Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "down_proj",
-    "o_proj",
     "up_proj",
+    "o_proj",
+    "k_proj",
     "gate_proj",
-    "k_proj"
+    "q_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 sha256:89ebd70b7f581a26b358316551aa9125aced9ba97b19403aa7625805c97e83ba
+oid sha256:248eb77cd6f6bbad7d1bcc7110ff200ac54b7115a21c51c156d8e51f8563ebc1
 size 83945296

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.0002994236095516131,
       "eval_loss": 11.5775728225708,
-      "eval_runtime": 95.8713,
-      "eval_samples_per_second": 7.343,
-      "eval_steps_per_second": 7.343,
+      "eval_runtime": 95.8227,
+      "eval_samples_per_second": 7.347,
+      "eval_steps_per_second": 7.347,
       "step": 1
     },
     {
@@ -40,9 +40,9 @@
     {
       "epoch": 0.0008982708286548395,
       "eval_loss": 11.5775728225708,
-      "eval_runtime": 94.6943,
-      "eval_samples_per_second": 7.434,
-      "eval_steps_per_second": 7.434,
+      "eval_runtime": 95.0865,
+      "eval_samples_per_second": 7.404,
+      "eval_steps_per_second": 7.404,
       "step": 3
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5cf1a7f24b2f4b6ffdd137a7076d460d56660645e71b5af0068e2d73030f31
+oid sha256:1ee223a43027b8c8afd21622e4578463f433159b96d4ac348cc6f399af5db597
 size 6776