Training in progress, step 10

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
     "gate_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
-    "k_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125e13f7cb1765ce96ec4e427f5b88e85439661f1efca9531e76c717ea31fbda
+oid sha256:91933fd2dbd762c0f1fd07d4b1bec63847485ce35cfe4d919cc8098127fcb4be
 size 167832240

runs/Aug20_07-28-42_5a8ce981d5b2/events.out.tfevents.1724138938.5a8ce981d5b2.211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6f23207a5161f49f579140ef328e74b642df5970e814f0670f048b9807af6a
+size 8021

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:d3e98a1d239f4d6410285da9966afe7c5f92dc3cd915cba97f34c6b720a93e8e
+oid sha256:3892af5d01f9424deca8b4d0c30f0efd8c6795088d7594c905ed2ed6d282e8fc
 size 5176