Training in progress, step 150

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "BioMistral/BioMistral-7B",
+  "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "o_proj",
-    "down_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
-    "q_proj"
+    "v_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:c9bab91057e2ad6f7012d3294b53b31815e96ab43c3eb81ef2826763362c2a4d
+oid sha256:7dc46686fe283c90f20f3fb7dec254a854940f91f13e775423a7ad4f7325c7e9
 size 5368770952

runs/Sep12_19-29-42_e0817b943d3e/events.out.tfevents.1726169386.e0817b943d3e.3491.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdfecc9b87835326d3441b5f75fa4f805eb3f70ec7adaf2ee994c896f56e7a47
+size 11453

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8c234d97d8fdb28d018731dfc5c712a26d941fb5afe7e209ab5b9db0e1a0bf
+oid sha256:ddddedd3ce6c6a9e566eacaec98b0e184800e2fa1e0df2124fd999efa2fe7029
 size 5432