End of training

README.md

@@ -42,11 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use paged_adamw_8bit 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: 3
-
-### Training results
-
-
+- num_epochs: 150
 
 ### Framework versions
 

adapter_config.json

@@ -23,14 +23,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "k_proj",
     "down_proj",
+    "q_proj",
+    "gate_proj",
     "up_proj",
+    "o_proj",
     "lora_megnitude_vector",
-    "gate_proj",
-    "k_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a57276d3e02cfb4518098c7b218396bd264ad2c86f3a16bb0640dc2d0f29b3
+oid sha256:2bb3d978c327e31ed44da70ae93337e6900d790a99f07587eee190c84e229be9
 size 50821720

runs/Dec24_14-44-47_ml-ubuntu/events.out.tfevents.1735051488.ml-ubuntu.2030742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6858f1fbfa9c68419bb4e67e7242edbf522bd9ce8919efabc461276479b8e85
+size 9595

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36722898d630add90d6f0726f1c4692a70ad1fdd7867d0471b204d882553bf09
+oid sha256:e4e2f281014e4c9d57529195f7a5232ce406e526cdfb524d50429e34790a3388
 size 5368