Model save

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816121308858d0f5c6b759c66be1c6e6e75e3de395aab41b3bf9340b542b3b9d
+oid sha256:b150355a4ad66458edda73bfcad6a82d94006ed631a49a87a6b1a41d706690fc
 size 1103312056

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.5998400449752808,
+      "grad_norm": 0.6483297944068909,
       "learning_rate": 8.786407766990292e-05,
-      "loss": 0.8149,
+      "loss": 0.8075,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.4742507338523865,
+      "grad_norm": 0.5044422745704651,
       "learning_rate": 7.572815533980583e-05,
-      "loss": 0.413,
+      "loss": 0.4046,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.4695584177970886,
+      "grad_norm": 0.4824484884738922,
       "learning_rate": 6.359223300970875e-05,
-      "loss": 0.3723,
+      "loss": 0.3675,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.4310486912727356,
+      "grad_norm": 0.46804532408714294,
       "learning_rate": 5.145631067961165e-05,
-      "loss": 0.3589,
+      "loss": 0.3546,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.4245561361312866,
+      "grad_norm": 0.46063533425331116,
       "learning_rate": 3.9320388349514564e-05,
-      "loss": 0.3504,
+      "loss": 0.3452,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.44671350717544556,
+      "grad_norm": 0.5105590224266052,
       "learning_rate": 2.7184466019417475e-05,
-      "loss": 0.3453,
+      "loss": 0.3386,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.44142115116119385,
+      "grad_norm": 0.5026459693908691,
       "learning_rate": 1.5048543689320387e-05,
-      "loss": 0.3374,
+      "loss": 0.3286,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.4220291078090668,
+      "grad_norm": 0.49067285656929016,
       "learning_rate": 2.912621359223301e-06,
-      "loss": 0.3335,
+      "loss": 0.3229,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
       "total_flos": 5.02561395295531e+17,
-      "train_loss": 0.41324964912192336,
-      "train_runtime": 8590.228,
-      "train_samples_per_second": 61.389,
-      "train_steps_per_second": 0.24
+      "train_loss": 0.4061128866325304,
+      "train_runtime": 7501.8102,
+      "train_samples_per_second": 70.296,
+      "train_steps_per_second": 0.275
     }
   ],
   "logging_steps": 250,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0931fc2a2259ac386f323f4d7eedacf0dba905111800140d61a2b8c1cf38b824
+oid sha256:9582b58b60b0709bf924bccdb54211549ee25cc771924bbeae800c98acd136c5
 size 5240