Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51a9241b6311030c6cd5c04f2509dd85e04b8fd951e024e9f76cce46dd90856
+oid sha256:a7a07963d3036e90a675f05387fa9bb6c43eeb623e9e084bbde253fd38a5e2d8
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebde6849c95ac46c6f62566bdd0aa876c49a93c3fddce5e306249e7dcc2c00f0
+oid sha256:5f9141e2d9a8587f290457a9478882587620f3d3f35b60f2c82ada6dab6e330b
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81cc07a5b653af9ce61ba4496723056c202bf511871373f57032cd14c01f80c
+oid sha256:edd3b2907932dbf3a61cca99001eb0adc8ac1b8907694309d76a7d6dc0fc1f27
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d485ae86a233dee528d82653fe3be172c017280b38acaf24e8d2ac5078598f9
+oid sha256:3694c43e3155a1fe41616341c3b4bd1d3792c3408b9522946384e58166daab3a
 size 1089994880

trainer_log.jsonl

@@ -12,3 +12,13 @@
 {"current_steps": 12, "total_steps": 150, "loss": 0.6261, "lr": 3.2000000000000005e-05, "epoch": 1.2, "percentage": 8.0, "elapsed_time": "0:07:50", "remaining_time": "1:30:14"}
 {"current_steps": 13, "total_steps": 150, "loss": 0.6269, "lr": 3.466666666666667e-05, "epoch": 1.3, "percentage": 8.67, "elapsed_time": "0:08:31", "remaining_time": "1:29:47"}
 {"current_steps": 14, "total_steps": 150, "loss": 0.5967, "lr": 3.733333333333334e-05, "epoch": 1.4, "percentage": 9.33, "elapsed_time": "0:09:00", "remaining_time": "1:27:32"}
+{"current_steps": 15, "total_steps": 150, "loss": 0.5839, "lr": 4e-05, "epoch": 1.5, "percentage": 10.0, "elapsed_time": "0:09:33", "remaining_time": "1:26:05"}
+{"current_steps": 16, "total_steps": 150, "loss": 0.5755, "lr": 3.999458482358924e-05, "epoch": 1.6, "percentage": 10.67, "elapsed_time": "0:09:58", "remaining_time": "1:23:35"}
+{"current_steps": 17, "total_steps": 150, "loss": 0.571, "lr": 3.99783422267705e-05, "epoch": 1.7, "percentage": 11.33, "elapsed_time": "0:10:34", "remaining_time": "1:22:43"}
+{"current_steps": 18, "total_steps": 150, "loss": 5.6007, "lr": 3.9951281005196486e-05, "epoch": 1.8, "percentage": 12.0, "elapsed_time": "0:11:09", "remaining_time": "1:21:51"}
+{"current_steps": 19, "total_steps": 150, "loss": 0.5816, "lr": 3.991341581299609e-05, "epoch": 1.9, "percentage": 12.67, "elapsed_time": "0:11:52", "remaining_time": "1:21:52"}
+{"current_steps": 20, "total_steps": 150, "loss": 0.529, "lr": 3.9864767154838864e-05, "epoch": 2.0, "percentage": 13.33, "elapsed_time": "0:12:26", "remaining_time": "1:20:53"}
+{"current_steps": 21, "total_steps": 150, "loss": 0.4979, "lr": 3.980536137483141e-05, "epoch": 2.1, "percentage": 14.0, "elapsed_time": "0:14:05", "remaining_time": "1:26:35"}
+{"current_steps": 22, "total_steps": 150, "loss": 0.4665, "lr": 3.973523064225159e-05, "epoch": 2.2, "percentage": 14.67, "elapsed_time": "0:14:41", "remaining_time": "1:25:28"}
+{"current_steps": 23, "total_steps": 150, "loss": 0.4194, "lr": 3.965441293412827e-05, "epoch": 2.3, "percentage": 15.33, "elapsed_time": "0:15:15", "remaining_time": "1:24:16"}
+{"current_steps": 24, "total_steps": 150, "loss": 0.4105, "lr": 3.9562952014676116e-05, "epoch": 2.4, "percentage": 16.0, "elapsed_time": "0:15:51", "remaining_time": "1:23:13"}