Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
     "down_proj",
-    "v_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
-    "up_proj"
+    "o_proj",
+    "v_proj",
+    "up_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 sha256:1d88b1e51271dd31989fdcb683c1f1b908065dbdaece123315139618413ff168
+oid sha256:94d8850e11cca622370bfbddbc62f582cf23bd36318d3013757d10bf3e7c9035
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22ece71d8000ff8dfbaa944694fb3173f5083ccc053d6dc045708f8cc7d2754
+oid sha256:2e7c0fb781ac70e00afa49c61491fc44eaa8956e31bb48b8c1a757eae1f8b619
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.013278936967253685,
+      "grad_norm": 0.013230768963694572,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933883666992188,
-      "eval_runtime": 0.0604,
-      "eval_samples_per_second": 265.052,
-      "eval_steps_per_second": 66.263,
+      "eval_loss": 11.933895111083984,
+      "eval_runtime": 0.0564,
+      "eval_samples_per_second": 283.589,
+      "eval_steps_per_second": 70.897,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c263e05fe207b407c6cd11bb652d63a63732b2d1b47dcaa717b61ddd3b2908e5
+oid sha256:7222a7b25ac9f1e85fb8b40af9a3b0707f583ffffe88d52dd092c860524156b3
 size 6776