Training in progress, step 5

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
-    "up_proj",
+    "q_proj",
     "o_proj",
     "k_proj",
+    "down_proj",
     "gate_proj",
-    "q_proj"
+    "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5092e31e1f34960a471eb65c1ec1481e18abe61f14efd816b04124adb6383156
+oid sha256:706b7ddb18d402e988ee734375f8e10dce3dcf7db79ccd90b598148a2d72bc04
 size 167832240

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.671875,
-    "eval_runtime": 0.2751,
-    "eval_samples_per_second": 14.54,
-    "eval_steps_per_second": 3.635
+    "eval_loss": 0.68359375,
+    "eval_runtime": 0.2697,
+    "eval_samples_per_second": 14.83,
+    "eval_steps_per_second": 3.707
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.671875,
-    "eval_runtime": 0.2751,
-    "eval_samples_per_second": 14.54,
-    "eval_steps_per_second": 3.635
+    "eval_loss": 0.68359375,
+    "eval_runtime": 0.2697,
+    "eval_samples_per_second": 14.83,
+    "eval_steps_per_second": 3.707
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4295e5810f5e42799cee4732da7dc252b070306543fcfa081cc488825d1c6c3f
+oid sha256:8f2f8d5722efd7acbf58563d4929a8b502a70bdb4351d17c9a92964e354fe5f3
 size 4977230976