Training in progress, step 100500
Browse files- model.safetensors +1 -1
- trainer_log.jsonl +49 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3554214752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a97644e194c53b892d56aaa0d7d829f2de4d9bf7e0e1401d56668e5e57b0116
|
3 |
size 3554214752
|
trainer_log.jsonl
CHANGED
@@ -10016,3 +10016,52 @@
|
|
10016 |
{"current_steps": 100150, "total_steps": 236854, "loss": 0.0144, "lr": 7.147313055718049e-06, "epoch": 0.8456650693462244, "percentage": 42.28, "elapsed_time": "19:32:06", "remaining_time": "1 day, 2:39:55"}
|
10017 |
{"current_steps": 100160, "total_steps": 236854, "loss": 0.0057, "lr": 7.146647565710687e-06, "epoch": 0.8457495091933883, "percentage": 42.29, "elapsed_time": "19:32:12", "remaining_time": "1 day, 2:39:46"}
|
10018 |
{"current_steps": 100170, "total_steps": 236854, "loss": 0.0082, "lr": 7.145982029078581e-06, "epoch": 0.8458339490405522, "percentage": 42.29, "elapsed_time": "19:32:19", "remaining_time": "1 day, 2:39:39"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10016 |
{"current_steps": 100150, "total_steps": 236854, "loss": 0.0144, "lr": 7.147313055718049e-06, "epoch": 0.8456650693462244, "percentage": 42.28, "elapsed_time": "19:32:06", "remaining_time": "1 day, 2:39:55"}
|
10017 |
{"current_steps": 100160, "total_steps": 236854, "loss": 0.0057, "lr": 7.146647565710687e-06, "epoch": 0.8457495091933883, "percentage": 42.29, "elapsed_time": "19:32:12", "remaining_time": "1 day, 2:39:46"}
|
10018 |
{"current_steps": 100170, "total_steps": 236854, "loss": 0.0082, "lr": 7.145982029078581e-06, "epoch": 0.8458339490405522, "percentage": 42.29, "elapsed_time": "19:32:19", "remaining_time": "1 day, 2:39:39"}
|
10019 |
+
{"current_steps": 100180, "total_steps": 236854, "loss": 0.0096, "lr": 7.145316445836185e-06, "epoch": 0.8459183888877161, "percentage": 42.3, "elapsed_time": "19:32:26", "remaining_time": "1 day, 2:39:32"}
|
10020 |
+
{"current_steps": 100190, "total_steps": 236854, "loss": 0.0167, "lr": 7.144650815997957e-06, "epoch": 0.84600282873488, "percentage": 42.3, "elapsed_time": "19:32:33", "remaining_time": "1 day, 2:39:25"}
|
10021 |
+
{"current_steps": 100200, "total_steps": 236854, "loss": 0.0076, "lr": 7.143985139578351e-06, "epoch": 0.8460872685820439, "percentage": 42.3, "elapsed_time": "19:32:39", "remaining_time": "1 day, 2:39:16"}
|
10022 |
+
{"current_steps": 100210, "total_steps": 236854, "loss": 0.0065, "lr": 7.143319416591826e-06, "epoch": 0.8461717084292077, "percentage": 42.31, "elapsed_time": "19:32:44", "remaining_time": "1 day, 2:39:07"}
|
10023 |
+
{"current_steps": 100220, "total_steps": 236854, "loss": 0.0069, "lr": 7.142653647052844e-06, "epoch": 0.8462561482763716, "percentage": 42.31, "elapsed_time": "19:32:52", "remaining_time": "1 day, 2:39:01"}
|
10024 |
+
{"current_steps": 100230, "total_steps": 236854, "loss": 0.0073, "lr": 7.141987830975864e-06, "epoch": 0.8463405881235355, "percentage": 42.32, "elapsed_time": "19:32:59", "remaining_time": "1 day, 2:38:54"}
|
10025 |
+
{"current_steps": 100240, "total_steps": 236854, "loss": 0.0076, "lr": 7.141321968375346e-06, "epoch": 0.8464250279706994, "percentage": 42.32, "elapsed_time": "19:33:05", "remaining_time": "1 day, 2:38:46"}
|
10026 |
+
{"current_steps": 100250, "total_steps": 236854, "loss": 0.0049, "lr": 7.140656059265755e-06, "epoch": 0.8465094678178633, "percentage": 42.33, "elapsed_time": "19:33:11", "remaining_time": "1 day, 2:38:38"}
|
10027 |
+
{"current_steps": 100260, "total_steps": 236854, "loss": 0.0055, "lr": 7.139990103661552e-06, "epoch": 0.8465939076650272, "percentage": 42.33, "elapsed_time": "19:33:18", "remaining_time": "1 day, 2:38:30"}
|
10028 |
+
{"current_steps": 100270, "total_steps": 236854, "loss": 0.004, "lr": 7.139324101577204e-06, "epoch": 0.846678347512191, "percentage": 42.33, "elapsed_time": "19:33:23", "remaining_time": "1 day, 2:38:21"}
|
10029 |
+
{"current_steps": 100280, "total_steps": 236854, "loss": 0.0077, "lr": 7.138658053027173e-06, "epoch": 0.8467627873593548, "percentage": 42.34, "elapsed_time": "19:33:29", "remaining_time": "1 day, 2:38:12"}
|
10030 |
+
{"current_steps": 100290, "total_steps": 236854, "loss": 0.0121, "lr": 7.1379919580259285e-06, "epoch": 0.8468472272065187, "percentage": 42.34, "elapsed_time": "19:33:36", "remaining_time": "1 day, 2:38:05"}
|
10031 |
+
{"current_steps": 100300, "total_steps": 236854, "loss": 0.0081, "lr": 7.1373258165879365e-06, "epoch": 0.8469316670536826, "percentage": 42.35, "elapsed_time": "19:33:43", "remaining_time": "1 day, 2:37:58"}
|
10032 |
+
{"current_steps": 100310, "total_steps": 236854, "loss": 0.0069, "lr": 7.136659628727667e-06, "epoch": 0.8470161069008465, "percentage": 42.35, "elapsed_time": "19:33:49", "remaining_time": "1 day, 2:37:50"}
|
10033 |
+
{"current_steps": 100320, "total_steps": 236854, "loss": 0.0178, "lr": 7.135993394459586e-06, "epoch": 0.8471005467480104, "percentage": 42.36, "elapsed_time": "19:33:56", "remaining_time": "1 day, 2:37:42"}
|
10034 |
+
{"current_steps": 100330, "total_steps": 236854, "loss": 0.0112, "lr": 7.135327113798167e-06, "epoch": 0.8471849865951743, "percentage": 42.36, "elapsed_time": "19:34:03", "remaining_time": "1 day, 2:37:36"}
|
10035 |
+
{"current_steps": 100340, "total_steps": 236854, "loss": 0.0077, "lr": 7.134660786757881e-06, "epoch": 0.8472694264423382, "percentage": 42.36, "elapsed_time": "19:34:09", "remaining_time": "1 day, 2:37:28"}
|
10036 |
+
{"current_steps": 100350, "total_steps": 236854, "loss": 0.0165, "lr": 7.1339944133532e-06, "epoch": 0.847353866289502, "percentage": 42.37, "elapsed_time": "19:34:17", "remaining_time": "1 day, 2:37:21"}
|
10037 |
+
{"current_steps": 100360, "total_steps": 236854, "loss": 0.0075, "lr": 7.1333279935985975e-06, "epoch": 0.8474383061366659, "percentage": 42.37, "elapsed_time": "19:34:23", "remaining_time": "1 day, 2:37:13"}
|
10038 |
+
{"current_steps": 100370, "total_steps": 236854, "loss": 0.0131, "lr": 7.132661527508549e-06, "epoch": 0.8475227459838298, "percentage": 42.38, "elapsed_time": "19:34:30", "remaining_time": "1 day, 2:37:07"}
|
10039 |
+
{"current_steps": 100380, "total_steps": 236854, "loss": 0.0101, "lr": 7.131995015097527e-06, "epoch": 0.8476071858309936, "percentage": 42.38, "elapsed_time": "19:34:36", "remaining_time": "1 day, 2:36:58"}
|
10040 |
+
{"current_steps": 100390, "total_steps": 236854, "loss": 0.0086, "lr": 7.1313284563800126e-06, "epoch": 0.8476916256781575, "percentage": 42.38, "elapsed_time": "19:34:43", "remaining_time": "1 day, 2:36:50"}
|
10041 |
+
{"current_steps": 100400, "total_steps": 236854, "loss": 0.0067, "lr": 7.1306618513704795e-06, "epoch": 0.8477760655253214, "percentage": 42.39, "elapsed_time": "19:34:50", "remaining_time": "1 day, 2:36:44"}
|
10042 |
+
{"current_steps": 100410, "total_steps": 236854, "loss": 0.0076, "lr": 7.129995200083407e-06, "epoch": 0.8478605053724853, "percentage": 42.39, "elapsed_time": "19:34:57", "remaining_time": "1 day, 2:36:36"}
|
10043 |
+
{"current_steps": 100420, "total_steps": 236854, "loss": 0.0067, "lr": 7.129328502533276e-06, "epoch": 0.8479449452196491, "percentage": 42.4, "elapsed_time": "19:35:03", "remaining_time": "1 day, 2:36:27"}
|
10044 |
+
{"current_steps": 100430, "total_steps": 236854, "loss": 0.0079, "lr": 7.128661758734569e-06, "epoch": 0.848029385066813, "percentage": 42.4, "elapsed_time": "19:35:09", "remaining_time": "1 day, 2:36:19"}
|
10045 |
+
{"current_steps": 100440, "total_steps": 236854, "loss": 0.0118, "lr": 7.1279949687017614e-06, "epoch": 0.8481138249139769, "percentage": 42.41, "elapsed_time": "19:35:16", "remaining_time": "1 day, 2:36:12"}
|
10046 |
+
{"current_steps": 100450, "total_steps": 236854, "loss": 0.0036, "lr": 7.1273281324493395e-06, "epoch": 0.8481982647611408, "percentage": 42.41, "elapsed_time": "19:35:21", "remaining_time": "1 day, 2:36:03"}
|
10047 |
+
{"current_steps": 100460, "total_steps": 236854, "loss": 0.0102, "lr": 7.126661249991786e-06, "epoch": 0.8482827046083047, "percentage": 42.41, "elapsed_time": "19:35:28", "remaining_time": "1 day, 2:35:56"}
|
10048 |
+
{"current_steps": 100470, "total_steps": 236854, "loss": 0.0092, "lr": 7.125994321343588e-06, "epoch": 0.8483671444554686, "percentage": 42.42, "elapsed_time": "19:35:35", "remaining_time": "1 day, 2:35:48"}
|
10049 |
+
{"current_steps": 100480, "total_steps": 236854, "loss": 0.0065, "lr": 7.125327346519229e-06, "epoch": 0.8484515843026325, "percentage": 42.42, "elapsed_time": "19:35:40", "remaining_time": "1 day, 2:35:39"}
|
10050 |
+
{"current_steps": 100490, "total_steps": 236854, "loss": 0.0096, "lr": 7.1246603255331925e-06, "epoch": 0.8485360241497963, "percentage": 42.43, "elapsed_time": "19:35:47", "remaining_time": "1 day, 2:35:31"}
|
10051 |
+
{"current_steps": 100500, "total_steps": 236854, "loss": 0.0081, "lr": 7.123993258399971e-06, "epoch": 0.8486204639969601, "percentage": 42.43, "elapsed_time": "19:35:53", "remaining_time": "1 day, 2:35:23"}
|
10052 |
+
{"current_steps": 100510, "total_steps": 236854, "loss": 0.0106, "lr": 7.123326145134052e-06, "epoch": 0.848704903844124, "percentage": 42.44, "elapsed_time": "19:36:22", "remaining_time": "1 day, 2:35:46"}
|
10053 |
+
{"current_steps": 100520, "total_steps": 236854, "loss": 0.0036, "lr": 7.122658985749924e-06, "epoch": 0.8487893436912879, "percentage": 42.44, "elapsed_time": "19:36:27", "remaining_time": "1 day, 2:35:37"}
|
10054 |
+
{"current_steps": 100530, "total_steps": 236854, "loss": 0.0095, "lr": 7.121991780262076e-06, "epoch": 0.8488737835384518, "percentage": 42.44, "elapsed_time": "19:36:35", "remaining_time": "1 day, 2:35:31"}
|
10055 |
+
{"current_steps": 100540, "total_steps": 236854, "loss": 0.0046, "lr": 7.121324528685003e-06, "epoch": 0.8489582233856157, "percentage": 42.45, "elapsed_time": "19:36:42", "remaining_time": "1 day, 2:35:23"}
|
10056 |
+
{"current_steps": 100550, "total_steps": 236854, "loss": 0.006, "lr": 7.120657231033196e-06, "epoch": 0.8490426632327795, "percentage": 42.45, "elapsed_time": "19:36:48", "remaining_time": "1 day, 2:35:15"}
|
10057 |
+
{"current_steps": 100560, "total_steps": 236854, "loss": 0.0073, "lr": 7.119989887321148e-06, "epoch": 0.8491271030799434, "percentage": 42.46, "elapsed_time": "19:36:55", "remaining_time": "1 day, 2:35:08"}
|
10058 |
+
{"current_steps": 100570, "total_steps": 236854, "loss": 0.0053, "lr": 7.119322497563354e-06, "epoch": 0.8492115429271073, "percentage": 42.46, "elapsed_time": "19:37:01", "remaining_time": "1 day, 2:35:00"}
|
10059 |
+
{"current_steps": 100580, "total_steps": 236854, "loss": 0.0034, "lr": 7.11865506177431e-06, "epoch": 0.8492959827742712, "percentage": 42.46, "elapsed_time": "19:37:07", "remaining_time": "1 day, 2:34:52"}
|
10060 |
+
{"current_steps": 100590, "total_steps": 236854, "loss": 0.0058, "lr": 7.117987579968513e-06, "epoch": 0.8493804226214351, "percentage": 42.47, "elapsed_time": "19:37:14", "remaining_time": "1 day, 2:34:44"}
|
10061 |
+
{"current_steps": 100600, "total_steps": 236854, "loss": 0.0069, "lr": 7.117320052160458e-06, "epoch": 0.849464862468599, "percentage": 42.47, "elapsed_time": "19:37:21", "remaining_time": "1 day, 2:34:38"}
|
10062 |
+
{"current_steps": 100610, "total_steps": 236854, "loss": 0.0106, "lr": 7.116652478364647e-06, "epoch": 0.8495493023157628, "percentage": 42.48, "elapsed_time": "19:37:28", "remaining_time": "1 day, 2:34:30"}
|
10063 |
+
{"current_steps": 100620, "total_steps": 236854, "loss": 0.0158, "lr": 7.115984858595576e-06, "epoch": 0.8496337421629266, "percentage": 42.48, "elapsed_time": "19:37:35", "remaining_time": "1 day, 2:34:23"}
|
10064 |
+
{"current_steps": 100630, "total_steps": 236854, "loss": 0.0073, "lr": 7.115317192867749e-06, "epoch": 0.8497181820100905, "percentage": 42.49, "elapsed_time": "19:37:42", "remaining_time": "1 day, 2:34:16"}
|
10065 |
+
{"current_steps": 100640, "total_steps": 236854, "loss": 0.0071, "lr": 7.114649481195665e-06, "epoch": 0.8498026218572544, "percentage": 42.49, "elapsed_time": "19:37:48", "remaining_time": "1 day, 2:34:08"}
|
10066 |
+
{"current_steps": 100650, "total_steps": 236854, "loss": 0.0057, "lr": 7.113981723593828e-06, "epoch": 0.8498870617044183, "percentage": 42.49, "elapsed_time": "19:37:56", "remaining_time": "1 day, 2:34:02"}
|
10067 |
+
{"current_steps": 100660, "total_steps": 236854, "loss": 0.0127, "lr": 7.113313920076742e-06, "epoch": 0.8499715015515822, "percentage": 42.5, "elapsed_time": "19:38:03", "remaining_time": "1 day, 2:33:55"}
|