Drew-ch/TAIDE-Merged_Temp

README.md

@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.41.0
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Datasets 2.19.2
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "Wq",
-    "v_proj",
+    "q_proj",
     "Wo",
+    "Wq",
     "Wv",
-    "Wk",
-    "q_proj"
+    "v_proj",
+    "Wk"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e3af15dbcd6add16bf16c6498c4d1c6b13689baa35425f7010bd26a1360df21
+oid sha256:3d7da71103135c930e7cf6bfbad5b3dd20a916f8e3b2172d98d772ef4c1042f2
 size 109069176

runs/Jun06_13-50-57_495652f0d654/events.out.tfevents.1717681968.495652f0d654.2758.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:facdfcccc1d8c36fed2f6df2aacaa2ea03604c13ac9c040721fab238e38ec4cc
+size 5991

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|end_of_text|>"
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e82ae606ee5629f1a2b18f3c910a352ea4ab775c656afdbd9ee1733d992d5a0
-size 5112
+oid sha256:5932f9621d4401df14ba7fc7dd9d904142b667f0a0a3961ec7ef08701f31007c
+size 5304