Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "q_proj",
+    "k_proj",
     "o_proj",
-    "gate_proj",
+    "up_proj",
     "v_proj",
-    "up_proj"
+    "gate_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 sha256:6f2f113b215450ab189fc7c65df223fe4077525016603c73570358e866cdc8e7
+oid sha256:683696870b61db0f565aec9bfa5088ca76ca9e52e82c515c4f10d625444de591
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4853ed9f59767a4445018b57b82e6c942cfefa8010a55c1d559dcf22cde190aa
+oid sha256:e4f4c1802ae3134714ea3a427a97473d05dd433acd77061011cebf3e591e6ee8
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.013981015421450138,
+      "grad_norm": 0.017626836895942688,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933908462524414,
-      "eval_runtime": 0.0576,
-      "eval_samples_per_second": 277.965,
-      "eval_steps_per_second": 69.491,
+      "eval_loss": 11.933895111083984,
+      "eval_runtime": 0.0579,
+      "eval_samples_per_second": 276.396,
+      "eval_steps_per_second": 69.099,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf5c14d48a8d1b56f6e1b6bf5ab8ce27c957e6685bd040ccaba0e5a642e3e0d
+oid sha256:963c02461e6f5e24acaa8f48a7d43a2b05dfaffb712d905acb8c8d5d74035d73
 size 6776