gemma_2b_oasst1_reward_model

README.md

@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4250
-- Accuracy: 0.7881
+- Loss: 0.4345
+- Accuracy: 0.8051
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.443         | 1.0   | 100  | 0.5045          | 0.7458   |
-| 0.4098        | 2.0   | 200  | 0.4312          | 0.7938   |
-| 0.5036        | 2.99  | 300  | 0.4250          | 0.7881   |
+| 0.5106        | 1.0   | 100  | 0.5843          | 0.7203   |
+| 0.4299        | 2.0   | 200  | 0.4418          | 0.7825   |
+| 0.5035        | 2.99  | 300  | 0.4345          | 0.8051   |
 
 
 ### Framework versions

adapter_config.json

@@ -13,16 +13,14 @@
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "score"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbbe5c5a3cbdef631341ec6ca752168bcbfb155d7263b87eda0c2a0de80bc47
+oid sha256:1205a50454ca4ff96b48f390603c27297d03af0968627f322716ec074ecc9663
 size 7390624