Training in progress, epoch 1

adapter_config.json

@@ -1,8 +1,9 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/phi-1_5",
+  "base_model_name_or_path": null,
   "bias": "none",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -12,24 +13,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 24,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "fc2",
-    "k_proj",
+    "v_proj",
+    "q_proj",
     "dense",
-    "v_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd22c15c0b31787a9790461e9582f1b3078f85a6b3b1e1db96f48d2d3fc90cbd
-size 40926200
+oid sha256:5e9918dd6698e7eec3f690a6d4c96cb731cf8e21667133ac68ecaad1f3385a67
+size 20486760

runs/May14_17-14-23_08ac3315d512/events.out.tfevents.1747242867.08ac3315d512.218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db6389a150825567f2a0cdfda60b6b5a6362358f7af0d5471cbde0f36d9411b
+size 10356

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fda3e4dd9a4d7ff7226f77500530f1a146d2e0229b7ae2b18a0367a87018b5
+oid sha256:b2b959ba01fcba2b15061d29b50a3df9fdfde3a6fb5c815a4744753cd89a6152
 size 5304