Model save

README.md

@@ -35,7 +35,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 1
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "q_proj",
-    "v_proj",
     "up_proj",
+    "o_proj",
     "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d668afb71de6a1fd06fe8612ec0145bd1b1303631697f2507dc24393b2eafc3a
+oid sha256:34217b8fc1880202977c57bbf7b597e2a50f5348001c8f270145dacb66cd9bc3
 size 50128536

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 16384,
     "strategy": "LongestFirst",
     "stride": 0
   },
@@ -239,8 +239,8 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     },
     {
       "id": 50278,
@@ -248,8 +248,8 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     },
     {
       "id": 50279,
@@ -257,8 +257,8 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     },
     {
       "id": 50280,

tokenizer_config.json

@@ -204,26 +204,26 @@
     "50277": {
       "content": "<fim_prefix>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "50278": {
       "content": "<fim_middle>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "50279": {
       "content": "<fim_suffix>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "50280": {
       "content": "<fim_pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34b98b73ff1c6451c0e59f9268f354d99add9e59f3cf1166edf70ec5c5c6494
+oid sha256:6c2def274e41f62c32dd4b86a76686e69ebf9e86de6cfc68c15554cfeadebdd5
 size 4792