Training in progress, step 260

adapter_config.json

@@ -8,28 +8,34 @@
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
-  "init_lora_weights": "gaussian",
+  "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.1,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "down_proj",
+    "k_proj",
     "gate_proj",
     "up_proj",
-    "k_proj",
+    "lm_head",
+    "fc1",
+    "out_proj",
+    "fc2",
     "q_proj",
-    "v_proj"
+    "linear_1",
+    "linear_2",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2dd5babf6d24d0ca2ca40fa5c22a8e16fd033a11f57a04b89dd70606f8d3148
-size 86573968
+oid sha256:d4224dab146b0767daed913a68f976fe1805d35de6dc6fd90ceb735b27868bab
+size 3003823256

runs/Oct17_13-18-37_instance-20241013-151046-finetune/events.out.tfevents.1729171121.instance-20241013-151046-finetune.2259592.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbec5dd2e336f59af675634c9426561a797982a9724bf71274d43d839557d4e
+size 18961

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3096d08840d5e028094f2f6f7ce798598eacb3ff42f6a5a30c1ef0e17b225a9
+size 5560