End of training

README.md

@@ -78,7 +78,7 @@ resume_from_checkpoint: null
 s2_attention: null
 sample_packing: false
 saves_per_epoch: 1
-sequence_len: 1024
+sequence_len: 2048
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer

adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "q_proj",
     "o_proj",
-    "k_proj",
-    "down_proj",
+    "up_proj",
     "gate_proj",
+    "down_proj",
     "v_proj",
-    "up_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ddde3a36b0ca356062609c87fe34714f71547fbe9af9fb64697605c9be3e
+oid sha256:7cb5ea007e0a8eaa8b3e070afc208a583061e439915bd5037980e578e7e57c72
 size 275494090

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d32c083904b1f56e21ef501c80382ac5d4ad36c87fcd1a340d4cb66b0d37da
+oid sha256:7acd179ffa2ea546a5bde50d8aa5560dc49adab619740d8adedd11ea21f628e4
 size 275341720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c59052ba1586b2b1a04bd7d18f4c3ce3f158983ba0ac0037958d221d817fc9b0
+oid sha256:0f720f4d873ef474d7e6f7f90e6967531d974a064d73ce6609e9da23b50d2421
 size 6776