End of training

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 10
+- training_steps: 2000
 
 ### Training results
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "down_proj",
+    "gate_proj",
+    "v_proj",
     "k_proj",
+    "o_proj",
     "q_proj",
-    "v_proj",
-    "gate_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:b28859ef91fa79516898e494eed3353551c8479cc3e1986fdae417635431fde9
+oid sha256:e61eb68a422e1f51a8357777f10914ea8eee53334f6b94646633c8ad458e5beb
 size 47584968

runs/Jan27_18-55-48_ws-l4-010/events.out.tfevents.1737989749.ws-l4-010.3206440.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e89b368026ee3d22cc4ccd1ff3ec5ecdcff2a2424f9027d44a56e12babc068a
+size 10500

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6525c90dd48d2e1f559b017ab1c13899d69f3e2c23ff1d6b2a04fabb698a685
-size 5368
+oid sha256:9d8f7e87adfa3288038c2b6662e614cf125ca36e2c041324c6025627e6c9b1b3
+size 5432