Training in progress, epoch 0

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj",
     "q_proj",
     "o_proj",
-    "up_proj",
-    "k_proj"
+    "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1f0e0b19d0ff50e96dc1a092984ec8dbe2d8cd6483e8f5075e3451cd8af0d4
+oid sha256:37546798c6de5b88257155289078634b88697fcdf3603331ebf28aae4390f071
 size 167832688

config.json

@@ -38,7 +38,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.42.3",
   "use_cache": false,
   "vocab_size": 128256
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c381254771883cfaa51f927e708607d8adf333b7fb2a263b66e63152dd7941
-size 7288
+oid sha256:137d77cebbd6fdab4a2e8710d8cdcfe77215de72c36740d1ddf02839f0476616
+size 7416