end of finetuning

README.md

@@ -54,5 +54,5 @@ The following hyperparameters were used during training:
 - PEFT 0.13.2
 - Transformers 4.44.2
 - Pytorch 2.5.0+cu121
-- Datasets 3.0.2
+- Datasets 3.1.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
+    "gate_proj",
     "up_proj",
-    "down_proj",
     "v_proj",
+    "k_proj",
     "o_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 sha256:0108c3cf42ca57237b9033051cc2a0d0d084e6cfd2ae464c6bdcbb8eba08cfd3
+oid sha256:8cecdb346932b342c411df291f651f78a4b3293e21a8ebab0ca9302602869454
 size 97307544

runs/Nov01_10-35-27_d47c93638a76/events.out.tfevents.1730457449.d47c93638a76.1049.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf21d09c84e2c76149faa8d1d6d6b06e5ba42d86d77687bee3999ed8347ae991
+size 6774

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead1c488717d260e446f1e3b06abda6e3b8c1d9fb1a3ada53da2f1e1c88b3cd5
+oid sha256:052e1d5b4b6afcd8169ed69ba6248c9ec4771619b8a1bf12b710cb5ef84da4be
 size 5496