Training in progress, step 5

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
     "k_proj",
-    "v_proj",
     "down_proj",
+    "o_proj",
+    "v_proj",
     "up_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298922edea9bd506a442bf3faaefa327c3431746fa35ad70b63b6f230de6e185
+oid sha256:51326898c9ef6fc768659d7f8ee0bb27d36722ca47a789d23e6736885330909a
 size 83945296

runs/Dec10_09-22-01_ed2eda2b1dab/events.out.tfevents.1702200825.ed2eda2b1dab.1854.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92db483a0a70070a220c3ecea82255e0c3d56f7985fc178ce0dc0bc2ba891ab5
+size 5362

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5059c653756752cb24f5c1887d956f8a30f1a817ab283357ddbf07235a6cac86
+oid sha256:b27b54f4df6b3ea01a348f2fcdb61d482edb9033e83476fc3a25b4bfa991e681
 size 4600

training_config.json

@@ -71,7 +71,7 @@
   "eval_delay": 0,
   "eval_steps": 1000,
   "warmup_steps": 3,
-  "max_steps": 100,
+  "max_steps": 75,
   "num_train_epochs": 1,
   "learning_rate": 0.0002,
   "max_grad_norm": 1.0,