Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
-    "o_proj",
-    "up_proj",
+    "down_proj",
     "v_proj",
     "gate_proj",
-    "down_proj"
+    "up_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 sha256:683696870b61db0f565aec9bfa5088ca76ca9e52e82c515c4f10d625444de591
+oid sha256:e2696e864f68cd81631f427694742414eefcd30ead6c7f1a493ed33055c2fc81
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f4c1802ae3134714ea3a427a97473d05dd433acd77061011cebf3e591e6ee8
+oid sha256:a3fb60ac5c567aede5c4a258b112c570d4444903a25f2ebeecd3cf9faa7343f9
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.017626836895942688,
+      "grad_norm": 0.015080804005265236,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933895111083984,
-      "eval_runtime": 0.0579,
-      "eval_samples_per_second": 276.396,
-      "eval_steps_per_second": 69.099,
+      "eval_loss": 11.933900833129883,
+      "eval_runtime": 0.0636,
+      "eval_samples_per_second": 251.495,
+      "eval_steps_per_second": 62.874,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963c02461e6f5e24acaa8f48a7d43a2b05dfaffb712d905acb8c8d5d74035d73
+oid sha256:a528a26120fdf4d351a788ed2ac024d23442f3d61c8af39ad12830519a58c638
 size 6776