Model save

README.md

@@ -2,14 +2,10 @@
 license: mit
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
 base_model: microsoft/phi-2
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: phi-2-gpo-test-iter-0
   results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-2-gpo-test-iter-0
 
-This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
 
 ## Model description
 

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "dense",
     "q_proj",
-    "v_proj"
+    "dense"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.7535,
+    "train_runtime": 3.7707,
     "train_samples": 30567,
-    "train_samples_per_second": 1.066,
-    "train_steps_per_second": 0.533
+    "train_samples_per_second": 1.061,
+    "train_steps_per_second": 0.53
 }

runs/Mar19_14-42-17_Braylon/events.out.tfevents.1710819791.Braylon.29513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0c6535a11a4900994c2281a7a9e397c83ebfdfc3b988773f8faf13d928c3a4
+size 5793

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.7535,
+    "train_runtime": 3.7707,
     "train_samples": 30567,
-    "train_samples_per_second": 1.066,
-    "train_steps_per_second": 0.533
+    "train_samples_per_second": 1.061,
+    "train_steps_per_second": 0.53
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 2.5006682335515507e-05,
-      "train_runtime": 3.7535,
-      "train_samples_per_second": 1.066,
-      "train_steps_per_second": 0.533
+      "train_runtime": 3.7707,
+      "train_samples_per_second": 1.061,
+      "train_steps_per_second": 0.53
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1d0f594fb782420a12c1aec1b64e6a2a2ec173e8915eb2dd9e4b4b3958eb09
+oid sha256:7c222e2966f72a6241aaf88fc33ed1efdf23812b915aeb40cde9e87f96f2f521
 size 5880