": 5.832323278182422e-07, "epoch": 18.7604821802935, "percentage": 93.8, "elapsed_time": "1:49:00", "remaining_time": "0:07:12", "throughput": 3579.13, "total_tokens": 23409048}
|
| 7178 |
+
{"current_steps": 35800, "total_steps": 38160, "loss": 0.5211, "lr": 5.807794551192986e-07, "epoch": 18.763102725366878, "percentage": 93.82, "elapsed_time": "1:49:01", "remaining_time": "0:07:11", "throughput": 3579.12, "total_tokens": 23411864}
|
| 7179 |
+
{"current_steps": 35805, "total_steps": 38160, "loss": 0.4155, "lr": 5.783316906427e-07, "epoch": 18.76572327044025, "percentage": 93.83, "elapsed_time": "1:49:02", "remaining_time": "0:07:10", "throughput": 3579.13, "total_tokens": 23414936}
|
| 7180 |
+
{"current_steps": 35810, "total_steps": 38160, "loss": 0.4854, "lr": 5.758890349004925e-07, "epoch": 18.768343815513628, "percentage": 93.84, "elapsed_time": "1:49:02", "remaining_time": "0:07:09", "throughput": 3579.12, "total_tokens": 23417976}
|
| 7181 |
+
{"current_steps": 35815, "total_steps": 38160, "loss": 0.4018, "lr": 5.734514884036563e-07, "epoch": 18.770964360587, "percentage": 93.85, "elapsed_time": "1:49:03", "remaining_time": "0:07:08", "throughput": 3579.09, "total_tokens": 23420984}
|
| 7182 |
+
{"current_steps": 35820, "total_steps": 38160, "loss": 0.4059, "lr": 5.710190516620945e-07, "epoch": 18.77358490566038, "percentage": 93.87, "elapsed_time": "1:49:04", "remaining_time": "0:07:07", "throughput": 3579.09, "total_tokens": 23424120}
|
| 7183 |
+
{"current_steps": 35825, "total_steps": 38160, "loss": 0.5631, "lr": 5.685917251846501e-07, "epoch": 18.77620545073375, "percentage": 93.88, "elapsed_time": "1:49:05", "remaining_time": "0:07:06", "throughput": 3579.01, "total_tokens": 23426584}
|
| 7184 |
+
{"current_steps": 35830, "total_steps": 38160, "loss": 0.469, "lr": 5.661695094790892e-07, "epoch": 18.77882599580713, "percentage": 93.89, "elapsed_time": "1:49:06", "remaining_time": "0:07:05", "throughput": 3579.01, "total_tokens": 23429880}
|
| 7185 |
+
{"current_steps": 35835, "total_steps": 38160, "loss": 0.4246, "lr": 5.637524050521064e-07, "epoch": 18.781446540880502, "percentage": 93.91, "elapsed_time": "1:49:07", "remaining_time": "0:07:04", "throughput": 3578.93, "total_tokens": 23432728}
|
| 7186 |
+
{"current_steps": 35840, "total_steps": 38160, "loss": 0.5554, "lr": 5.613404124093391e-07, "epoch": 18.78406708595388, "percentage": 93.92, "elapsed_time": "1:49:08", "remaining_time": "0:07:03", "throughput": 3578.93, "total_tokens": 23435704}
|
| 7187 |
+
{"current_steps": 35845, "total_steps": 38160, "loss": 0.3991, "lr": 5.589335320553446e-07, "epoch": 18.786687631027252, "percentage": 93.93, "elapsed_time": "1:49:09", "remaining_time": "0:07:02", "throughput": 3578.97, "total_tokens": 23439416}
|
| 7188 |
+
{"current_steps": 35850, "total_steps": 38160, "loss": 0.4752, "lr": 5.565317644936202e-07, "epoch": 18.78930817610063, "percentage": 93.95, "elapsed_time": "1:49:10", "remaining_time": "0:07:02", "throughput": 3578.91, "total_tokens": 23441880}
|
| 7189 |
+
{"current_steps": 35855, "total_steps": 38160, "loss": 0.5058, "lr": 5.541351102265863e-07, "epoch": 18.791928721174003, "percentage": 93.96, "elapsed_time": "1:49:10", "remaining_time": "0:07:01", "throughput": 3579.0, "total_tokens": 23445560}
|
| 7190 |
+
{"current_steps": 35860, "total_steps": 38160, "loss": 0.5323, "lr": 5.51743569755589e-07, "epoch": 18.79454926624738, "percentage": 93.97, "elapsed_time": "1:49:11", "remaining_time": "0:07:00", "throughput": 3579.01, "total_tokens": 23448760}
|
| 7191 |
+
{"current_steps": 35865, "total_steps": 38160, "loss": 0.3166, "lr": 5.493571435809197e-07, "epoch": 18.797169811320753, "percentage": 93.99, "elapsed_time": "1:49:12", "remaining_time": "0:06:59", "throughput": 3579.02, "total_tokens": 23451864}
|
| 7192 |
+
{"current_steps": 35870, "total_steps": 38160, "loss": 0.4283, "lr": 5.469758322017849e-07, "epoch": 18.79979035639413, "percentage": 94.0, "elapsed_time": "1:49:14", "remaining_time": "0:06:58", "throughput": 3579.23, "total_tokens": 23458552}
|
| 7193 |
+
{"current_steps": 35875, "total_steps": 38160, "loss": 0.4125, "lr": 5.445996361163358e-07, "epoch": 18.802410901467507, "percentage": 94.01, "elapsed_time": "1:49:14", "remaining_time": "0:06:57", "throughput": 3579.24, "total_tokens": 23461656}
|
| 7194 |
+
{"current_steps": 35880, "total_steps": 38160, "loss": 0.517, "lr": 5.422285558216389e-07, "epoch": 18.80503144654088, "percentage": 94.03, "elapsed_time": "1:49:15", "remaining_time": "0:06:56", "throughput": 3579.24, "total_tokens": 23464664}
|
| 7195 |
+
{"current_steps": 35885, "total_steps": 38160, "loss": 0.5183, "lr": 5.398625918137001e-07, "epoch": 18.807651991614257, "percentage": 94.04, "elapsed_time": "1:49:16", "remaining_time": "0:06:55", "throughput": 3579.29, "total_tokens": 23468216}
|
| 7196 |
+
{"current_steps": 35890, "total_steps": 38160, "loss": 0.5345, "lr": 5.375017445874486e-07, "epoch": 18.81027253668763, "percentage": 94.05, "elapsed_time": "1:49:17", "remaining_time": "0:06:54", "throughput": 3579.25, "total_tokens": 23471064}
|
| 7197 |
+
{"current_steps": 35895, "total_steps": 38160, "loss": 0.3837, "lr": 5.351460146367504e-07, "epoch": 18.812893081761008, "percentage": 94.06, "elapsed_time": "1:49:18", "remaining_time": "0:06:53", "throughput": 3579.25, "total_tokens": 23474264}
|
| 7198 |
+
{"current_steps": 35900, "total_steps": 38160, "loss": 0.4074, "lr": 5.327954024543946e-07, "epoch": 18.81551362683438, "percentage": 94.08, "elapsed_time": "1:49:19", "remaining_time": "0:06:52", "throughput": 3579.29, "total_tokens": 23477720}
|
| 7199 |
+
{"current_steps": 35905, "total_steps": 38160, "loss": 0.3776, "lr": 5.304499085321074e-07, "epoch": 18.818134171907758, "percentage": 94.09, "elapsed_time": "1:49:20", "remaining_time": "0:06:52", "throughput": 3579.25, "total_tokens": 23480344}
|
| 7200 |
+
{"current_steps": 35910, "total_steps": 38160, "loss": 0.4835, "lr": 5.281095333605352e-07, "epoch": 18.82075471698113, "percentage": 94.1, "elapsed_time": "1:49:20", "remaining_time": "0:06:51", "throughput": 3579.29, "total_tokens": 23483544}
|
| 7201 |
+
{"current_steps": 35915, "total_steps": 38160, "loss": 0.5053, "lr": 5.257742774292556e-07, "epoch": 18.82337526205451, "percentage": 94.12, "elapsed_time": "1:49:21", "remaining_time": "0:06:50", "throughput": 3579.28, "total_tokens": 23486392}
|
| 7202 |
+
{"current_steps": 35920, "total_steps": 38160, "loss": 0.6596, "lr": 5.234441412267837e-07, "epoch": 18.82599580712788, "percentage": 94.13, "elapsed_time": "1:49:22", "remaining_time": "0:06:49", "throughput": 3579.37, "total_tokens": 23490200}
|
| 7203 |
+
{"current_steps": 35925, "total_steps": 38160, "loss": 0.4634, "lr": 5.211191252405517e-07, "epoch": 18.82861635220126, "percentage": 94.14, "elapsed_time": "1:49:23", "remaining_time": "0:06:48", "throughput": 3579.35, "total_tokens": 23493048}
|
| 7204 |
+
{"current_steps": 35930, "total_steps": 38160, "loss": 0.6183, "lr": 5.187992299569316e-07, "epoch": 18.831236897274632, "percentage": 94.16, "elapsed_time": "1:49:24", "remaining_time": "0:06:47", "throughput": 3579.43, "total_tokens": 23496440}
|
| 7205 |
+
{"current_steps": 35935, "total_steps": 38160, "loss": 0.4305, "lr": 5.164844558612131e-07, "epoch": 18.83385744234801, "percentage": 94.17, "elapsed_time": "1:49:25", "remaining_time": "0:06:46", "throughput": 3579.47, "total_tokens": 23499832}
|
| 7206 |
+
{"current_steps": 35940, "total_steps": 38160, "loss": 0.5607, "lr": 5.141748034376254e-07, "epoch": 18.836477987421382, "percentage": 94.18, "elapsed_time": "1:49:26", "remaining_time": "0:06:45", "throughput": 3579.53, "total_tokens": 23503416}
|
| 7207 |
+
{"current_steps": 35945, "total_steps": 38160, "loss": 0.377, "lr": 5.118702731693209e-07, "epoch": 18.83909853249476, "percentage": 94.2, "elapsed_time": "1:49:26", "remaining_time": "0:06:44", "throughput": 3579.53, "total_tokens": 23506616}
|
| 7208 |
+
{"current_steps": 35950, "total_steps": 38160, "loss": 0.5968, "lr": 5.095708655383751e-07, "epoch": 18.841719077568133, "percentage": 94.21, "elapsed_time": "1:49:27", "remaining_time": "0:06:43", "throughput": 3579.55, "total_tokens": 23509912}
|
| 7209 |
+
{"current_steps": 35955, "total_steps": 38160, "loss": 0.4354, "lr": 5.07276581025809e-07, "epoch": 18.84433962264151, "percentage": 94.22, "elapsed_time": "1:49:28", "remaining_time": "0:06:42", "throughput": 3579.62, "total_tokens": 23513272}
|
| 7210 |
+
{"current_steps": 35960, "total_steps": 38160, "loss": 0.4642, "lr": 5.049874201115495e-07, "epoch": 18.846960167714883, "percentage": 94.23, "elapsed_time": "1:49:29", "remaining_time": "0:06:41", "throughput": 3579.59, "total_tokens": 23515992}
|
| 7211 |
+
{"current_steps": 35965, "total_steps": 38160, "loss": 0.4395, "lr": 5.027033832744693e-07, "epoch": 18.84958071278826, "percentage": 94.25, "elapsed_time": "1:49:30", "remaining_time": "0:06:40", "throughput": 3579.6, "total_tokens": 23519032}
|
| 7212 |
+
{"current_steps": 35970, "total_steps": 38160, "loss": 0.4222, "lr": 5.004244709923639e-07, "epoch": 18.852201257861637, "percentage": 94.26, "elapsed_time": "1:49:31", "remaining_time": "0:06:40", "throughput": 3579.63, "total_tokens": 23522392}
|
| 7213 |
+
{"current_steps": 35975, "total_steps": 38160, "loss": 0.3732, "lr": 4.981506837419519e-07, "epoch": 18.85482180293501, "percentage": 94.27, "elapsed_time": "1:49:31", "remaining_time": "0:06:39", "throughput": 3579.63, "total_tokens": 23525240}
|
| 7214 |
+
{"current_steps": 35980, "total_steps": 38160, "loss": 0.537, "lr": 4.958820219988836e-07, "epoch": 18.857442348008387, "percentage": 94.29, "elapsed_time": "1:49:32", "remaining_time": "0:06:38", "throughput": 3579.64, "total_tokens": 23528568}
|
| 7215 |
+
{"current_steps": 35985, "total_steps": 38160, "loss": 0.4513, "lr": 4.936184862377402e-07, "epoch": 18.86006289308176, "percentage": 94.3, "elapsed_time": "1:49:33", "remaining_time": "0:06:37", "throughput": 3579.61, "total_tokens": 23531288}
|
| 7216 |
+
{"current_steps": 35990, "total_steps": 38160, "loss": 0.4601, "lr": 4.913600769320237e-07, "epoch": 18.862683438155138, "percentage": 94.31, "elapsed_time": "1:49:34", "remaining_time": "0:06:36", "throughput": 3579.66, "total_tokens": 23534520}
|
| 7217 |
+
{"current_steps": 35995, "total_steps": 38160, "loss": 0.537, "lr": 4.891067945541728e-07, "epoch": 18.86530398322851, "percentage": 94.33, "elapsed_time": "1:49:35", "remaining_time": "0:06:35", "throughput": 3579.73, "total_tokens": 23537880}
|
| 7218 |
+
{"current_steps": 36000, "total_steps": 38160, "loss": 0.4532, "lr": 4.868586395755437e-07, "epoch": 18.867924528301888, "percentage": 94.34, "elapsed_time": "1:49:36", "remaining_time": "0:06:34", "throughput": 3579.75, "total_tokens": 23541464}
|
| 7219 |
+
{"current_steps": 36005, "total_steps": 38160, "loss": 0.3149, "lr": 4.846156124664242e-07, "epoch": 18.87054507337526, "percentage": 94.35, "elapsed_time": "1:49:37", "remaining_time": "0:06:33", "throughput": 3579.76, "total_tokens": 23544760}
|
| 7220 |
+
{"current_steps": 36010, "total_steps": 38160, "loss": 0.4612, "lr": 4.823777136960362e-07, "epoch": 18.87316561844864, "percentage": 94.37, "elapsed_time": "1:49:38", "remaining_time": "0:06:32", "throughput": 3579.77, "total_tokens": 23547832}
|
| 7221 |
+
{"current_steps": 36015, "total_steps": 38160, "loss": 0.3964, "lr": 4.801449437325162e-07, "epoch": 18.87578616352201, "percentage": 94.38, "elapsed_time": "1:49:38", "remaining_time": "0:06:31", "throughput": 3579.72, "total_tokens": 23550968}
|
| 7222 |
+
{"current_steps": 36020, "total_steps": 38160, "loss": 0.3968, "lr": 4.779173030429379e-07, "epoch": 18.87840670859539, "percentage": 94.39, "elapsed_time": "1:49:39", "remaining_time": "0:06:30", "throughput": 3579.81, "total_tokens": 23554680}
|
| 7223 |
+
{"current_steps": 36025, "total_steps": 38160, "loss": 0.452, "lr": 4.7569479209329804e-07, "epoch": 18.881027253668762, "percentage": 94.41, "elapsed_time": "1:49:40", "remaining_time": "0:06:30", "throughput": 3579.89, "total_tokens": 23558168}
|
| 7224 |
+
{"current_steps": 36030, "total_steps": 38160, "loss": 0.4628, "lr": 4.734774113485163e-07, "epoch": 18.88364779874214, "percentage": 94.42, "elapsed_time": "1:49:41", "remaining_time": "0:06:29", "throughput": 3579.85, "total_tokens": 23560952}
|
| 7225 |
+
{"current_steps": 36035, "total_steps": 38160, "loss": 0.431, "lr": 4.7126516127244945e-07, "epoch": 18.886268343815512, "percentage": 94.43, "elapsed_time": "1:49:42", "remaining_time": "0:06:28", "throughput": 3579.74, "total_tokens": 23563096}
|
| 7226 |
+
{"current_steps": 36040, "total_steps": 38160, "loss": 0.578, "lr": 4.690580423278718e-07, "epoch": 18.88888888888889, "percentage": 94.44, "elapsed_time": "1:49:43", "remaining_time": "0:06:27", "throughput": 3579.66, "total_tokens": 23565400}
|
| 7227 |
+
{"current_steps": 36045, "total_steps": 38160, "loss": 0.4342, "lr": 4.668560549764861e-07, "epoch": 18.891509433962263, "percentage": 94.46, "elapsed_time": "1:49:44", "remaining_time": "0:06:26", "throughput": 3579.73, "total_tokens": 23569016}
|
| 7228 |
+
{"current_steps": 36050, "total_steps": 38160, "loss": 0.545, "lr": 4.646591996789268e-07, "epoch": 18.89412997903564, "percentage": 94.47, "elapsed_time": "1:49:44", "remaining_time": "0:06:25", "throughput": 3579.75, "total_tokens": 23572216}
|
| 7229 |
+
{"current_steps": 36055, "total_steps": 38160, "loss": 0.5421, "lr": 4.6246747689474847e-07, "epoch": 18.896750524109013, "percentage": 94.48, "elapsed_time": "1:49:45", "remaining_time": "0:06:24", "throughput": 3579.83, "total_tokens": 23576056}
|
| 7230 |
+
{"current_steps": 36060, "total_steps": 38160, "loss": 0.607, "lr": 4.6028088708243434e-07, "epoch": 18.89937106918239, "percentage": 94.5, "elapsed_time": "1:49:46", "remaining_time": "0:06:23", "throughput": 3579.84, "total_tokens": 23579096}
|
| 7231 |
+
{"current_steps": 36065, "total_steps": 38160, "loss": 0.4508, "lr": 4.580994306993991e-07, "epoch": 18.901991614255767, "percentage": 94.51, "elapsed_time": "1:49:47", "remaining_time": "0:06:22", "throughput": 3579.8, "total_tokens": 23581720}
|
| 7232 |
+
{"current_steps": 36070, "total_steps": 38160, "loss": 0.7108, "lr": 4.5592310820196936e-07, "epoch": 18.90461215932914, "percentage": 94.52, "elapsed_time": "1:49:48", "remaining_time": "0:06:21", "throughput": 3579.82, "total_tokens": 23584824}
|
| 7233 |
+
{"current_steps": 36075, "total_steps": 38160, "loss": 0.4651, "lr": 4.537519200454116e-07, "epoch": 18.907232704402517, "percentage": 94.54, "elapsed_time": "1:49:49", "remaining_time": "0:06:20", "throughput": 3579.8, "total_tokens": 23587800}
|
| 7234 |
+
{"current_steps": 36080, "total_steps": 38160, "loss": 0.6023, "lr": 4.515858666839151e-07, "epoch": 18.90985324947589, "percentage": 94.55, "elapsed_time": "1:49:49", "remaining_time": "0:06:19", "throughput": 3579.79, "total_tokens": 23590584}
|
| 7235 |
+
{"current_steps": 36085, "total_steps": 38160, "loss": 0.644, "lr": 4.494249485705926e-07, "epoch": 18.912473794549268, "percentage": 94.56, "elapsed_time": "1:49:51", "remaining_time": "0:06:19", "throughput": 3579.78, "total_tokens": 23594392}
|
| 7236 |
+
{"current_steps": 36090, "total_steps": 38160, "loss": 0.4494, "lr": 4.472691661574824e-07, "epoch": 18.91509433962264, "percentage": 94.58, "elapsed_time": "1:49:51", "remaining_time": "0:06:18", "throughput": 3579.76, "total_tokens": 23597176}
|
| 7237 |
+
{"current_steps": 36095, "total_steps": 38160, "loss": 0.4742, "lr": 4.4511851989555156e-07, "epoch": 18.917714884696018, "percentage": 94.59, "elapsed_time": "1:49:52", "remaining_time": "0:06:17", "throughput": 3579.81, "total_tokens": 23600600}
|
| 7238 |
+
{"current_steps": 36100, "total_steps": 38160, "loss": 0.5889, "lr": 4.429730102346874e-07, "epoch": 18.92033542976939, "percentage": 94.6, "elapsed_time": "1:49:53", "remaining_time": "0:06:16", "throughput": 3579.8, "total_tokens": 23603480}
|
| 7239 |
+
{"current_steps": 36105, "total_steps": 38160, "loss": 0.3745, "lr": 4.4083263762370873e-07, "epoch": 18.92295597484277, "percentage": 94.61, "elapsed_time": "1:49:54", "remaining_time": "0:06:15", "throughput": 3579.68, "total_tokens": 23605784}
|
| 7240 |
+
{"current_steps": 36110, "total_steps": 38160, "loss": 0.4637, "lr": 4.386974025103574e-07, "epoch": 18.92557651991614, "percentage": 94.63, "elapsed_time": "1:49:55", "remaining_time": "0:06:14", "throughput": 3579.72, "total_tokens": 23609144}
|
| 7241 |
+
{"current_steps": 36115, "total_steps": 38160, "loss": 0.5504, "lr": 4.365673053413011e-07, "epoch": 18.92819706498952, "percentage": 94.64, "elapsed_time": "1:49:56", "remaining_time": "0:06:13", "throughput": 3579.68, "total_tokens": 23611960}
|
| 7242 |
+
{"current_steps": 36120, "total_steps": 38160, "loss": 0.4779, "lr": 4.34442346562125e-07, "epoch": 18.930817610062892, "percentage": 94.65, "elapsed_time": "1:49:56", "remaining_time": "0:06:12", "throughput": 3579.65, "total_tokens": 23614680}
|
| 7243 |
+
{"current_steps": 36125, "total_steps": 38160, "loss": 0.462, "lr": 4.323225266173542e-07, "epoch": 18.93343815513627, "percentage": 94.67, "elapsed_time": "1:49:57", "remaining_time": "0:06:11", "throughput": 3579.64, "total_tokens": 23617592}
|
| 7244 |
+
{"current_steps": 36130, "total_steps": 38160, "loss": 0.4644, "lr": 4.302078459504283e-07, "epoch": 18.936058700209642, "percentage": 94.68, "elapsed_time": "1:49:58", "remaining_time": "0:06:10", "throughput": 3579.6, "total_tokens": 23620440}
|
| 7245 |
+
{"current_steps": 36135, "total_steps": 38160, "loss": 0.36, "lr": 4.2809830500371294e-07, "epoch": 18.93867924528302, "percentage": 94.69, "elapsed_time": "1:49:59", "remaining_time": "0:06:09", "throughput": 3579.59, "total_tokens": 23623320}
|
| 7246 |
+
{"current_steps": 36140, "total_steps": 38160, "loss": 0.3725, "lr": 4.2599390421850236e-07, "epoch": 18.941299790356393, "percentage": 94.71, "elapsed_time": "1:50:00", "remaining_time": "0:06:08", "throughput": 3579.51, "total_tokens": 23626168}
|
| 7247 |
+
{"current_steps": 36145, "total_steps": 38160, "loss": 0.5861, "lr": 4.2389464403501113e-07, "epoch": 18.94392033542977, "percentage": 94.72, "elapsed_time": "1:50:01", "remaining_time": "0:06:08", "throughput": 3579.5, "total_tokens": 23629240}
|
| 7248 |
+
{"current_steps": 36150, "total_steps": 38160, "loss": 0.4324, "lr": 4.218005248923823e-07, "epoch": 18.946540880503143, "percentage": 94.73, "elapsed_time": "1:50:02", "remaining_time": "0:06:07", "throughput": 3579.51, "total_tokens": 23632472}
|
| 7249 |
+
{"current_steps": 36155, "total_steps": 38160, "loss": 0.5251, "lr": 4.1971154722867946e-07, "epoch": 18.94916142557652, "percentage": 94.75, "elapsed_time": "1:50:03", "remaining_time": "0:06:06", "throughput": 3579.54, "total_tokens": 23635864}
|
| 7250 |
+
{"current_steps": 36160, "total_steps": 38160, "loss": 0.44, "lr": 4.176277114808946e-07, "epoch": 18.951781970649897, "percentage": 94.76, "elapsed_time": "1:50:03", "remaining_time": "0:06:05", "throughput": 3579.53, "total_tokens": 23638712}
|
| 7251 |
+
{"current_steps": 36165, "total_steps": 38160, "loss": 0.4706, "lr": 4.155490180849431e-07, "epoch": 18.95440251572327, "percentage": 94.77, "elapsed_time": "1:50:04", "remaining_time": "0:06:04", "throughput": 3579.51, "total_tokens": 23641592}
|
| 7252 |
+
{"current_steps": 36170, "total_steps": 38160, "loss": 0.4337, "lr": 4.1347546747566304e-07, "epoch": 18.957023060796647, "percentage": 94.79, "elapsed_time": "1:50:05", "remaining_time": "0:06:03", "throughput": 3579.58, "total_tokens": 23645912}
|
| 7253 |
+
{"current_steps": 36175, "total_steps": 38160, "loss": 0.4615, "lr": 4.114070600868131e-07, "epoch": 18.95964360587002, "percentage": 94.8, "elapsed_time": "1:50:06", "remaining_time": "0:06:02", "throughput": 3579.56, "total_tokens": 23648824}
|
| 7254 |
+
{"current_steps": 36180, "total_steps": 38160, "loss": 0.4698, "lr": 4.093437963510888e-07, "epoch": 18.962264150943398, "percentage": 94.81, "elapsed_time": "1:50:07", "remaining_time": "0:06:01", "throughput": 3579.45, "total_tokens": 23651096}
|
| 7255 |
+
{"current_steps": 36185, "total_steps": 38160, "loss": 0.4655, "lr": 4.072856767000949e-07, "epoch": 18.96488469601677, "percentage": 94.82, "elapsed_time": "1:50:08", "remaining_time": "0:06:00", "throughput": 3579.48, "total_tokens": 23654616}
|
| 7256 |
+
{"current_steps": 36190, "total_steps": 38160, "loss": 0.5283, "lr": 4.052327015643703e-07, "epoch": 18.967505241090148, "percentage": 94.84, "elapsed_time": "1:50:09", "remaining_time": "0:05:59", "throughput": 3579.51, "total_tokens": 23658200}
|
| 7257 |
+
{"current_steps": 36195, "total_steps": 38160, "loss": 0.5089, "lr": 4.031848713733744e-07, "epoch": 18.97012578616352, "percentage": 94.85, "elapsed_time": "1:50:10", "remaining_time": "0:05:58", "throughput": 3579.47, "total_tokens": 23660856}
|
| 7258 |
+
{"current_steps": 36200, "total_steps": 38160, "loss": 0.4746, "lr": 4.011421865554837e-07, "epoch": 18.9727463312369, "percentage": 94.86, "elapsed_time": "1:50:10", "remaining_time": "0:05:57", "throughput": 3579.51, "total_tokens": 23664056}
|
| 7259 |
+
{"current_steps": 36205, "total_steps": 38160, "loss": 0.5262, "lr": 3.9910464753801224e-07, "epoch": 18.97536687631027, "percentage": 94.88, "elapsed_time": "1:50:11", "remaining_time": "0:05:57", "throughput": 3579.55, "total_tokens": 23667256}
|
| 7260 |
+
{"current_steps": 36210, "total_steps": 38160, "loss": 0.5139, "lr": 3.9707225474718557e-07, "epoch": 18.97798742138365, "percentage": 94.89, "elapsed_time": "1:50:12", "remaining_time": "0:05:56", "throughput": 3579.57, "total_tokens": 23670456}
|
| 7261 |
+
{"current_steps": 36215, "total_steps": 38160, "loss": 0.4958, "lr": 3.950450086081553e-07, "epoch": 18.980607966457022, "percentage": 94.9, "elapsed_time": "1:50:13", "remaining_time": "0:05:55", "throughput": 3579.58, "total_tokens": 23673656}
|
| 7262 |
+
{"current_steps": 36220, "total_steps": 38160, "loss": 0.5408, "lr": 3.930229095450072e-07, "epoch": 18.9832285115304, "percentage": 94.92, "elapsed_time": "1:50:14", "remaining_time": "0:05:54", "throughput": 3579.58, "total_tokens": 23676824}
|
| 7263 |
+
{"current_steps": 36225, "total_steps": 38160, "loss": 0.7257, "lr": 3.9100595798073345e-07, "epoch": 18.985849056603772, "percentage": 94.93, "elapsed_time": "1:50:15", "remaining_time": "0:05:53", "throughput": 3579.53, "total_tokens": 23679832}
|
| 7264 |
+
{"current_steps": 36230, "total_steps": 38160, "loss": 0.4604, "lr": 3.8899415433725493e-07, "epoch": 18.98846960167715, "percentage": 94.94, "elapsed_time": "1:50:16", "remaining_time": "0:05:52", "throughput": 3579.53, "total_tokens": 23682808}
|
| 7265 |
+
{"current_steps": 36235, "total_steps": 38160, "loss": 0.584, "lr": 3.8698749903542666e-07, "epoch": 18.991090146750523, "percentage": 94.96, "elapsed_time": "1:50:17", "remaining_time": "0:05:51", "throughput": 3579.56, "total_tokens": 23685976}
|
| 7266 |
+
{"current_steps": 36240, "total_steps": 38160, "loss": 0.5389, "lr": 3.8498599249501e-07, "epoch": 18.9937106918239, "percentage": 94.97, "elapsed_time": "1:50:17", "remaining_time": "0:05:50", "throughput": 3579.55, "total_tokens": 23688952}
|
| 7267 |
+
{"current_steps": 36245, "total_steps": 38160, "loss": 0.4875, "lr": 3.8298963513470345e-07, "epoch": 18.996331236897273, "percentage": 94.98, "elapsed_time": "1:50:18", "remaining_time": "0:05:49", "throughput": 3579.53, "total_tokens": 23691832}
|
| 7268 |
+
{"current_steps": 36250, "total_steps": 38160, "loss": 0.4151, "lr": 3.8099842737211734e-07, "epoch": 18.99895178197065, "percentage": 94.99, "elapsed_time": "1:50:19", "remaining_time": "0:05:48", "throughput": 3579.61, "total_tokens": 23695544}
|
| 7269 |
+
{"current_steps": 36252, "total_steps": 38160, "eval_loss": 0.4916197657585144, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "1:50:30", "remaining_time": "0:05:48", "throughput": 3573.98, "total_tokens": 23696296}
|
| 7270 |
+
{"current_steps": 36255, "total_steps": 38160, "loss": 0.5434, "lr": 3.7901236962379627e-07, "epoch": 19.001572327044027, "percentage": 95.01, "elapsed_time": "1:50:32", "remaining_time": "0:05:48", "throughput": 3572.93, "total_tokens": 23697768}
|
| 7271 |
+
{"current_steps": 36260, "total_steps": 38160, "loss": 0.4666, "lr": 3.7703146230519126e-07, "epoch": 19.0041928721174, "percentage": 95.02, "elapsed_time": "1:50:33", "remaining_time": "0:05:47", "throughput": 3572.79, "total_tokens": 23700072}
|
| 7272 |
+
{"current_steps": 36265, "total_steps": 38160, "loss": 0.5916, "lr": 3.7505570583069306e-07, "epoch": 19.006813417190777, "percentage": 95.03, "elapsed_time": "1:50:34", "remaining_time": "0:05:46", "throughput": 3572.74, "total_tokens": 23702856}
|