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-longest-iter-0
   results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-2-gpo-test-longest-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": [
-    "k_proj",
-    "dense",
     "v_proj",
-    "q_proj"
+    "dense",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.33,
     "train_loss": 0.0029907251009717584,
-    "train_runtime": 7.8342,
+    "train_runtime": 7.9772,
     "train_samples": 30567,
-    "train_samples_per_second": 2.298,
-    "train_steps_per_second": 0.255
+    "train_samples_per_second": 2.256,
+    "train_steps_per_second": 0.251
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.33,
     "train_loss": 0.0029907251009717584,
-    "train_runtime": 7.8342,
+    "train_runtime": 7.9772,
     "train_samples": 30567,
-    "train_samples_per_second": 2.298,
-    "train_steps_per_second": 0.255
+    "train_samples_per_second": 2.256,
+    "train_steps_per_second": 0.251
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 0.0029907251009717584,
-      "train_runtime": 7.8342,
-      "train_samples_per_second": 2.298,
-      "train_steps_per_second": 0.255
+      "train_runtime": 7.9772,
+      "train_samples_per_second": 2.256,
+      "train_steps_per_second": 0.251
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449526b1bd55c3cb5562c5e59a35ea23bb7fbed4e24e9d5ed04317c66dad3cef
+oid sha256:c9d5fba5aa2d52c5c13aca2a85588c7109f576c68ce8d7649266dff2bfdf5fbd
 size 5880