Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "down_proj",
-    "v_proj",
     "k_proj",
     "up_proj",
-    "q_proj"
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "down_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 sha256:4ffdeb4a8627bfa9b7a1d8fe4bcdac48b5042f4029ad9e717ea47b596472cefe
+oid sha256:1f8c27aadeaf2c61fe2aa558f2a11f1a8d437d63eebb0762eb9f59aeb546e7d5
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd1f7018cfac6c6eda9f564360483fc30e93d6f797e2b8844b49a26e13b9c41
+oid sha256:9a7ee51018df09ef7335302014ee7c6b729d87e07033eb22250964970355dc33
 size 21505540

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 4.349953781741069e-05,
       "eval_loss": 0.8842230439186096,
-      "eval_runtime": 2359.9429,
-      "eval_samples_per_second": 4.102,
-      "eval_steps_per_second": 2.051,
+      "eval_runtime": 2809.6763,
+      "eval_samples_per_second": 3.445,
+      "eval_steps_per_second": 1.723,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cfbb62e62b3dd71d138069b2f91f7c90aafabbfdf98d883e6536055a48877e
+oid sha256:a822097c021eef86977370f9063bd91b19392c28d366f706b15d3522a927a04c
 size 6776