Training in progress, step 20

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
     "down_proj",
-    "up_proj",
+    "q_proj",
     "gate_proj",
-    "o_proj",
-    "v_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79f8339fd10656bc3e44887f4514009734d96e2480e18915bdb23bccf834288
+oid sha256:b9a4110b2f067c1c3df33d9875e16ff46ec4326efa78cd8ecf7e6b17dfa169e1
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "./custom_deepspeed", "train_runtime": 262.4605, "train_samples_per_second": 12.192, "train_steps_per_second": 0.076, "total_flos": 3.848728354383462e+16, "train_loss": 1.5906079292297364, "epoch": 0.0365296803652968}
+{"run_name": "./custom_deepspeed", "train_runtime": 262.0252, "train_samples_per_second": 12.213, "train_steps_per_second": 0.076, "total_flos": 3.848728354383462e+16, "train_loss": 1.592696189880371, "epoch": 0.0365296803652968}