Training in progress, epoch 1

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "v_proj",
-    "up_proj",
-    "k_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
-    "o_proj"
+    "o_proj",
+    "k_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:fcfcb66cd72088f8181a0a1092d29bd8fc09ff82d17effa3d70a2b66ff7b6c46
+oid sha256:22b9e75291d7b6a2740563836f4ddea1cbababae063344da2efe6c5c4304659a
 size 2146498720

runs/Nov01_08-27-43_a251e1696bd2/events.out.tfevents.1730449669.a251e1696bd2.348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fa9365a1881b25cd1a9e9f9743d200148ea291b4230b4a7b5592086efd802d
+size 64887

tokenizer_config.json

@@ -2077,7 +2077,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 512,
+  "model_max_length": 128,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fdbdaac52ba4ed539b7cf968901b2925a2b3fdbfc9b4a4ab69d68d5107c427
+oid sha256:c9f23754151b7c6749d521a6894aed525cbd58b7c812ffd2d8f55a0c3455196a
 size 5688