Model save

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ae2022f453d5bc64fcc557be09cba7e1a151bf480dcbe7e4ce44fbfb893bfa
+oid sha256:e5921c0fd6d2eb03fa31b3b31670bcd75bd838590709d826641fbd2ae591bc11
 size 1103312056

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.6159274578094482,
+      "grad_norm": 0.6541855931282043,
       "learning_rate": 8.786407766990292e-05,
-      "loss": 0.7326,
+      "loss": 0.8179,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.45552706718444824,
+      "grad_norm": 0.48072507977485657,
       "learning_rate": 7.572815533980583e-05,
-      "loss": 0.3702,
+      "loss": 0.4138,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.440681517124176,
+      "grad_norm": 0.4883740544319153,
       "learning_rate": 6.359223300970875e-05,
-      "loss": 0.3325,
+      "loss": 0.3734,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.4214372932910919,
+      "grad_norm": 0.45032238960266113,
       "learning_rate": 5.145631067961165e-05,
-      "loss": 0.3201,
+      "loss": 0.3606,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.40064775943756104,
+      "grad_norm": 0.42356109619140625,
       "learning_rate": 3.9320388349514564e-05,
-      "loss": 0.3109,
+      "loss": 0.3521,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.4439554214477539,
+      "grad_norm": 0.4464420676231384,
       "learning_rate": 2.7184466019417475e-05,
-      "loss": 0.3051,
+      "loss": 0.3473,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.4426790773868561,
+      "grad_norm": 0.45505988597869873,
       "learning_rate": 1.5048543689320387e-05,
-      "loss": 0.2952,
+      "loss": 0.3394,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.4219134747982025,
+      "grad_norm": 0.40663233399391174,
       "learning_rate": 2.912621359223301e-06,
-      "loss": 0.2899,
+      "loss": 0.3358,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
-      "total_flos": 4.867642930150072e+17,
-      "train_loss": 0.367200387565835,
-      "train_runtime": 8608.2467,
-      "train_samples_per_second": 61.261,
-      "train_steps_per_second": 0.239
+      "total_flos": 5.02338223728341e+17,
+      "train_loss": 0.41515450986843666,
+      "train_runtime": 8856.6028,
+      "train_samples_per_second": 59.543,
+      "train_steps_per_second": 0.233
     }
   ],
   "logging_steps": 250,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.867642930150072e+17,
+  "total_flos": 5.02338223728341e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ad0b8eecbff5e8dbe3ece6c82b15da0f30681324000404361929c5959dac6a
+oid sha256:f75fc3677fd8ad1feca080a4f3c5d9d3134501587f21d3481dd1897201810002
 size 5240