Training in progress, epoch 1

adapter_config.json

@@ -13,30 +13,27 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "fc1",
-    "o_proj",
-    "q_proj",
     "fc2",
-    "gate_proj",
-    "up_proj",
+    "q_proj",
+    "k_proj",
     "out_proj",
-    "v_proj"
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5437a85ef905468b3230f19d00fd90f28810c2791599fe45ec77b92eb655957
-size 2839124552
+oid sha256:a2f4a075f1381b6bb04cc471e7eb8466ebffa1425a4b303d4920947b867a1664
+size 154114368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7264346be152c9c1da00ecffebf96554a557d4bfe3502bdb21e4bece2d1a742e
-size 5688
+oid sha256:c20bef00ffc01a53cf9b560ca51c42803e0cdb647cd2778efd7f0f66a4cb3aec
+size 5752