Training in progress, step 100

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dae9ece926fc92d97b3ef5e7d9322407cd9ddb406ebb829fa9bf41eb3138774
-size 134235048
+oid sha256:bc9f1ecbe14b7af4d8080e8fb281dc949bb0abae8c421227625280a4132d7e7c
+size 268453016

runs/Apr08_01-25-31_cbb8bfd0aac3/events.out.tfevents.1712539541.cbb8bfd0aac3.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b17a50f35686d41752a08a24ec69f8bd9d887d020dccd6987579da2a9ae56b
+size 5937

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049bf63f77a5d37f6be78d18f5737bdbef6b0cfdb79ff9aaa459721ea5098c63
+oid sha256:4c90e6544094499aa3709ea1a1d655a618f05887f7195ad387f0ab4b39e57cfc
 size 4920