Training in progress, epoch 0

adapter_config.json

@@ -8,18 +8,22 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdaede79d7aa73b88648e53b02b9bf18e8deb31afaa99686ce21bd2dc3da674
-size 54560368
+oid sha256:8b6a9a954f9bc591666f5989742125a871da8bb18a85536f2d697cab29681dd2
+size 340225224

runs/Nov23_17-56-00_3c25d1b99ca3/events.out.tfevents.1700762293.3c25d1b99ca3.813.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2d9877d30790aed50ae177525ad414f8d42af891c62459f5789602c478abca
+size 6873

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b9ea130f41610c4015fd44f7913fb90582d5ce5cdc0b70796e585cb26f79dd8
+oid sha256:9324d85ea97af71809e3d932082f96e3a4729f1c8bc6c7bfbe60944fe1d19003
 size 4664