Model save

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee76dc585a7e8ba46bdb20e416db19ac101127d365a4080ffe2989539045f0e
+oid sha256:c912bd6c1b47a48656f4ae4f8c0cd53416555be1cdd2297192d2f5c47b5564b7
 size 1103312056

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.00045738942571915686,
+      "grad_norm": 0.6159527897834778,
       "learning_rate": 8.786407766990292e-05,
-      "loss": 0.0207,
+      "loss": 0.8155,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.00029479857767000794,
+      "grad_norm": 0.49799874424934387,
       "learning_rate": 7.572815533980583e-05,
-      "loss": 0.0003,
+      "loss": 0.4143,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.0002690601395443082,
+      "grad_norm": 0.5027524828910828,
       "learning_rate": 6.359223300970875e-05,
-      "loss": 0.0002,
+      "loss": 0.3728,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.0002600083244033158,
+      "grad_norm": 0.4434279203414917,
       "learning_rate": 5.145631067961165e-05,
-      "loss": 0.0002,
+      "loss": 0.3591,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.00026350130792707205,
+      "grad_norm": 0.4563457667827606,
       "learning_rate": 3.9320388349514564e-05,
-      "loss": 0.0002,
+      "loss": 0.3505,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.00025795461260713637,
+      "grad_norm": 0.47118082642555237,
       "learning_rate": 2.7184466019417475e-05,
-      "loss": 0.0002,
+      "loss": 0.345,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.0002608244540169835,
+      "grad_norm": 0.4446455240249634,
       "learning_rate": 1.5048543689320387e-05,
-      "loss": 0.0002,
+      "loss": 0.3368,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.0002616070560179651,
+      "grad_norm": 0.4269810914993286,
       "learning_rate": 2.912621359223301e-06,
-      "loss": 0.0002,
+      "loss": 0.333,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
       "total_flos": 5.02561395295531e+17,
-      "train_loss": 0.0027217757191906854,
-      "train_runtime": 7579.4374,
-      "train_samples_per_second": 69.576,
-      "train_steps_per_second": 0.272
+      "train_loss": 0.4133911410581718,
+      "train_runtime": 8627.1447,
+      "train_samples_per_second": 61.127,
+      "train_steps_per_second": 0.239
     }
   ],
   "logging_steps": 250,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06af99df7019b88eb50658af177abd9b74ba64e01cd5d8993a0e51e7560fd205
+oid sha256:90004e4dfb3712af218d80aed2cd5bb64801a4e28047cbf76cce32132410c5a2
 size 5240