Training in progress, step 100818
Browse files- model.safetensors +1 -1
- trainer_log.jsonl +76 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1260367448
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:225c63b0dc9cb3604ef105952ca0ee21dbe6b5b3f799adc14d6f72632097fd9d
|
3 |
size 1260367448
|
trainer_log.jsonl
CHANGED
@@ -10008,3 +10008,79 @@
|
|
10008 |
{"current_steps": 100040, "total_steps": 100818, "loss": 0.0012, "lr": 1.8139003621547857e-09, "epoch": 2.9768050823501406, "percentage": 99.23, "elapsed_time": "21:09:31", "remaining_time": "0:09:52"}
|
10009 |
{"current_steps": 100050, "total_steps": 100818, "loss": 0.0012, "lr": 1.7675729402866216e-09, "epoch": 2.977102643833782, "percentage": 99.24, "elapsed_time": "21:09:39", "remaining_time": "0:09:44"}
|
10010 |
{"current_steps": 100060, "total_steps": 100818, "loss": 0.0013, "lr": 1.7218446978939373e-09, "epoch": 2.9774002053174238, "percentage": 99.25, "elapsed_time": "21:09:47", "remaining_time": "0:09:37"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10008 |
{"current_steps": 100040, "total_steps": 100818, "loss": 0.0012, "lr": 1.8139003621547857e-09, "epoch": 2.9768050823501406, "percentage": 99.23, "elapsed_time": "21:09:31", "remaining_time": "0:09:52"}
|
10009 |
{"current_steps": 100050, "total_steps": 100818, "loss": 0.0012, "lr": 1.7675729402866216e-09, "epoch": 2.977102643833782, "percentage": 99.24, "elapsed_time": "21:09:39", "remaining_time": "0:09:44"}
|
10010 |
{"current_steps": 100060, "total_steps": 100818, "loss": 0.0013, "lr": 1.7218446978939373e-09, "epoch": 2.9774002053174238, "percentage": 99.25, "elapsed_time": "21:09:47", "remaining_time": "0:09:37"}
|
10011 |
+
{"current_steps": 100070, "total_steps": 100818, "loss": 0.0019, "lr": 1.6767156404595698e-09, "epoch": 2.9776977668010653, "percentage": 99.26, "elapsed_time": "21:09:56", "remaining_time": "0:09:29"}
|
10012 |
+
{"current_steps": 100080, "total_steps": 100818, "loss": 0.0025, "lr": 1.63218577339308e-09, "epoch": 2.977995328284707, "percentage": 99.27, "elapsed_time": "21:10:04", "remaining_time": "0:09:21"}
|
10013 |
+
{"current_steps": 100090, "total_steps": 100818, "loss": 0.0022, "lr": 1.5882551020329762e-09, "epoch": 2.9782928897683485, "percentage": 99.28, "elapsed_time": "21:10:10", "remaining_time": "0:09:14"}
|
10014 |
+
{"current_steps": 100100, "total_steps": 100818, "loss": 0.0017, "lr": 1.5449236316450456e-09, "epoch": 2.97859045125199, "percentage": 99.29, "elapsed_time": "21:10:17", "remaining_time": "0:09:06"}
|
10015 |
+
{"current_steps": 100110, "total_steps": 100818, "loss": 0.001, "lr": 1.502191367424022e-09, "epoch": 2.9788880127356316, "percentage": 99.3, "elapsed_time": "21:10:26", "remaining_time": "0:08:59"}
|
10016 |
+
{"current_steps": 100120, "total_steps": 100818, "loss": 0.0017, "lr": 1.4600583144930291e-09, "epoch": 2.979185574219273, "percentage": 99.31, "elapsed_time": "21:10:33", "remaining_time": "0:08:51"}
|
10017 |
+
{"current_steps": 100130, "total_steps": 100818, "loss": 0.0025, "lr": 1.4185244779019168e-09, "epoch": 2.979483135702915, "percentage": 99.32, "elapsed_time": "21:10:42", "remaining_time": "0:08:43"}
|
10018 |
+
{"current_steps": 100140, "total_steps": 100818, "loss": 0.0049, "lr": 1.3775898626305907e-09, "epoch": 2.9797806971865564, "percentage": 99.33, "elapsed_time": "21:10:49", "remaining_time": "0:08:36"}
|
10019 |
+
{"current_steps": 100150, "total_steps": 100818, "loss": 0.0029, "lr": 1.3372544735856807e-09, "epoch": 2.980078258670198, "percentage": 99.34, "elapsed_time": "21:10:58", "remaining_time": "0:08:28"}
|
10020 |
+
{"current_steps": 100160, "total_steps": 100818, "loss": 0.0016, "lr": 1.2975183156027637e-09, "epoch": 2.9803758201538395, "percentage": 99.35, "elapsed_time": "21:11:07", "remaining_time": "0:08:21"}
|
10021 |
+
{"current_steps": 100170, "total_steps": 100818, "loss": 0.0009, "lr": 1.2583813934452517e-09, "epoch": 2.980673381637481, "percentage": 99.36, "elapsed_time": "21:11:16", "remaining_time": "0:08:13"}
|
10022 |
+
{"current_steps": 100180, "total_steps": 100818, "loss": 0.0017, "lr": 1.2198437118049467e-09, "epoch": 2.9809709431211227, "percentage": 99.37, "elapsed_time": "21:11:24", "remaining_time": "0:08:05"}
|
10023 |
+
{"current_steps": 100190, "total_steps": 100818, "loss": 0.0044, "lr": 1.1819052753014871e-09, "epoch": 2.9812685046047642, "percentage": 99.38, "elapsed_time": "21:11:30", "remaining_time": "0:07:58"}
|
10024 |
+
{"current_steps": 100200, "total_steps": 100818, "loss": 0.0015, "lr": 1.1445660884834564e-09, "epoch": 2.9815660660884054, "percentage": 99.39, "elapsed_time": "21:11:39", "remaining_time": "0:07:50"}
|
10025 |
+
{"current_steps": 100210, "total_steps": 100818, "loss": 0.0014, "lr": 1.1078261558261638e-09, "epoch": 2.981863627572047, "percentage": 99.4, "elapsed_time": "21:11:47", "remaining_time": "0:07:42"}
|
10026 |
+
{"current_steps": 100220, "total_steps": 100818, "loss": 0.0015, "lr": 1.071685481734419e-09, "epoch": 2.9821611890556885, "percentage": 99.41, "elapsed_time": "21:11:55", "remaining_time": "0:07:35"}
|
10027 |
+
{"current_steps": 100230, "total_steps": 100818, "loss": 0.0015, "lr": 1.0361440705403126e-09, "epoch": 2.98245875053933, "percentage": 99.42, "elapsed_time": "21:12:03", "remaining_time": "0:07:27"}
|
10028 |
+
{"current_steps": 100240, "total_steps": 100818, "loss": 0.0013, "lr": 1.00120192650488e-09, "epoch": 2.9827563120229716, "percentage": 99.43, "elapsed_time": "21:12:11", "remaining_time": "0:07:20"}
|
10029 |
+
{"current_steps": 100250, "total_steps": 100818, "loss": 0.0013, "lr": 9.668590538169931e-10, "epoch": 2.983053873506613, "percentage": 99.44, "elapsed_time": "21:12:19", "remaining_time": "0:07:12"}
|
10030 |
+
{"current_steps": 100260, "total_steps": 100818, "loss": 0.0021, "lr": 9.331154565933586e-10, "epoch": 2.983351434990255, "percentage": 99.45, "elapsed_time": "21:12:27", "remaining_time": "0:07:04"}
|
10031 |
+
{"current_steps": 100270, "total_steps": 100818, "loss": 0.0015, "lr": 8.999711388790744e-10, "epoch": 2.9836489964738964, "percentage": 99.46, "elapsed_time": "21:12:36", "remaining_time": "0:06:57"}
|
10032 |
+
{"current_steps": 100280, "total_steps": 100818, "loss": 0.002, "lr": 8.674261046470734e-10, "epoch": 2.983946557957538, "percentage": 99.47, "elapsed_time": "21:12:43", "remaining_time": "0:06:49"}
|
10033 |
+
{"current_steps": 100290, "total_steps": 100818, "loss": 0.0016, "lr": 8.354803577997895e-10, "epoch": 2.9842441194411795, "percentage": 99.48, "elapsed_time": "21:12:50", "remaining_time": "0:06:42"}
|
10034 |
+
{"current_steps": 100300, "total_steps": 100818, "loss": 0.0009, "lr": 8.041339021663819e-10, "epoch": 2.984541680924821, "percentage": 99.49, "elapsed_time": "21:12:57", "remaining_time": "0:06:34"}
|
10035 |
+
{"current_steps": 100310, "total_steps": 100818, "loss": 0.0017, "lr": 7.733867415044005e-10, "epoch": 2.9848392424084627, "percentage": 99.5, "elapsed_time": "21:13:05", "remaining_time": "0:06:26"}
|
10036 |
+
{"current_steps": 100320, "total_steps": 100818, "loss": 0.0023, "lr": 7.432388794997858e-10, "epoch": 2.9851368038921042, "percentage": 99.51, "elapsed_time": "21:13:12", "remaining_time": "0:06:19"}
|
10037 |
+
{"current_steps": 100330, "total_steps": 100818, "loss": 0.0024, "lr": 7.136903197663136e-10, "epoch": 2.985434365375746, "percentage": 99.52, "elapsed_time": "21:13:20", "remaining_time": "0:06:11"}
|
10038 |
+
{"current_steps": 100340, "total_steps": 100818, "loss": 0.0023, "lr": 6.847410658472609e-10, "epoch": 2.9857319268593874, "percentage": 99.53, "elapsed_time": "21:13:27", "remaining_time": "0:06:03"}
|
10039 |
+
{"current_steps": 100350, "total_steps": 100818, "loss": 0.0013, "lr": 6.563911212120743e-10, "epoch": 2.986029488343029, "percentage": 99.54, "elapsed_time": "21:13:35", "remaining_time": "0:05:56"}
|
10040 |
+
{"current_steps": 100360, "total_steps": 100818, "loss": 0.0018, "lr": 6.286404892591469e-10, "epoch": 2.9863270498266705, "percentage": 99.55, "elapsed_time": "21:13:42", "remaining_time": "0:05:48"}
|
10041 |
+
{"current_steps": 100370, "total_steps": 100818, "loss": 0.0016, "lr": 6.014891733163719e-10, "epoch": 2.986624611310312, "percentage": 99.56, "elapsed_time": "21:13:48", "remaining_time": "0:05:41"}
|
10042 |
+
{"current_steps": 100380, "total_steps": 100818, "loss": 0.0016, "lr": 5.74937176637258e-10, "epoch": 2.9869221727939537, "percentage": 99.57, "elapsed_time": "21:13:56", "remaining_time": "0:05:33"}
|
10043 |
+
{"current_steps": 100390, "total_steps": 100818, "loss": 0.0017, "lr": 5.489845024053698e-10, "epoch": 2.9872197342775952, "percentage": 99.58, "elapsed_time": "21:14:04", "remaining_time": "0:05:25"}
|
10044 |
+
{"current_steps": 100400, "total_steps": 100818, "loss": 0.0022, "lr": 5.23631153732107e-10, "epoch": 2.987517295761237, "percentage": 99.59, "elapsed_time": "21:14:12", "remaining_time": "0:05:18"}
|
10045 |
+
{"current_steps": 100410, "total_steps": 100818, "loss": 0.0013, "lr": 4.988771336567055e-10, "epoch": 2.9878148572448784, "percentage": 99.6, "elapsed_time": "21:14:20", "remaining_time": "0:05:10"}
|
10046 |
+
{"current_steps": 100420, "total_steps": 100818, "loss": 0.0029, "lr": 4.747224451462363e-10, "epoch": 2.9881124187285195, "percentage": 99.61, "elapsed_time": "21:14:29", "remaining_time": "0:05:03"}
|
10047 |
+
{"current_steps": 100430, "total_steps": 100818, "loss": 0.0013, "lr": 4.511670910967159e-10, "epoch": 2.988409980212161, "percentage": 99.62, "elapsed_time": "21:14:36", "remaining_time": "0:04:55"}
|
10048 |
+
{"current_steps": 100440, "total_steps": 100818, "loss": 0.0008, "lr": 4.282110743314416e-10, "epoch": 2.9887075416958027, "percentage": 99.63, "elapsed_time": "21:14:45", "remaining_time": "0:04:47"}
|
10049 |
+
{"current_steps": 100450, "total_steps": 100818, "loss": 0.0025, "lr": 4.0585439760321146e-10, "epoch": 2.9890051031794442, "percentage": 99.63, "elapsed_time": "21:14:52", "remaining_time": "0:04:40"}
|
10050 |
+
{"current_steps": 100460, "total_steps": 100818, "loss": 0.002, "lr": 3.840970635909935e-10, "epoch": 2.989302664663086, "percentage": 99.64, "elapsed_time": "21:14:59", "remaining_time": "0:04:32"}
|
10051 |
+
{"current_steps": 100470, "total_steps": 100818, "loss": 0.0017, "lr": 3.62939074903812e-10, "epoch": 2.9896002261467274, "percentage": 99.65, "elapsed_time": "21:15:07", "remaining_time": "0:04:24"}
|
10052 |
+
{"current_steps": 100480, "total_steps": 100818, "loss": 0.0008, "lr": 3.423804340779713e-10, "epoch": 2.989897787630369, "percentage": 99.66, "elapsed_time": "21:15:15", "remaining_time": "0:04:17"}
|
10053 |
+
{"current_steps": 100490, "total_steps": 100818, "loss": 0.0009, "lr": 3.224211435781666e-10, "epoch": 2.9901953491140105, "percentage": 99.67, "elapsed_time": "21:15:21", "remaining_time": "0:04:09"}
|
10054 |
+
{"current_steps": 100500, "total_steps": 100818, "loss": 0.0014, "lr": 3.0306120579637333e-10, "epoch": 2.990492910597652, "percentage": 99.68, "elapsed_time": "21:15:29", "remaining_time": "0:04:02"}
|
10055 |
+
{"current_steps": 100510, "total_steps": 100818, "loss": 0.0019, "lr": 2.843006230535128e-10, "epoch": 2.9907904720812937, "percentage": 99.69, "elapsed_time": "21:15:36", "remaining_time": "0:03:54"}
|
10056 |
+
{"current_steps": 100520, "total_steps": 100818, "loss": 0.0038, "lr": 2.6613939759945195e-10, "epoch": 2.9910880335649352, "percentage": 99.7, "elapsed_time": "21:15:44", "remaining_time": "0:03:46"}
|
10057 |
+
{"current_steps": 100530, "total_steps": 100818, "loss": 0.0017, "lr": 2.48577531610783e-10, "epoch": 2.991385595048577, "percentage": 99.71, "elapsed_time": "21:15:52", "remaining_time": "0:03:39"}
|
10058 |
+
{"current_steps": 100540, "total_steps": 100818, "loss": 0.0015, "lr": 2.3161502719248886e-10, "epoch": 2.9916831565322184, "percentage": 99.72, "elapsed_time": "21:16:00", "remaining_time": "0:03:31"}
|
10059 |
+
{"current_steps": 100550, "total_steps": 100818, "loss": 0.001, "lr": 2.1525188637849804e-10, "epoch": 2.99198071801586, "percentage": 99.73, "elapsed_time": "21:16:09", "remaining_time": "0:03:24"}
|
10060 |
+
{"current_steps": 100560, "total_steps": 100818, "loss": 0.0009, "lr": 1.9948811113001953e-10, "epoch": 2.9922782794995015, "percentage": 99.74, "elapsed_time": "21:16:18", "remaining_time": "0:03:16"}
|
10061 |
+
{"current_steps": 100570, "total_steps": 100818, "loss": 0.0017, "lr": 1.8432370333720805e-10, "epoch": 2.992575840983143, "percentage": 99.75, "elapsed_time": "21:16:25", "remaining_time": "0:03:08"}
|
10062 |
+
{"current_steps": 100580, "total_steps": 100818, "loss": 0.0012, "lr": 1.697586648174987e-10, "epoch": 2.9928734024667847, "percentage": 99.76, "elapsed_time": "21:16:32", "remaining_time": "0:03:01"}
|
10063 |
+
{"current_steps": 100590, "total_steps": 100818, "loss": 0.0011, "lr": 1.5579299731671715e-10, "epoch": 2.9931709639504263, "percentage": 99.77, "elapsed_time": "21:16:39", "remaining_time": "0:02:53"}
|
10064 |
+
{"current_steps": 100600, "total_steps": 100818, "loss": 0.0024, "lr": 1.4242670251018997e-10, "epoch": 2.993468525434068, "percentage": 99.78, "elapsed_time": "21:16:47", "remaining_time": "0:02:46"}
|
10065 |
+
{"current_steps": 100610, "total_steps": 100818, "loss": 0.0025, "lr": 1.2965978199941388e-10, "epoch": 2.9937660869177094, "percentage": 99.79, "elapsed_time": "21:16:56", "remaining_time": "0:02:38"}
|
10066 |
+
{"current_steps": 100620, "total_steps": 100818, "loss": 0.0028, "lr": 1.174922373148313e-10, "epoch": 2.994063648401351, "percentage": 99.8, "elapsed_time": "21:17:03", "remaining_time": "0:02:30"}
|
10067 |
+
{"current_steps": 100630, "total_steps": 100818, "loss": 0.0012, "lr": 1.0592406991472015e-10, "epoch": 2.9943612098849925, "percentage": 99.81, "elapsed_time": "21:17:10", "remaining_time": "0:02:23"}
|
10068 |
+
{"current_steps": 100640, "total_steps": 100818, "loss": 0.002, "lr": 9.495528118685926e-11, "epoch": 2.994658771368634, "percentage": 99.82, "elapsed_time": "21:17:16", "remaining_time": "0:02:15"}
|
10069 |
+
{"current_steps": 100650, "total_steps": 100818, "loss": 0.002, "lr": 8.458587244575268e-11, "epoch": 2.9949563328522757, "percentage": 99.83, "elapsed_time": "21:17:22", "remaining_time": "0:02:07"}
|
10070 |
+
{"current_steps": 100660, "total_steps": 100818, "loss": 0.0016, "lr": 7.481584493373994e-11, "epoch": 2.9952538943359173, "percentage": 99.84, "elapsed_time": "21:17:32", "remaining_time": "0:02:00"}
|
10071 |
+
{"current_steps": 100670, "total_steps": 100818, "loss": 0.0013, "lr": 6.56451998232166e-11, "epoch": 2.995551455819559, "percentage": 99.85, "elapsed_time": "21:17:40", "remaining_time": "0:01:52"}
|
10072 |
+
{"current_steps": 100680, "total_steps": 100818, "loss": 0.0017, "lr": 5.7073938212748315e-11, "epoch": 2.9958490173032004, "percentage": 99.86, "elapsed_time": "21:17:46", "remaining_time": "0:01:45"}
|
10073 |
+
{"current_steps": 100690, "total_steps": 100818, "loss": 0.001, "lr": 4.9102061130401616e-11, "epoch": 2.996146578786842, "percentage": 99.87, "elapsed_time": "21:17:54", "remaining_time": "0:01:37"}
|
10074 |
+
{"current_steps": 100700, "total_steps": 100818, "loss": 0.0012, "lr": 4.172956953096829e-11, "epoch": 2.9964441402704836, "percentage": 99.88, "elapsed_time": "21:18:02", "remaining_time": "0:01:29"}
|
10075 |
+
{"current_steps": 100710, "total_steps": 100818, "loss": 0.0025, "lr": 3.4956464298741e-11, "epoch": 2.996741701754125, "percentage": 99.89, "elapsed_time": "21:18:11", "remaining_time": "0:01:22"}
|
10076 |
+
{"current_steps": 100720, "total_steps": 100818, "loss": 0.0018, "lr": 2.8782746246402983e-11, "epoch": 2.9970392632377667, "percentage": 99.9, "elapsed_time": "21:18:19", "remaining_time": "0:01:14"}
|
10077 |
+
{"current_steps": 100730, "total_steps": 100818, "loss": 0.0012, "lr": 2.3208416112807664e-11, "epoch": 2.9973368247214083, "percentage": 99.91, "elapsed_time": "21:18:26", "remaining_time": "0:01:07"}
|
10078 |
+
{"current_steps": 100740, "total_steps": 100818, "loss": 0.0013, "lr": 1.8233474566864418e-11, "epoch": 2.99763438620505, "percentage": 99.92, "elapsed_time": "21:18:34", "remaining_time": "0:00:59"}
|
10079 |
+
{"current_steps": 100750, "total_steps": 100818, "loss": 0.0024, "lr": 1.3857922204763008e-11, "epoch": 2.9979319476886914, "percentage": 99.93, "elapsed_time": "21:18:41", "remaining_time": "0:00:51"}
|
10080 |
+
{"current_steps": 100760, "total_steps": 100818, "loss": 0.0026, "lr": 1.0081759551083814e-11, "epoch": 2.998229509172333, "percentage": 99.94, "elapsed_time": "21:18:48", "remaining_time": "0:00:44"}
|
10081 |
+
{"current_steps": 100770, "total_steps": 100818, "loss": 0.0015, "lr": 6.90498705879783e-12, "epoch": 2.998527070655974, "percentage": 99.95, "elapsed_time": "21:18:57", "remaining_time": "0:00:36"}
|
10082 |
+
{"current_steps": 100780, "total_steps": 100818, "loss": 0.0017, "lr": 4.327605108156441e-12, "epoch": 2.9988246321396157, "percentage": 99.96, "elapsed_time": "21:19:05", "remaining_time": "0:00:28"}
|
10083 |
+
{"current_steps": 100790, "total_steps": 100818, "loss": 0.002, "lr": 2.3496140089118715e-12, "epoch": 2.9991221936232573, "percentage": 99.97, "elapsed_time": "21:19:13", "remaining_time": "0:00:21"}
|
10084 |
+
{"current_steps": 100800, "total_steps": 100818, "loss": 0.0019, "lr": 9.71013996986514e-13, "epoch": 2.999419755106899, "percentage": 99.98, "elapsed_time": "21:19:20", "remaining_time": "0:00:13"}
|
10085 |
+
{"current_steps": 100810, "total_steps": 100818, "loss": 0.0024, "lr": 1.918052389138225e-13, "epoch": 2.9997173165905404, "percentage": 99.99, "elapsed_time": "21:19:27", "remaining_time": "0:00:06"}
|
10086 |
+
{"current_steps": 100818, "total_steps": 100818, "epoch": 2.9999553657774536, "percentage": 100.0, "elapsed_time": "21:19:53", "remaining_time": "0:00:00"}
|