End of training

README.md

@@ -77,7 +77,7 @@ lora_target_modules:
 
 gradient_accumulation_steps: 2
 micro_batch_size: 1
-num_epochs: 0.1
+num_epochs: 0.2
 optimizer: paged_adamw_8bit
 lr_scheduler: cosine
 learning_rate: 0.0002
@@ -155,7 +155,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 0.1
+- num_epochs: 0.2
 
 ### Training results
 

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "o_proj",
-    "k_proj"
+    "q_proj",
+    "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35022410b2473b288182ea633c51ffbab225dca82ab0d755107039abc5c6e7a5
+oid sha256:d21af6e8357542230e8b9669f5183ae711e8dae8c2d5c7cbd94887f8c73239e2
 size 27354957

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663a26f1f1a3b4fcfd581184eee642fd42fda734b67a37de0e0427b6782aa593
+oid sha256:caa9ed65767a1c5bf472fc551098fbf96f4669be162665287b2c1326e32b2cbd
 size 27297032

runs/Feb29_17-11-22_azure-jap/events.out.tfevents.1709226683.azure-jap.97068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3807b03d20eaac110839621e9302aab4dea92c6f82f823e1129e00f244050f8c
+size 15204

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c59c6a5f88064305dd076a6acaf260003a37a4382f71c6a289edbc23a6aece0
+oid sha256:608bc2aeb704ee007228ce05771320912e465432790f2336f9c619c7b87612c6
 size 4859