stlee9048/HMGICS_SETBOX

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6224
+- Loss: nan
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.6187        | 10.0  | 10   | 3.2202          |
-| 1.2119        | 20.0  | 20   | 3.0447          |
-| 0.008         | 30.0  | 30   | 3.1600          |
-| 0.0           | 40.0  | 40   | 3.7623          |
-| 0.0           | 50.0  | 50   | 4.2872          |
-| 0.0           | 60.0  | 60   | 4.5001          |
-| 0.0           | 70.0  | 70   | 4.6249          |
-| 0.0           | 80.0  | 80   | 4.5756          |
-| 0.0           | 90.0  | 90   | 4.7558          |
-| 0.0           | 100.0 | 100  | 4.6224          |
+| 0.0           | 10.0  | 10   | nan             |
+| 0.0           | 20.0  | 20   | nan             |
+| 0.0           | 30.0  | 30   | nan             |
+| 0.0           | 40.0  | 40   | nan             |
+| 0.0           | 50.0  | 50   | nan             |
+| 0.0           | 60.0  | 60   | nan             |
+| 0.0           | 70.0  | 70   | nan             |
+| 0.0           | 80.0  | 80   | nan             |
+| 0.0           | 90.0  | 90   | nan             |
+| 0.0           | 100.0 | 100  | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
     "k_proj",
     "down_proj",
-    "gate_proj",
-    "q_proj",
-    "o_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:b2f19c4e749969a72cec6fe00d0808d698b17a9ab583b47c9839d0b136699184
+oid sha256:3ad398dd72d0426402c8b17fd6e2d1daf82f2c49197bcde73c74b4eef55066d2
 size 167832240

runs/Nov22_12-45-35_2300022N01/events.out.tfevents.1732250744.2300022N01.50084.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5583854dfc9ee128583cca3570c49101a9c74ea44885888d4e9c7ad3ab349d
+size 29420

runs/Nov22_13-37-52_2300022N01/events.out.tfevents.1732253880.2300022N01.26744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42122d2ce43a2c03067867b7b91148d6d5e63c697937618b47842dc067cacc6
+size 29420

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640c0fbd64d131bd5eac7f9eb69274dabfc307c39fcf83a04f9b59c315945ca9
+oid sha256:33545fca7b92443663e6d3c0d479ffaa7ec030116e205ec2b596424ebb3ffad3
 size 5304