Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "gate_proj",
+    "up_proj",
+    "k_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
-    "o_proj",
-    "up_proj",
-    "k_proj"
+    "o_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 sha256:54894ac9731779a4cffad40a96b655b5614be25eaf4a233ca09f1e8b8c40993f
+oid sha256:9c1c29d1f5649df700edb2931a4ba65802f1d7aede9c11934423e1b0801b9fcb
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a43c77e40e118be477ea158d39ef09eeded6e136af1427895a32831cbcc74a
+oid sha256:a42d954b1a09f470dff3b078b5597b5e7417e591f49cdff866f5e78474794bea
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.020904982462525368,
+      "grad_norm": 0.017132652923464775,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933905601501465,
-      "eval_runtime": 0.0579,
-      "eval_samples_per_second": 276.126,
-      "eval_steps_per_second": 69.032,
+      "eval_loss": 11.933894157409668,
+      "eval_runtime": 0.0614,
+      "eval_samples_per_second": 260.547,
+      "eval_steps_per_second": 65.137,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e42930cd52e7d734e30c5c6d6a43f32f194e435c318c4c68450883372a9c56
+oid sha256:5f30b79b60b8c46ca02ae421a50ada3e80027f9f26343b71ced3942fb88eb24b
 size 6776