Training in progress, step 28

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "k_proj",
-    "up_proj",
     "gate_proj",
+    "o_proj",
     "v_proj",
-    "down_proj"
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb65b9356e4522a83bd90c5236a95ab0167d24378b14de9bb28058fdc40a9ca
+oid sha256:e2dad4871fa49a9ef59cfa0e95d93830bececa9c879646ff8a08e05195686aac
 size 207244392

trainer_log.jsonl

@@ -1,3 +1,3 @@
-{"current_steps": 10, "total_steps": 28, "loss": 0.9002, "lr": 8.18711994874345e-05, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:13:25", "remaining_time": "0:24:09"}
-{"current_steps": 20, "total_steps": 28, "loss": 0.5484, "lr": 2.3208660251050158e-05, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:26:39", "remaining_time": "0:10:39"}
-{"current_steps": 28, "total_steps": 28, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:38:34", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 28, "loss": 0.8991, "lr": 8.18711994874345e-05, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:13:28", "remaining_time": "0:24:14"}
+{"current_steps": 20, "total_steps": 28, "loss": 0.5462, "lr": 2.3208660251050158e-05, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:26:45", "remaining_time": "0:10:42"}
+{"current_steps": 28, "total_steps": 28, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:38:42", "remaining_time": "0:00:00"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bada97cc8e11dc51a09f5d0de260f252598309dde161af954794f57e3c952239
+oid sha256:f1acaa0e2de5de7ee544707ed1f2995e24c8c449ae89d1bfe71f25ccf6af99bb
 size 7608