Training in progress, step 5

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "down_proj",
-    "v_proj",
+    "up_proj",
     "k_proj",
+    "v_proj",
     "o_proj",
-    "q_proj",
-    "gate_proj",
-    "up_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c450e1cbd58b94ecfd0d5841141af8b9d2f6ba3693b70255f4c2a5b4619d7e
+oid sha256:d52e0d38fcdb26716819afd6481ca1303c968789a8fed6664eacbd2e5d184da0
 size 125248064

runs/Dec07_16-17-34_0791dc8f5ec2/events.out.tfevents.1701966330.0791dc8f5ec2.270.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a3a84abf60c6d899d2394d3da4d9161bfac69fcf873a352fe995cd0555bd1a
+size 5406

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b24c342352645870f6d47f021fb8d46deec6ae91268f62f23c83e4985c2068d
+oid sha256:2b9fc228c3c47641175a267c20a8bed63fa9082c03bc18b5aad785a75b8728f1
 size 4600

training_config.json

@@ -71,7 +71,7 @@
   "eval_delay": 0,
   "eval_steps": 1000,
   "warmup_steps": 3,
-  "max_steps": 150,
+  "max_steps": 100,
   "num_train_epochs": 1,
   "learning_rate": 0.0002,
   "max_grad_norm": 1.0,