Training in progress, step 2

adapter_config.json

@@ -29,27 +29,27 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "layers.9.mlp.down_proj",
+    "layers.2.mlp.down_proj",
     "layers.0.mlp.down_proj",
-    "layers.12.mlp.down_proj",
     "q_proj",
-    "layers.8.mlp.down_proj",
-    "o_proj",
-    "k_proj",
-    "layers.15.mlp.down_proj",
-    "layers.1.mlp.down_proj",
-    "layers.5.mlp.down_proj",
-    "layers.3.mlp.down_proj",
-    "gate_up_proj",
-    "layers.2.mlp.down_proj",
-    "layers.13.mlp.down_proj",
+    "layers.9.mlp.down_proj",
     "layers.6.mlp.down_proj",
-    "v_proj",
-    "layers.10.mlp.down_proj",
     "layers.11.mlp.down_proj",
-    "layers.4.mlp.down_proj",
+    "layers.10.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "v_proj",
+    "gate_up_proj",
+    "layers.12.mlp.down_proj",
+    "layers.3.mlp.down_proj",
+    "o_proj",
+    "layers.14.mlp.down_proj",
+    "layers.8.mlp.down_proj",
+    "layers.5.mlp.down_proj",
     "layers.7.mlp.down_proj",
-    "layers.14.mlp.down_proj"
+    "layers.1.mlp.down_proj",
+    "k_proj",
+    "layers.4.mlp.down_proj",
+    "layers.13.mlp.down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6494294b948aa99fff72dbbe472c25a3765f108a83770ffc53569ae817fd860
+oid sha256:64df0764bfe053c84726c27244f3a4f48ca2824cda34102ebae5b1f6c142f440
 size 29912904

runs/Apr09_05-18-42_cs-01knr8f8jy7kcvx4v0ce8jkn3q-1tpz/events.out.tfevents.1775711922.cs-01knr8f8jy7kcvx4v0ce8jkn3q-1tpz.131664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c23f3743cb3b30817c27ef57b88c9bc1587927e18ae9962d38b99b9e5862ff
+size 6645

trainer_log.jsonl

@@ -1,8 +1,3 @@
 {"current_steps": 1, "total_steps": 5, "loss": 2.965193033218384, "lr": 0.0, "epoch": 0.3076923076923077, "percentage": 20.0, "elapsed_time": "0:00:02", "remaining_time": "0:00:10"}
 {"current_steps": 2, "total_steps": 5, "loss": 2.7841198444366455, "lr": 0.0001, "epoch": 0.6153846153846154, "percentage": 40.0, "elapsed_time": "0:00:03", "remaining_time": "0:00:05"}
 {"current_steps": 2, "total_steps": 5, "eval_loss": 2.749584436416626, "epoch": 0.6153846153846154, "percentage": 40.0, "elapsed_time": "0:00:05", "remaining_time": "0:00:08"}
-{"current_steps": 3, "total_steps": 5, "loss": 2.890326499938965, "lr": 8.535533905932738e-05, "epoch": 0.9230769230769231, "percentage": 60.0, "elapsed_time": "0:00:08", "remaining_time": "0:00:05"}
-{"current_steps": 4, "total_steps": 5, "loss": 2.643332004547119, "lr": 5e-05, "epoch": 1.0, "percentage": 80.0, "elapsed_time": "0:00:08", "remaining_time": "0:00:02"}
-{"current_steps": 4, "total_steps": 5, "eval_loss": 2.586768388748169, "epoch": 1.0, "percentage": 80.0, "elapsed_time": "0:00:10", "remaining_time": "0:00:02"}
-{"current_steps": 5, "total_steps": 5, "loss": 2.5542030334472656, "lr": 1.4644660940672627e-05, "epoch": 1.3076923076923077, "percentage": 100.0, "elapsed_time": "0:00:13", "remaining_time": "0:00:00"}
-{"current_steps": 5, "total_steps": 5, "epoch": 1.3076923076923077, "percentage": 100.0, "elapsed_time": "0:00:14", "remaining_time": "0:00:00"}