Training in progress, epoch 10

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e05c63f54edd097759e6f7d884b71cc4580edd93007440e4ee26960a99b4a1
+oid sha256:2deeab5273c12cdcd10eb04c82632ecfd42e4b2557486227f148b7742650336f
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210298d92673dfe110845ed04387765b93f69aee66418cc73d0a4fed007bca0d
+oid sha256:69925b6fe24282ff40b44792bb37954a7673b7fb099537806bbbbac9ba85b38d
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755ec1fec4a6768b1c057636e889756effa3193b3c65696b5d36a03c13e4ed83
+oid sha256:254a3eceb1e0738a24158ff5d3cf37f3e66db72688101190dc3cf4eaac42f288
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66656823af93376286c3e692513f02551cfd3f5d2e9b9c64de08aa4dbe40469c
+oid sha256:257cd031c223e917f32e3b8c7cee1667e025cfdb8ca06f861de98240ea161b50
 size 1089994880

trainer_log.jsonl

@@ -97,3 +97,13 @@
 {"current_steps": 97, "total_steps": 117, "loss": 0.2628, "lr": 8.688061284200266e-07, "epoch": 10.20253164556962, "percentage": 82.91, "elapsed_time": "1:17:22", "remaining_time": "0:15:57"}
 {"current_steps": 98, "total_steps": 117, "loss": 0.2297, "lr": 7.863952067298042e-07, "epoch": 10.30379746835443, "percentage": 83.76, "elapsed_time": "1:18:06", "remaining_time": "0:15:08"}
 {"current_steps": 99, "total_steps": 117, "loss": 0.2639, "lr": 7.077560319906696e-07, "epoch": 10.405063291139241, "percentage": 84.62, "elapsed_time": "1:18:47", "remaining_time": "0:14:19"}
+{"current_steps": 100, "total_steps": 117, "loss": 0.2529, "lr": 6.329589969143518e-07, "epoch": 10.50632911392405, "percentage": 85.47, "elapsed_time": "1:19:29", "remaining_time": "0:13:30"}
+{"current_steps": 101, "total_steps": 117, "loss": 0.217, "lr": 5.620710549772295e-07, "epoch": 10.60759493670886, "percentage": 86.32, "elapsed_time": "1:20:13", "remaining_time": "0:12:42"}
+{"current_steps": 102, "total_steps": 117, "loss": 0.2323, "lr": 4.951556604879049e-07, "epoch": 10.708860759493671, "percentage": 87.18, "elapsed_time": "1:20:48", "remaining_time": "0:11:52"}
+{"current_steps": 103, "total_steps": 117, "loss": 0.2482, "lr": 4.322727117869951e-07, "epoch": 10.810126582278482, "percentage": 88.03, "elapsed_time": "1:21:33", "remaining_time": "0:11:05"}
+{"current_steps": 104, "total_steps": 117, "loss": 0.2479, "lr": 3.734784976300165e-07, "epoch": 10.91139240506329, "percentage": 88.89, "elapsed_time": "1:22:15", "remaining_time": "0:10:16"}
+{"current_steps": 105, "total_steps": 117, "loss": 0.2239, "lr": 3.18825646801314e-07, "epoch": 11.050632911392405, "percentage": 89.74, "elapsed_time": "1:24:00", "remaining_time": "0:09:36"}
+{"current_steps": 106, "total_steps": 117, "loss": 0.2224, "lr": 2.6836308100417874e-07, "epoch": 11.151898734177216, "percentage": 90.6, "elapsed_time": "1:24:43", "remaining_time": "0:08:47"}
+{"current_steps": 107, "total_steps": 117, "loss": 0.2639, "lr": 2.2213597106929608e-07, "epoch": 11.253164556962025, "percentage": 91.45, "elapsed_time": "1:25:25", "remaining_time": "0:07:58"}
+{"current_steps": 108, "total_steps": 117, "loss": 0.2192, "lr": 1.801856965207338e-07, "epoch": 11.354430379746836, "percentage": 92.31, "elapsed_time": "1:26:01", "remaining_time": "0:07:10"}
+{"current_steps": 109, "total_steps": 117, "loss": 0.217, "lr": 1.4254980853566248e-07, "epoch": 11.455696202531646, "percentage": 93.16, "elapsed_time": "1:26:45", "remaining_time": "0:06:22"}