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: 3.3878
+- Loss: 7.3704
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 5.1326        | 7.2727  | 10   | 3.1947          |
-| 3.6512        | 14.5455 | 20   | 2.7407          |
-| 2.442         | 21.8182 | 30   | 1.8273          |
-| 0.795         | 29.0909 | 40   | 1.9012          |
-| 0.0041        | 36.3636 | 50   | 3.3044          |
-| 0.0005        | 43.6364 | 60   | 3.5940          |
-| 0.0251        | 50.9091 | 70   | 3.1454          |
-| 0.062         | 58.1818 | 80   | 3.3136          |
-| 0.0006        | 65.4545 | 90   | 3.1543          |
-| 0.0001        | 72.7273 | 100  | 3.3878          |
+| 3.1821        | 4.4444  | 10   | 3.6998          |
+| 2.6754        | 8.8889  | 20   | 3.4513          |
+| 3.8983        | 13.3333 | 30   | 3.2089          |
+| 1.4461        | 17.7778 | 40   | 3.4964          |
+| 0.5732        | 22.2222 | 50   | 4.5111          |
+| 0.0226        | 26.6667 | 60   | 6.9400          |
+| 0.0818        | 31.1111 | 70   | 7.3203          |
+| 0.0024        | 35.5556 | 80   | 6.2920          |
+| 0.0026        | 40.0    | 90   | 6.9197          |
+| 0.0004        | 44.4444 | 100  | 7.3704          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
     "gate_proj",
     "q_proj",
-    "v_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
     "up_proj",
-    "k_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:efe4c2c81eea88e93f5d33ff80490fb8c78bb74ae69b52022c5376b849bc18d8
+oid sha256:cea206e86cf353a3267db61b0ddd2239ade1556ee00451b33ad5e71d7a29ecc0
 size 167832240

runs/Nov21_15-00-00_2300022N01/events.out.tfevents.1732172769.2300022N01.35984.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4cd7394b048723daf924f85924bf91e94021a050e703b08f8d848fcfd83014d
+size 29420

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
-size 17209961
+oid sha256:42245018febb197f678c617aa628114f94db7080a6d3eb5304197fdf74ff30f3
+size 17210060

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8247c3fd040f626a94f6d7e2add05eb08c6245a0df622d9b00347ee0f4b064
+oid sha256:0e4746c60d647ac555df1869f31c67159fe896e9ad303abeac865b068d0e5951
 size 5304