Training in progress, step 8169
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d4b44451890d9c90f26714123d0ddc0bce028e7b88a64d984ac83cbb2bed118
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4aa7b4ee46f51f765b67b592914b330502cec4c7f5bafaab12bdb7b17a6c13c
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71fa806590f371dad24f4550d182d9abe40c08982d1b17ae29e065299fb50847
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:909b99dbe056154e891d9405eefa5537a7a9dc4a9f2e3e145869c2f91c0b4d8e
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -2313,3 +2313,33 @@
|
|
| 2313 |
{"current_steps": 8010, "total_steps": 8169, "loss": 0.1203, "lr": 4.6726099997655985e-08, "epoch": 6.863753213367609, "percentage": 98.05, "elapsed_time": "5:48:40", "remaining_time": "0:06:55"}
|
| 2314 |
{"current_steps": 8015, "total_steps": 8169, "loss": 0.1352, "lr": 4.385240072010355e-08, "epoch": 6.868037703513282, "percentage": 98.11, "elapsed_time": "5:51:29", "remaining_time": "0:06:45"}
|
| 2315 |
{"current_steps": 8020, "total_steps": 8169, "loss": 0.1321, "lr": 4.1069798699389094e-08, "epoch": 6.872322193658954, "percentage": 98.18, "elapsed_time": "5:54:19", "remaining_time": "0:06:34"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2313 |
{"current_steps": 8010, "total_steps": 8169, "loss": 0.1203, "lr": 4.6726099997655985e-08, "epoch": 6.863753213367609, "percentage": 98.05, "elapsed_time": "5:48:40", "remaining_time": "0:06:55"}
|
| 2314 |
{"current_steps": 8015, "total_steps": 8169, "loss": 0.1352, "lr": 4.385240072010355e-08, "epoch": 6.868037703513282, "percentage": 98.11, "elapsed_time": "5:51:29", "remaining_time": "0:06:45"}
|
| 2315 |
{"current_steps": 8020, "total_steps": 8169, "loss": 0.1321, "lr": 4.1069798699389094e-08, "epoch": 6.872322193658954, "percentage": 98.18, "elapsed_time": "5:54:19", "remaining_time": "0:06:34"}
|
| 2316 |
+
{"current_steps": 8025, "total_steps": 8169, "loss": 0.1243, "lr": 3.83783066377319e-08, "epoch": 6.876606683804627, "percentage": 98.24, "elapsed_time": "5:57:11", "remaining_time": "0:06:24"}
|
| 2317 |
+
{"current_steps": 8030, "total_steps": 8169, "loss": 0.113, "lr": 3.5777936821450584e-08, "epoch": 6.8808911739503, "percentage": 98.3, "elapsed_time": "6:00:02", "remaining_time": "0:06:13"}
|
| 2318 |
+
{"current_steps": 8035, "total_steps": 8169, "loss": 0.1331, "lr": 3.326870112090097e-08, "epoch": 6.885175664095972, "percentage": 98.36, "elapsed_time": "6:02:54", "remaining_time": "0:06:03"}
|
| 2319 |
+
{"current_steps": 8040, "total_steps": 8169, "loss": 0.1285, "lr": 3.0850610990422745e-08, "epoch": 6.889460154241645, "percentage": 98.42, "elapsed_time": "6:05:58", "remaining_time": "0:05:52"}
|
| 2320 |
+
{"current_steps": 8045, "total_steps": 8169, "loss": 0.1143, "lr": 2.8523677468286216e-08, "epoch": 6.893744644387318, "percentage": 98.48, "elapsed_time": "6:08:42", "remaining_time": "0:05:40"}
|
| 2321 |
+
{"current_steps": 8050, "total_steps": 8169, "loss": 0.1321, "lr": 2.6287911176643422e-08, "epoch": 6.89802913453299, "percentage": 98.54, "elapsed_time": "6:11:29", "remaining_time": "0:05:29"}
|
| 2322 |
+
{"current_steps": 8055, "total_steps": 8169, "loss": 0.1341, "lr": 2.414332232148375e-08, "epoch": 6.902313624678663, "percentage": 98.6, "elapsed_time": "6:14:14", "remaining_time": "0:05:17"}
|
| 2323 |
+
{"current_steps": 8060, "total_steps": 8169, "loss": 0.1377, "lr": 2.2089920692578427e-08, "epoch": 6.906598114824336, "percentage": 98.67, "elapsed_time": "6:16:52", "remaining_time": "0:05:05"}
|
| 2324 |
+
{"current_steps": 8065, "total_steps": 8169, "loss": 0.1054, "lr": 2.0127715663442737e-08, "epoch": 6.910882604970008, "percentage": 98.73, "elapsed_time": "6:19:47", "remaining_time": "0:04:53"}
|
| 2325 |
+
{"current_steps": 8070, "total_steps": 8169, "loss": 0.1319, "lr": 1.8256716191293876e-08, "epoch": 6.915167095115681, "percentage": 98.79, "elapsed_time": "6:22:37", "remaining_time": "0:04:41"}
|
| 2326 |
+
{"current_steps": 8075, "total_steps": 8169, "loss": 0.1211, "lr": 1.647693081700208e-08, "epoch": 6.919451585261354, "percentage": 98.85, "elapsed_time": "6:25:20", "remaining_time": "0:04:29"}
|
| 2327 |
+
{"current_steps": 8080, "total_steps": 8169, "loss": 0.1236, "lr": 1.4788367665061753e-08, "epoch": 6.923736075407026, "percentage": 98.91, "elapsed_time": "6:28:17", "remaining_time": "0:04:16"}
|
| 2328 |
+
{"current_steps": 8085, "total_steps": 8169, "loss": 0.1101, "lr": 1.3191034443544859e-08, "epoch": 6.928020565552699, "percentage": 98.97, "elapsed_time": "6:31:09", "remaining_time": "0:04:03"}
|
| 2329 |
+
{"current_steps": 8090, "total_steps": 8169, "loss": 0.1327, "lr": 1.1684938444074256e-08, "epoch": 6.932305055698372, "percentage": 99.03, "elapsed_time": "6:33:46", "remaining_time": "0:03:50"}
|
| 2330 |
+
{"current_steps": 8095, "total_steps": 8169, "loss": 0.1158, "lr": 1.0270086541785961e-08, "epoch": 6.936589545844044, "percentage": 99.09, "elapsed_time": "6:36:37", "remaining_time": "0:03:37"}
|
| 2331 |
+
{"current_steps": 8100, "total_steps": 8169, "loss": 0.1226, "lr": 8.946485195295839e-09, "epoch": 6.940874035989717, "percentage": 99.16, "elapsed_time": "6:39:31", "remaining_time": "0:03:24"}
|
| 2332 |
+
{"current_steps": 8105, "total_steps": 8169, "loss": 0.1251, "lr": 7.714140446677399e-09, "epoch": 6.94515852613539, "percentage": 99.22, "elapsed_time": "6:42:27", "remaining_time": "0:03:10"}
|
| 2333 |
+
{"current_steps": 8110, "total_steps": 8169, "loss": 0.1265, "lr": 6.573057921421821e-09, "epoch": 6.949443016281062, "percentage": 99.28, "elapsed_time": "6:45:21", "remaining_time": "0:02:56"}
|
| 2334 |
+
{"current_steps": 8115, "total_steps": 8169, "loss": 0.1228, "lr": 5.523242828429087e-09, "epoch": 6.953727506426735, "percentage": 99.34, "elapsed_time": "6:48:16", "remaining_time": "0:02:43"}
|
| 2335 |
+
{"current_steps": 8120, "total_steps": 8169, "loss": 0.1306, "lr": 4.5646999599657795e-09, "epoch": 6.958011996572408, "percentage": 99.4, "elapsed_time": "6:50:58", "remaining_time": "0:02:28"}
|
| 2336 |
+
{"current_steps": 8125, "total_steps": 8169, "loss": 0.1208, "lr": 3.697433691662866e-09, "epoch": 6.96229648671808, "percentage": 99.46, "elapsed_time": "6:53:49", "remaining_time": "0:02:14"}
|
| 2337 |
+
{"current_steps": 8130, "total_steps": 8169, "loss": 0.1338, "lr": 2.9214479824757336e-09, "epoch": 6.966580976863753, "percentage": 99.52, "elapsed_time": "6:56:39", "remaining_time": "0:01:59"}
|
| 2338 |
+
{"current_steps": 8135, "total_steps": 8169, "loss": 0.1351, "lr": 2.236746374681964e-09, "epoch": 6.970865467009426, "percentage": 99.58, "elapsed_time": "6:59:26", "remaining_time": "0:01:45"}
|
| 2339 |
+
{"current_steps": 8140, "total_steps": 8169, "loss": 0.125, "lr": 1.6433319938569115e-09, "epoch": 6.975149957155098, "percentage": 99.64, "elapsed_time": "7:02:13", "remaining_time": "0:01:30"}
|
| 2340 |
+
{"current_steps": 8145, "total_steps": 8169, "loss": 0.1255, "lr": 1.1412075488581587e-09, "epoch": 6.979434447300771, "percentage": 99.71, "elapsed_time": "7:04:54", "remaining_time": "0:01:15"}
|
| 2341 |
+
{"current_steps": 8150, "total_steps": 8169, "loss": 0.1232, "lr": 7.303753318232964e-10, "epoch": 6.983718937446444, "percentage": 99.77, "elapsed_time": "7:07:45", "remaining_time": "0:00:59"}
|
| 2342 |
+
{"current_steps": 8155, "total_steps": 8169, "loss": 0.1172, "lr": 4.1083721814549893e-10, "epoch": 6.988003427592116, "percentage": 99.83, "elapsed_time": "7:10:39", "remaining_time": "0:00:44"}
|
| 2343 |
+
{"current_steps": 8160, "total_steps": 8169, "loss": 0.1335, "lr": 1.8259466647574386e-10, "epoch": 6.992287917737789, "percentage": 99.89, "elapsed_time": "7:13:25", "remaining_time": "0:00:28"}
|
| 2344 |
+
{"current_steps": 8165, "total_steps": 8169, "loss": 0.1217, "lr": 4.564871871393095e-11, "epoch": 6.996572407883462, "percentage": 99.95, "elapsed_time": "7:16:17", "remaining_time": "0:00:12"}
|
| 2345 |
+
{"current_steps": 8169, "total_steps": 8169, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "7:19:42", "remaining_time": "0:00:00"}
|