Training in progress, step 400, checkpoint

checkpoint-400/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "up_proj",
     "q_proj",
-    "k_proj",
-    "v_proj",
     "down_proj",
-    "up_proj",
-    "o_proj"
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
   ],
   "task_type": null,
   "use_dora": false,

checkpoint-400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5256433f9c923f3493a02bf569833f89d5fbfcff5be680cfc069aa2df5d706ea
+oid sha256:0cc89dfb9b765b32ce6f448933129830c849d570b08a647f54c99af737f80fde
 size 180385008

checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9faf1b7025b56e814394009eb78edf0ff342576185198b9250f97ece766f9564
-size 91855290
+oid sha256:fbca4a361a60953927988840fdcccedc3d91cd6a83e7812adb9751746163b151
+size 92431954

checkpoint-400/trainer_state.json

@@ -25,17 +25,17 @@
     },
     {
       "epoch": 0.3574620196604111,
-      "grad_norm": 0.41231265664100647,
+      "grad_norm": 0.3873799443244934,
       "learning_rate": 9.95497608932715e-05,
-      "loss": 0.1347,
+      "loss": 0.1345,
       "step": 400
     },
     {
       "epoch": 0.3574620196604111,
-      "eval_loss": 0.1247013583779335,
-      "eval_runtime": 42.7006,
-      "eval_samples_per_second": 4.239,
-      "eval_steps_per_second": 2.131,
+      "eval_loss": 0.12613661587238312,
+      "eval_runtime": 44.9042,
+      "eval_samples_per_second": 4.031,
+      "eval_steps_per_second": 2.027,
       "step": 400
     }
   ],