Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
-    "v_proj",
-    "down_proj",
-    "q_proj",
+    "k_proj",
+    "gate_proj",
     "up_proj",
-    "gate_proj"
+    "down_proj",
+    "v_proj",
+    "q_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 sha256:37f0b12f2df5b0f3a16b7ba5390c20a6022432d02060e6a2ece844b4bb2d9204
+oid sha256:d7852585117ab7e733a360e395b42a15109794255fc2b94d6fb304fe99b01b38
 size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2749564122b2ed1557383859e91ce01e2a9d8a5d85d8597b9a79b78bf4318a06
+oid sha256:a9dd24bf82675a1b9664d25032a62b0c4463e49ec2e63cc71997601f1f846c91
 size 28134

last-checkpoint/trainer_state.json

@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.0002666666666666667,
-      "grad_norm": 0.014745122753083706,
+      "grad_norm": 0.021443048492074013,
       "learning_rate": 0.0,
       "loss": 11.9308,
       "step": 1
     },
     {
       "epoch": 0.0002666666666666667,
-      "eval_loss": 11.933927536010742,
-      "eval_runtime": 0.0608,
-      "eval_samples_per_second": 263.08,
-      "eval_steps_per_second": 65.77,
+      "eval_loss": 11.933900833129883,
+      "eval_runtime": 0.0575,
+      "eval_samples_per_second": 278.085,
+      "eval_steps_per_second": 69.521,
       "step": 1
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6b8dcb9a6ffeb8b79cc321155c4fedef9714808cc00d893dbca15f2cb3911b
+oid sha256:83494d13a107a003433dc5e1b2823861f25f94221c84a2722f20abfe7fed71d1
 size 6776