Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
-    "gate_proj",
-    "v_proj",
-    "down_proj",
+    "k_proj",
     "up_proj",
-    "o_proj"
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_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 sha256:95f9b3b0b9a3b4c66a756817dab4fb65cc89f6da57ce489080c6ce2045387b11
+oid sha256:87353425784104d0f1a6e5d5def26fa72ec7cf5be5bdcb60c99d50fafc80b78c
 size 36981072

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 0.5862,
-      "eval_samples_per_second": 3.412,
-      "eval_steps_per_second": 1.706,
+      "eval_runtime": 0.5874,
+      "eval_samples_per_second": 3.405,
+      "eval_steps_per_second": 1.702,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3c961982fe74f5b91411343af59d9ac021995bcdd240c3a697011d164388d1
+oid sha256:d7c2f14d6cd263cfcc7579ffb2eeffc28582f0b6807ce6e7da6df0a1b642b5ea
 size 6776