Training in progress, epoch 13

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2268fc1b1b9525c05540a5bf663ee12d6a95293d66b0a138f03e25ea7ca2c55b
+oid sha256:6b85b700135583cd5176b904e6a43def83fbe62e780b9528c4bd45b3978b57d4
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e935efab4fd88c7ae660f5c3c670419c638539db82de20a294cf5cfb89bc7d
+oid sha256:948791620152e87b5b5437e9c8f71150c815df3efab6c98fabb59f7281124335
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a8b8417b97c64309eab072898add0b6190cb164a74530c47ddcac9d5ce4dc5
+oid sha256:e15408f5850e78581eb066d9d2aceb944fe0aeb8c1221bb604049c116977a241
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ce20425e8903a41b042e66409ef75fe886f2364e189f3272ed411adde872d9
+oid sha256:ef37d792c08e76121271f7f32f98429e212e7145d459c624d67f66967fbbc01a
 size 1089994880

trainer_log.jsonl

@@ -118,3 +118,14 @@
 {"current_steps": 118, "total_steps": 130, "loss": 0.2206, "lr": 2.573177902642726e-07, "epoch": 11.8, "percentage": 90.77, "elapsed_time": "0:43:03", "remaining_time": "0:04:22"}
 {"current_steps": 119, "total_steps": 130, "loss": 0.1837, "lr": 2.1651789586287442e-07, "epoch": 11.9, "percentage": 91.54, "elapsed_time": "0:43:14", "remaining_time": "0:03:59"}
 {"current_steps": 120, "total_steps": 130, "loss": 0.2006, "lr": 1.7916662733218848e-07, "epoch": 12.0, "percentage": 92.31, "elapsed_time": "0:43:24", "remaining_time": "0:03:37"}
+{"current_steps": 121, "total_steps": 130, "loss": 0.2014, "lr": 1.4529091286973994e-07, "epoch": 12.1, "percentage": 93.08, "elapsed_time": "0:45:53", "remaining_time": "0:03:24"}
+{"current_steps": 122, "total_steps": 130, "loss": 0.2224, "lr": 1.1491517499091498e-07, "epoch": 12.2, "percentage": 93.85, "elapsed_time": "0:46:04", "remaining_time": "0:03:01"}
+{"current_steps": 123, "total_steps": 130, "loss": 0.2179, "lr": 8.80613129216762e-08, "epoch": 12.3, "percentage": 94.62, "elapsed_time": "0:46:14", "remaining_time": "0:02:37"}
+{"current_steps": 124, "total_steps": 130, "loss": 0.2017, "lr": 6.474868681043578e-08, "epoch": 12.4, "percentage": 95.38, "elapsed_time": "0:46:25", "remaining_time": "0:02:14"}
+{"current_steps": 125, "total_steps": 130, "loss": 0.2009, "lr": 4.499410377045765e-08, "epoch": 12.5, "percentage": 96.15, "elapsed_time": "0:46:37", "remaining_time": "0:01:51"}
+{"current_steps": 126, "total_steps": 130, "loss": 0.1787, "lr": 2.8811805762860578e-08, "epoch": 12.6, "percentage": 96.92, "elapsed_time": "0:46:48", "remaining_time": "0:01:29"}
+{"current_steps": 127, "total_steps": 130, "loss": 0.2302, "lr": 1.6213459328950355e-08, "epoch": 12.7, "percentage": 97.69, "elapsed_time": "0:47:00", "remaining_time": "0:01:06"}
+{"current_steps": 128, "total_steps": 130, "loss": 0.2181, "lr": 7.2081471792911914e-09, "epoch": 12.8, "percentage": 98.46, "elapsed_time": "0:47:11", "remaining_time": "0:00:44"}
+{"current_steps": 129, "total_steps": 130, "loss": 0.1762, "lr": 1.8023616455731253e-09, "epoch": 12.9, "percentage": 99.23, "elapsed_time": "0:47:22", "remaining_time": "0:00:22"}
+{"current_steps": 130, "total_steps": 130, "loss": 0.211, "lr": 0.0, "epoch": 13.0, "percentage": 100.0, "elapsed_time": "0:47:34", "remaining_time": "0:00:00"}
+{"current_steps": 130, "total_steps": 130, "epoch": 13.0, "percentage": 100.0, "elapsed_time": "0:52:51", "remaining_time": "0:00:00"}