Training in progress, step 10

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
-    "down_proj",
+    "q_proj",
     "v_proj",
+    "down_proj",
+    "gate_proj",
     "up_proj",
-    "q_proj",
-    "k_proj"
+    "k_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 sha256:075027d4cdaffe0ebdc9e46b7b5bcd5123a34bfc693e6310a9bda677c9ff1d4a
+oid sha256:91933fd2dbd762c0f1fd07d4b1bec63847485ce35cfe4d919cc8098127fcb4be
 size 167832240

runs/Aug20_09-07-32_60dd22d1c1a0/events.out.tfevents.1724144874.60dd22d1c1a0.321.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d6dd0de14e450bea600c596aeaed3c5edea7958baf28a7d2ff3dcc30d07ef2
+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:b73f767b546c2e6be7593c238f843c4ec94838fbd9e3f09ad73dcb8f4248d71a
+oid sha256:4039152f89a6e513170b4f315020c79ed0e2b1280f2a8abca2f8363c1f1aa34f
 size 5176