Model save

README.md

@@ -53,4 +53,5 @@ The following hyperparameters were used during training:
 - PEFT 0.13.0
 - Transformers 4.45.2
 - Pytorch 2.4.0
+- Datasets 2.21.0
 - Tokenizers 0.20.0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
+    "down_proj",
     "up_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4362f75679bf4f5e357de009c0daa6baf45eca037300bc533ce7c7af7172c500
+oid sha256:98dd0ea0587b9b1e81279d8b9227b37f8396611c6bf17e6120d39e518ffec2e7
 size 1082290000

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 2.1187877655029297,
+      "grad_norm": 1.9190031290054321,
       "learning_rate": 8.794946550048592e-05,
-      "loss": 0.6386,
+      "loss": 0.6452,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 1.740912675857544,
+      "grad_norm": 1.3683266639709473,
       "learning_rate": 7.580174927113704e-05,
-      "loss": 0.3835,
+      "loss": 0.3863,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 1.9458281993865967,
+      "grad_norm": 1.4516526460647583,
       "learning_rate": 6.365403304178815e-05,
-      "loss": 0.3585,
+      "loss": 0.3609,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 2.2465028762817383,
+      "grad_norm": 1.76002836227417,
       "learning_rate": 5.150631681243926e-05,
-      "loss": 0.3352,
+      "loss": 0.3382,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 2.5679686069488525,
+      "grad_norm": 1.7399638891220093,
       "learning_rate": 3.9358600583090386e-05,
-      "loss": 0.3078,
+      "loss": 0.3105,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 2.835810899734497,
+      "grad_norm": 1.924517035484314,
       "learning_rate": 2.72108843537415e-05,
-      "loss": 0.2888,
+      "loss": 0.2913,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 2.606696367263794,
+      "grad_norm": 1.8956573009490967,
       "learning_rate": 1.5063168124392615e-05,
-      "loss": 0.2672,
+      "loss": 0.2694,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 2.562168836593628,
+      "grad_norm": 1.7733403444290161,
       "learning_rate": 2.915451895043732e-06,
-      "loss": 0.2569,
+      "loss": 0.2591,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
-      "total_flos": 4.998764563388621e+17,
-      "train_loss": 0.35164398545200387,
-      "train_runtime": 15327.6354,
-      "train_samples_per_second": 34.405,
-      "train_steps_per_second": 0.134
+      "total_flos": 4.996544770678579e+17,
+      "train_loss": 0.35469038972576844,
+      "train_runtime": 73403.6809,
+      "train_samples_per_second": 7.184,
+      "train_steps_per_second": 0.028
     }
   ],
   "logging_steps": 250,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.998764563388621e+17,
+  "total_flos": 4.996544770678579e+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 sha256:8633d9c0f297b452fd7e6997b1a857978104ecf0f156a35e33ed6acc4cb7b486
+oid sha256:24b06bab9f3e206e251d5427eee0a2ee36740ed7c01d911e5a1aaffacaa9739c
 size 5176