Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "../../../model-weights/Mistral-7B-v0.3",
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "k_proj",
-    "v_proj",
     "o_proj",
     "q_proj",
-    "up_proj",
-    "down_proj"
+    "gate_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:a05d9af34cbc8e73c9fb1fcff1006d7729c68cd8b3b7db216c90cce698cf7acf
+oid sha256:c30eec269ce79e6391d7562b509028b01f6cdb9b2f5a0d71987ec095692fc850
 size 167832240

runs/Feb28_01-01-01_gpu010/events.out.tfevents.1740725012.gpu010.12482.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8065330e209a8a627c9848d1cee055736418fb8dae8123dce0987d59ae31d6da
+size 11106

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4973e23c51ecaa3da0202b6765a4e42ea04d8032482ce0ee50484bcfdb23f38e
-size 6328
+oid sha256:c8a78117f51d132d902507c9b2d592239e829aae342a464662c7d1f1eb4eebf4
+size 6456