Model save

adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "q_proj",
     "up_proj",
     "gate_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e5e7e65249a38a0be831c2c2f4075aa8346d04526c74eb71a2379c9b7b7b55
+oid sha256:c7f823d070fb4bc434289fe85e13dbd360fc27d0ba59d70e964da5d34863719a
 size 1080767344

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 1.2864075899124146,
+      "grad_norm": 1.1607048511505127,
       "learning_rate": 8.786407766990292e-05,
-      "loss": 0.9145,
+      "loss": 0.8852,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 1.188614010810852,
+      "grad_norm": 0.9901185631752014,
       "learning_rate": 7.572815533980583e-05,
-      "loss": 0.4526,
+      "loss": 0.4521,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.9511885643005371,
+      "grad_norm": 0.8445346355438232,
       "learning_rate": 6.359223300970875e-05,
-      "loss": 0.3883,
+      "loss": 0.3889,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.9136967062950134,
+      "grad_norm": 0.7807681560516357,
       "learning_rate": 5.145631067961165e-05,
-      "loss": 0.3679,
+      "loss": 0.3685,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.8330370187759399,
+      "grad_norm": 0.7362964153289795,
       "learning_rate": 3.9320388349514564e-05,
-      "loss": 0.3575,
+      "loss": 0.3581,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.8505567312240601,
+      "grad_norm": 0.785736620426178,
       "learning_rate": 2.7184466019417475e-05,
-      "loss": 0.3519,
+      "loss": 0.3525,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.8043777942657471,
+      "grad_norm": 0.7113440632820129,
       "learning_rate": 1.5048543689320387e-05,
-      "loss": 0.3441,
+      "loss": 0.3446,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.7657044529914856,
+      "grad_norm": 0.6975888013839722,
       "learning_rate": 2.912621359223301e-06,
-      "loss": 0.34,
+      "loss": 0.3404,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
       "total_flos": 4.996840775351132e+17,
-      "train_loss": 0.43661616056868174,
-      "train_runtime": 6256.3385,
-      "train_samples_per_second": 84.29,
-      "train_steps_per_second": 0.329
+      "train_loss": 0.4334296365386074,
+      "train_runtime": 6711.8297,
+      "train_samples_per_second": 78.57,
+      "train_steps_per_second": 0.307
     }
   ],
   "logging_steps": 250,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b6c52b9f627568833b5a40081bbe0d1bb983e34382ebd886e4a21a6e9cdb57
+oid sha256:4971a71404bdc4471db5496187a2a0962d0fcb9bda93b897a427de69a0807442
 size 5240