Training in progress, step 500

adapter_config.json

@@ -7,14 +7,19 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "revision": null,
   "target_modules": [
     "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ced87f7939b503d56c01b6ec9e3447cfbd1e5fc4784fdb1357e25abe3d4490
-size 67154893
+oid sha256:e55120625687c565e690bd8174332fd7986f44332a13a1e7941e1ba86c25ced5
+size 160069389

runs/Dec18_23-16-55_gpu3/events.out.tfevents.1702941425.gpu3.3301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c03e226a29cbea34ef0c20e0c69c20290767c9b278e2979fad035448068d59c
+size 5169

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a29bf5877a769de2ed9ae2f45be0f565b383b6404799aebf624f1ed8ded37e
+oid sha256:94c21d71386114f0b1a597033a9077773b7c12a5464db0762dda7c0090069363
 size 3963