Training in progress, step 1600

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10faeed6ac4b838e0227233b086ba8e1426bad28a5f9f71a767cd4d14194fff7
+oid sha256:5477d9183962b8afe8261e1d3687a50c07760f10ee9ed6769d150ed5313b4e68
 size 147770496

trainer_log.jsonl

@@ -1 +1,4 @@
-{"current_steps": 1560, "total_steps": 851, "epoch": 1.832892804698972, "percentage": 183.31, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 1570, "total_steps": 2553, "loss": 0.4961, "lr": 9.801073315964465e-05, "epoch": 1.844640234948605, "percentage": 61.5, "elapsed_time": "0:30:52", "remaining_time": "0:19:19"}
+{"current_steps": 1580, "total_steps": 2553, "loss": 0.5028, "lr": 9.627652564299405e-05, "epoch": 1.8563876651982378, "percentage": 61.89, "elapsed_time": "1:01:40", "remaining_time": "0:37:58"}
+{"current_steps": 1590, "total_steps": 2553, "loss": 0.5011, "lr": 9.455051721519528e-05, "epoch": 1.8681350954478708, "percentage": 62.28, "elapsed_time": "1:32:25", "remaining_time": "0:55:58"}
+{"current_steps": 1600, "total_steps": 2553, "loss": 0.4977, "lr": 9.283297129362094e-05, "epoch": 1.8798825256975036, "percentage": 62.67, "elapsed_time": "2:03:14", "remaining_time": "1:13:24"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33076acf983c67a9af3ec88ed8cf599555bafd0fc3deb7c70cc87e367b0d75fc
+oid sha256:4b713423fc23989f171bd9369f8d27ecc877d147ecb85294c3afe127b5b5031a
 size 5752