Training in progress, epoch 3

adapter_config.json

@@ -9,7 +9,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -17,17 +17,17 @@
     "lm_head"
   ],
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "o_proj",
     "down_proj",
-    "q_proj",
-    "k_proj",
     "v_proj",
+    "gate_proj",
+    "k_proj",
     "up_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650937e5f041033b6fc2371355f828edc18365d8799ae72ace9db4188782eeb7
-size 1090646616
+oid sha256:137d252aed948c6d1c406489ff5120c338c1c9c0fe05f7ac6055065f3b69cca3
+size 1132590104

runs/Apr06_11-21-37_90d0c6419ce2/events.out.tfevents.1712402501.90d0c6419ce2.789.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d5b32c6ecb328826cca92d46b0761aa3c9ec0638d79170a78a30a9e91155f4
-size 6476
+oid sha256:5091fe3e913982233bc5092dfb13d7a47a50c439af8c3463e6cf64ba1cca3579
+size 7298

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db107a659e36681c588786c4c1f79eeff989b22f58b53f8873df602a1cf6b26c
+oid sha256:f48e910c5f01ebcecf5cec2f4731ab4fd94fa30ed0be2744dfe04b2f9c65e251
 size 4728