End of training

README.md

@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
-    "v_proj",
     "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
     "q_proj",
     "up_proj",
-    "o_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24593e883defc2c6c8037cd4aa8a0ac2ac869d9ccfc704e5c02204230014b7de
+oid sha256:ac386bdf4423ed3e618bb55c804d4e5af256198655e8b167cb77c7ace834a5a1
 size 39256456

runs/Feb26_07-51-59_0c1f5c963644/events.out.tfevents.1708933921.0c1f5c963644.1907.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5bc6b0c4e0051246842504c22d99e49eaf4c1a0eda1680a169c40089651a65
+size 11554

runs/Feb26_07-52-46_0c1f5c963644/events.out.tfevents.1708933969.0c1f5c963644.1907.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20074e3006ff30372aad88a945c5e55b250948b1d29f2675423297f4cca37dd7
+size 11554

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752281a218c9daa23e7421c417365032aa1e62ffc355e40c0903117e9e2221c1
+oid sha256:567e9d55eef539d5f987b0e6091bf820bad735f84657e2d14b3e3013c2164e62
 size 4856