Training in progress, step 60

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
     "k_proj",
+    "q_proj",
+    "up_proj",
     "v_proj",
     "down_proj",
-    "o_proj",
-    "q_proj",
-    "gate_proj"
+    "o_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:b9d95198d68f9d8e42f974e19f5d66e85428a4f61c96a8db3cb4c4ee7d7eaadb
+oid sha256:fc374590aee85f5239fe13c09cab2dbbe93888c25368074b9850292cae0f57e8
 size 167832240

runs/Aug20_12-31-41_dbdf76e0a4ee/events.out.tfevents.1724157111.dbdf76e0a4ee.268.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169297d87626b62eaac60914e9bb30a21fbbf905458e9c8e52903cf75992ef83
+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 sha256:7da0ce8d671bc192795378bd5f52d67ebd19528d1db20d5bf8864fe35fef7738
+oid sha256:ca725d97e7ef0722813921cb92c339d890dba4afb9bd0f5d2db4940fd724282b
 size 5176