Training in progress, step 100

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "up_proj",
-    "k_proj",
     "q_proj",
-    "gate_proj",
-    "v_proj",
+    "k_proj",
     "o_proj",
+    "v_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f99d4f8d755725cb833eb5ba1ce5c565b3454d4c82f1b5219a3cf43fb6edf3c4
+oid sha256:9d0a7535df5835b4cebd09e6931ed00dfb4fb3b5692c39569dc0a6d25c1bb81e
 size 50056096

runs/May19_11-55-30_deep-diver-main-fresh-rabbit-1-0-0/events.out.tfevents.1716134302.deep-diver-main-fresh-rabbit-1-0-0.385.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea63bfa5c28931f34edc6348df7f7bfa947f4ac133482f2ab0883c6988f442af
+size 9970

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0962f474e19c3fed701adc37dea159ca4210ee36bb8fad7d566f99a42af8765
-size 5304
+oid sha256:2cc86e24a8f76a34d1a92ba62cc649329593a7bbb34e3d71619e27bd4c6db84c
+size 5368