Training in progress, step 91

adapter_config.json

@@ -3,11 +3,9 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "bias": "none",
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
-  "init_lora_weights": true,
+  "init_lora_weights": "pissa",
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
@@ -22,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc05bcfde2dd84579a363550564f03a66d5c37fc4bddb39067fa7c9361d471d
+oid sha256:868c0546b90bbf191cdd30c449d2951084260d422013f512cd449bd3e4bfa97b
 size 4216407520

runs/Nov18_08-12-16_main-pissa-llama-alpaca-0-0/events.out.tfevents.1731937293.main-pissa-llama-alpaca-0-0.457.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9e0d958405ab835d6bc1dbf941924bbe68aaca11aff61884edc51976e4b0ed
+size 10107

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1c4773b66b4334017eb6ff4b7d0d0df14318532f78a4005e4b3c655d92277b
+oid sha256:feda4170ef3a503acf8148dc55445ecd22e621e69ce823b1d6845573f48e743b
 size 5624