Training in progress, step 28

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "q_proj",
     "o_proj",
+    "down_proj",
+    "gate_proj",
     "up_proj",
-    "q_proj",
     "v_proj",
-    "k_proj",
-    "down_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 sha256:555c830797d68f6cd480f6b5757ec531790bca3a34311ecee191a42962c871fd
+oid sha256:f158e86e11f72e3cadbfea7ba800a6b4be939b28a462247daa70d5ec15132f05
 size 207244392

trainer_log.jsonl

@@ -1,3 +1,3 @@
-{"current_steps": 10, "total_steps": 28, "loss": 0.9027, "lr": 8.18711994874345e-05, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:13:26", "remaining_time": "0:24:11"}
-{"current_steps": 20, "total_steps": 28, "loss": 0.5519, "lr": 2.3208660251050158e-05, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:26:40", "remaining_time": "0:10:40"}
-{"current_steps": 28, "total_steps": 28, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:38:42", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 28, "loss": 0.8992, "lr": 8.18711994874345e-05, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:13:24", "remaining_time": "0:24:08"}
+{"current_steps": 20, "total_steps": 28, "loss": 0.549, "lr": 2.3208660251050158e-05, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:26:38", "remaining_time": "0:10:39"}
+{"current_steps": 28, "total_steps": 28, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:38:30", "remaining_time": "0:00:00"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0947bee77408dfd8c8570dc593f3b0328326d9dcc6ea4f23a777078d30af2c
+oid sha256:0bb3e2e6655e166df7876dab260b82cf8f053e94ca89e18c726c65ba736122d6
 size 7608