Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "nmcco/gemma-2-27b-speakertokens",
+  "base_model_name_or_path": "nmcco/gemma-2-2b-with-speaker-tokens-nospeaker-tok",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
     "down_proj",
     "k_proj",
-    "v_proj",
     "o_proj",
-    "q_proj"
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68604ef65ab2a86a06c5c1157aa4b121e7bcb8b5039c5830137e0dae61a36d03
-size 114266104
+oid sha256:d8eda45a9b3f292022832df874a279546b94ddccd56b74fb46a3bfbe8abe58eb
+size 20814808

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ba3d82e2d192f5c590b9c04a80c94e6b0027a4858b83dbfe038c58b75e66cd
+oid sha256:15565598e7f1970b6eb39457c72f0665c5b84eb1a87c8a85ddcb30a371b5d66f
 size 6904