Training in progress, step 60

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "q_proj",
-    "up_proj",
     "v_proj",
+    "o_proj",
     "down_proj",
-    "o_proj"
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "k_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:fc374590aee85f5239fe13c09cab2dbbe93888c25368074b9850292cae0f57e8
+oid sha256:36e4a5600b2101b6684597a68270cdc564bae1d09c6268e123128e4daeab7a98
 size 167832240

runs/Aug20_13-48-42_131089ae00d3/events.out.tfevents.1724161732.131089ae00d3.921.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3f75fee1b07ac9aad146ce821678bc769bdd1f3bb3a82ebc58029f5d633cbf
+size 18371

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca725d97e7ef0722813921cb92c339d890dba4afb9bd0f5d2db4940fd724282b
+oid sha256:993324930418d0ed4180274153e36d39c1afe6ff5525e87d0685af29b1b976d3
 size 5176