ItchyChin/llama-merge-all-lang-outputs

README.md

@@ -18,18 +18,18 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3713
-- Rewards/chosen: -0.0313
-- Rewards/rejected: -0.9473
+- Loss: 0.1433
+- Rewards/chosen: -0.0156
+- Rewards/rejected: -1.1268
 - Rewards/accuracies: 1.0
-- Rewards/margins: 0.9160
-- Logps/rejected: -9.4728
-- Logps/chosen: -0.3131
-- Logits/rejected: -0.1560
-- Logits/chosen: 0.4722
-- Nll Loss: 0.3713
-- Log Odds Ratio: -0.0001
-- Log Odds Chosen: 10.7603
+- Rewards/margins: 1.1112
+- Logps/rejected: -11.2681
+- Logps/chosen: -0.1556
+- Logits/rejected: -0.2138
+- Logits/chosen: 0.6631
+- Nll Loss: 0.1433
+- Log Odds Ratio: -0.0000
+- Log Odds Chosen: 13.2065
 
 ## Model description
 
@@ -61,7 +61,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
 |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
-| 0.4339        | 0.5000 | 6564 | 0.3713          | -0.0313        | -0.9473          | 1.0                | 0.9160          | -9.4728        | -0.3131      | -0.1560         | 0.4722        | 0.3713   | -0.0001        | 10.7603         |
+| 0.1869        | 0.5001 | 2175 | 0.1433          | -0.0156        | -1.1268          | 1.0                | 1.1112          | -11.2681       | -0.1556      | -0.2138         | 0.6631        | 0.1433   | -0.0000        | 13.2065         |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "v_proj",
     "gate_proj",
+    "o_proj",
     "k_proj",
     "q_proj",
-    "o_proj",
-    "up_proj",
-    "v_proj"
+    "down_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41721a093a35ae3768769c502747fc0e9881238b300937c5b13114573381733a
+oid sha256:cd5a4258006edcfcc86ddfb63de47f9d18467f4db28e6ffc626b5a633dcc4c3e
 size 4370592096

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b789f7b50ba4af079916eff1bbe6eb55a79f6f52171c230f65713f9295d8bc
+oid sha256:5fd433c7578b52ac26fa9f7e0aad02a6669b1a049f8ad43e6ac2c6fb78cc323e
 size 5368