Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e43f8c63ac354543ef36c72956f999d2dccc19ff99fc2ff60e85728bcd29419
+oid sha256:af6115a97d02a158fec5b5f71d4d66751ae1c61dae552e4eefa6d43d68698ed9
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee72bcea527a9628a0312a134966ca469695d58ab1cfd763557d11b105a6743
+oid sha256:aaafe5e96ff1b31bc808822c5dda6d1a06ac65659790416903614d5b096b0c87
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83006574278a17e33a11fa10fc4b79066d62212cdee756e60d2c07e114786cc0
+oid sha256:093f923db1014287794687550c81a9ee1ae6e1af64084d39e8bf08cad212ae8d
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf8cebc486cf36d5d49b26d7fe5cc04f0bbca3c7c44bff9631112ef18e848b8
+oid sha256:d59607569af98afff6e6598a2d37dc4535336af57565f8ff93d6d75b419e7be8
 size 1089994880

trainer_log.jsonl

@@ -13,3 +13,13 @@
 {"current_steps": 13, "total_steps": 30, "loss": 0.8104, "lr": 6.980398830195785e-06, "epoch": 1.2380952380952381, "percentage": 43.33, "elapsed_time": "0:05:00", "remaining_time": "0:06:32"}
 {"current_steps": 14, "total_steps": 30, "loss": 0.8269, "lr": 6.434016163555452e-06, "epoch": 1.3333333333333333, "percentage": 46.67, "elapsed_time": "0:05:15", "remaining_time": "0:06:00"}
 {"current_steps": 15, "total_steps": 30, "loss": 0.9437, "lr": 5.8682408883346535e-06, "epoch": 1.4285714285714286, "percentage": 50.0, "elapsed_time": "0:05:36", "remaining_time": "0:05:36"}
+{"current_steps": 16, "total_steps": 30, "loss": 0.8208, "lr": 5.290724144552379e-06, "epoch": 1.5238095238095237, "percentage": 53.33, "elapsed_time": "0:05:53", "remaining_time": "0:05:09"}
+{"current_steps": 17, "total_steps": 30, "loss": 0.8353, "lr": 4.7092758554476215e-06, "epoch": 1.619047619047619, "percentage": 56.67, "elapsed_time": "0:06:14", "remaining_time": "0:04:46"}
+{"current_steps": 18, "total_steps": 30, "loss": 0.8716, "lr": 4.131759111665349e-06, "epoch": 1.7142857142857144, "percentage": 60.0, "elapsed_time": "0:06:39", "remaining_time": "0:04:26"}
+{"current_steps": 19, "total_steps": 30, "loss": 0.7681, "lr": 3.5659838364445505e-06, "epoch": 1.8095238095238095, "percentage": 63.33, "elapsed_time": "0:06:58", "remaining_time": "0:04:02"}
+{"current_steps": 20, "total_steps": 30, "loss": 0.8329, "lr": 3.019601169804216e-06, "epoch": 1.9047619047619047, "percentage": 66.67, "elapsed_time": "0:07:20", "remaining_time": "0:03:40"}
+{"current_steps": 21, "total_steps": 30, "loss": 1.2754, "lr": 2.5000000000000015e-06, "epoch": 2.0, "percentage": 70.0, "elapsed_time": "0:07:37", "remaining_time": "0:03:16"}
+{"current_steps": 22, "total_steps": 30, "loss": 0.8055, "lr": 2.0142070414860704e-06, "epoch": 2.0952380952380953, "percentage": 73.33, "elapsed_time": "0:08:52", "remaining_time": "0:03:13"}
+{"current_steps": 23, "total_steps": 30, "loss": 0.8038, "lr": 1.5687918106563326e-06, "epoch": 2.1904761904761907, "percentage": 76.67, "elapsed_time": "0:09:10", "remaining_time": "0:02:47"}
+{"current_steps": 24, "total_steps": 30, "loss": 0.7889, "lr": 1.1697777844051105e-06, "epoch": 2.2857142857142856, "percentage": 80.0, "elapsed_time": "0:09:29", "remaining_time": "0:02:22"}
+{"current_steps": 25, "total_steps": 30, "loss": 0.8067, "lr": 8.225609429353187e-07, "epoch": 2.380952380952381, "percentage": 83.33, "elapsed_time": "0:09:46", "remaining_time": "0:01:57"}