SmolLM-360M-Instruct_fsdp_qlora_nf4_adapter

README.md

@@ -57,25 +57,25 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 2.2932        | 0.9524  | 10   | 2.1445          |
-| 2.105         | 2.0     | 21   | 2.0315          |
-| 2.017         | 2.9524  | 31   | 1.9665          |
-| 1.9535        | 4.0     | 42   | 1.9197          |
-| 1.9104        | 4.9524  | 52   | 1.8906          |
-| 1.888         | 6.0     | 63   | 1.8669          |
-| 1.8552        | 6.9524  | 73   | 1.8511          |
-| 1.8491        | 8.0     | 84   | 1.8384          |
-| 1.8228        | 8.9524  | 94   | 1.8296          |
-| 1.8198        | 10.0    | 105  | 1.8224          |
-| 1.8073        | 10.9524 | 115  | 1.8173          |
-| 1.7958        | 12.0    | 126  | 1.8131          |
-| 1.7958        | 12.9524 | 136  | 1.8106          |
+| 2.2926        | 0.9524  | 10   | 2.1440          |
+| 2.1035        | 2.0     | 21   | 2.0304          |
+| 2.0163        | 2.9524  | 31   | 1.9668          |
+| 1.9537        | 4.0     | 42   | 1.9199          |
+| 1.9107        | 4.9524  | 52   | 1.8908          |
+| 1.8883        | 6.0     | 63   | 1.8671          |
+| 1.8554        | 6.9524  | 73   | 1.8512          |
+| 1.8492        | 8.0     | 84   | 1.8385          |
+| 1.8229        | 8.9524  | 94   | 1.8296          |
+| 1.8198        | 10.0    | 105  | 1.8223          |
+| 1.8074        | 10.9524 | 115  | 1.8172          |
+| 1.7958        | 12.0    | 126  | 1.8130          |
+| 1.7958        | 12.9524 | 136  | 1.8105          |
 | 1.792         | 14.0    | 147  | 1.8088          |
-| 1.7843        | 14.9524 | 157  | 1.8080          |
+| 1.7843        | 14.9524 | 157  | 1.8079          |
 | 1.7873        | 16.0    | 168  | 1.8077          |
-| 1.7848        | 16.9524 | 178  | 1.8077          |
-| 1.7837        | 18.0    | 189  | 1.8076          |
-| 1.7828        | 18.9524 | 199  | 1.8076          |
+| 1.7848        | 16.9524 | 178  | 1.8076          |
+| 1.7836        | 18.0    | 189  | 1.8075          |
+| 1.7828        | 18.9524 | 199  | 1.8075          |
 | 1.7827        | 19.0476 | 200  | 1.8076          |
 
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "gate_proj",
+    "v_proj",
     "up_proj",
-    "down_proj",
+    "k_proj",
     "o_proj",
-    "k_proj"
+    "down_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 sha256:51dbf197b9a00eaeef34909e9e6e4f1c69741bb5b4d1003ddbee4ac6a6badaaf
+oid sha256:a74c253a9300c52ed13afb1303a21193b3a26b98795ed94d11ccf5314ac9d653
 size 17426248

runs/Sep04_12-54-06_algo-2/events.out.tfevents.1725454460.algo-2.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703f16a369c8176d34279ca49ad51a45e05f6bf977c616ef3ae79dc269fb038c
+size 15293

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ecb0ca58db99f2e515f95ef361e3a5d323e06586f6cbdb868585a6fe08b033
+oid sha256:a5f46807250b5c695501899087945ede7c1e6a0a14e8498bf1b43eb8568a0de2
 size 5240