Training in progress, step 200

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj",
+    "up_proj",
+    "k_proj",
     "q_proj",
+    "v_proj",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:371b303de59d9e24f248233c859326f2c535471180a3a790e3ce97d3e0937d9e
+oid sha256:e2b4d9dda9295e4ae4116cb98765d5306e840538dd763f36e97dd4fc3568a19a
 size 90207248

tokenizer_config.json

@@ -2059,6 +2059,6 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d4fca3c0742b56a871e562bf753d129c3a1292343466940e0991f4829b4479
+size 5560