Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "up_proj",
+    "o_proj",
+    "down_proj",
     "v_proj",
     "q_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "o_proj"
+    "k_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:a0b84e48017d871f42d1cd64cedba7be9b2b2716880c2a516286aa3a00889d8b
+oid sha256:4e7dd43504caa6e3c4e0865228e9c86b4d107d29815ba3aeabc5527a3d7bf536
 size 137714904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d781b024bc8c21ff06621be1b525bf0979918b7d37a4f443500ed69871d1db
+oid sha256:ede2b629e3e2c39ff05a949466b294289b24d9a42ddd52e37306b6da9eae152a
 size 70674004

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 0.00026768386535501573,
       "eval_loss": 2.071660041809082,
-      "eval_runtime": 396.0093,
-      "eval_samples_per_second": 3.972,
-      "eval_steps_per_second": 1.987,
+      "eval_runtime": 493.3932,
+      "eval_samples_per_second": 3.188,
+      "eval_steps_per_second": 1.595,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d809d2829fef13038bc3334caed1dfe5f274520cc3364e30c729508f10a6ac
+oid sha256:9b1d6e4eecbe56c61402444c5ada80afa4fa66f732c4e57af55e046997df8098
 size 6776