Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311a52b716b3339c60a62267c8aa5422f7cbb319cc51e92f9393193e16a0be71
+oid sha256:d51452f09cba25a97858be9728873a4f9ab22ec42b289c5ae919074eae206de2
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e1ff5a56ff1a2121e7a6d994036ff4533b890112ba5b5dc6ff4040d96dd92c
+oid sha256:34537d2f849274bdee2a3478488786ea20b048bbc5eba955a53b159ffbdafd81
 size 20632826

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 1.1053296231102318e-05,
       "eval_loss": 3.9584224224090576,
-      "eval_runtime": 2351.5782,
-      "eval_samples_per_second": 16.199,
-      "eval_steps_per_second": 8.1,
+      "eval_runtime": 2345.0853,
+      "eval_samples_per_second": 16.244,
+      "eval_steps_per_second": 8.122,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a28599c7fc0a215525d73691b99f1a62e15c0977e8bca0dfdee80c494d67c83
+oid sha256:375d55097a57ad2692d76165a3180ddec185f71472834fd49d11cbd14d671db8
 size 6776