Model save

README.md

@@ -17,19 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
 # orpo-phi3
 
 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 4.4137
-- Rewards/chosen: -0.4068
-- Rewards/rejected: -0.4068
-- Rewards/accuracies: 0.0
-- Rewards/margins: 0.0
-- Logps/rejected: -4.0684
-- Logps/chosen: -4.0684
-- Logits/rejected: 22.3128
-- Logits/chosen: 22.3128
-- Nll Loss: 4.3444
-- Log Odds Ratio: -0.6931
-- Log Odds Chosen: 0.0
 
 ## Model description
 
@@ -59,17 +46,10 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 10
 - num_epochs: 1
 
-### Training results
-
-| 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 |
-|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
-| 4.1766        | 0.8   | 1    | 4.4137          | -0.4068        | -0.4068          | 0.0                | 0.0             | -4.0684        | -4.0684      | 22.3128         | 22.3128       | 4.3444   | -0.6931        | 0.0             |
-
-
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.41.2
-- Pytorch 2.3.0+cu121
+- Transformers 4.42.3
+- Pytorch 2.1.2
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
     "o_proj",
+    "gate_up_proj",
     "qkv_proj",
     "down_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a595c549d8d93ddaccc29e80a93b2a02720016cf695a50c46ea2f82f673459
+oid sha256:fd0f5bb1237bf549fa73ac2c283393d35d064f7c3c8ca6170b9632bc644ce2cd
 size 887450008

runs/Jul15_06-59-30_08422e6f1a8e/events.out.tfevents.1721026772.08422e6f1a8e.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0e7088509cb81f021f4876412413687e9d5decfce922f492bd0ea27843a8f5
+size 19541

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": false,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996082b3e31474d0f885e97d42c2162e4ad600cfee32e088aa509e8dfebdd7ac
+oid sha256:8a168b42dff42511590c6f2518b832bc993667bc81459de5d369f89df13b5f8d
 size 5432