defsound/llama38binstruct-summary-100s

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8079
+- Loss: 1.7359
 
 ## Model description
 
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.0954        | 1.1364 | 25   | 1.6426          |
-| 0.0512        | 2.2727 | 50   | 1.6826          |
-| 0.042         | 3.4091 | 75   | 1.6778          |
-| 0.0269        | 4.5455 | 100  | 1.8079          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.3102        | 1.25  | 25   | 1.3008          |
+| 0.4803        | 2.5   | 50   | 1.5715          |
+| 0.1848        | 3.75  | 75   | 1.6767          |
+| 0.0972        | 5.0   | 100  | 1.7359          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
+    "up_proj",
     "q_proj",
+    "gate_proj",
     "o_proj",
     "down_proj",
-    "up_proj",
-    "k_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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:334c48c53e003f8f47ab82364d74c20c07682efd7bdef27f754dcf15786e619c
+size 167832240

runs/Jun14_17-23-34_1f55961ed06e/events.out.tfevents.1718385820.1f55961ed06e.34529.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828e1d3e0442d0b528843bb0eb232b8dc5b3d42b4205ec5dc1fe6b14ccf3dcf2
+size 9238

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:febda76e87cae2b92ab30a7ace4093fc8b8bd511f7d57b7d0c66ffe134fb0258
+oid sha256:8dc211a0b31c79fd05c341c6ca9921715b8b68d44b75409aac1ec8d72d67a257
 size 5368