Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
+    "q_proj",
     "o_proj",
+    "gate_proj",
     "up_proj",
     "v_proj",
     "k_proj",
-    "q_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.026058631921824105,
       "eval_loss": NaN,
-      "eval_runtime": 0.2562,
-      "eval_samples_per_second": 1010.966,
-      "eval_steps_per_second": 128.81,
+      "eval_runtime": 0.5893,
+      "eval_samples_per_second": 439.496,
+      "eval_steps_per_second": 55.998,
       "step": 1
     },
     {
@@ -194,9 +194,9 @@
     {
       "epoch": 0.6514657980456026,
       "eval_loss": NaN,
-      "eval_runtime": 0.2552,
-      "eval_samples_per_second": 1014.721,
-      "eval_steps_per_second": 129.289,
+      "eval_runtime": 0.4126,
+      "eval_samples_per_second": 627.756,
+      "eval_steps_per_second": 79.984,
       "step": 25
     },
     {
@@ -377,9 +377,9 @@
     {
       "epoch": 1.3029315960912053,
       "eval_loss": NaN,
-      "eval_runtime": 1.5208,
-      "eval_samples_per_second": 170.304,
-      "eval_steps_per_second": 21.699,
+      "eval_runtime": 0.4903,
+      "eval_samples_per_second": 528.219,
+      "eval_steps_per_second": 67.302,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0290b9e0572c0442e2f3c5bb8154917b3c206aa2dee90567c3ae5345037c31cd
+oid sha256:8c9ce3dede1171fbae96fc9e469488048390a8e9e48e1e8b2b43082992111f35
 size 6776