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": [
-    "dense",
-    "v_proj",
     "k_proj",
-    "q_proj"
+    "dense",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.7084,
+    "train_runtime": 3.6978,
     "train_samples": 30567,
-    "train_samples_per_second": 1.079,
-    "train_steps_per_second": 0.539
+    "train_samples_per_second": 1.082,
+    "train_steps_per_second": 0.541
 }

runs/Mar19_13-57-28_Braylon/events.out.tfevents.1710817110.Braylon.21041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6333c8ce35c9bd384771bd52e91e5f869e2d20fdcbbb9e8035ae418c5d17bd
+size 5793

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.7084,
+    "train_runtime": 3.6978,
     "train_samples": 30567,
-    "train_samples_per_second": 1.079,
-    "train_steps_per_second": 0.539
+    "train_samples_per_second": 1.082,
+    "train_steps_per_second": 0.541
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 2.5006682335515507e-05,
-      "train_runtime": 3.7084,
-      "train_samples_per_second": 1.079,
-      "train_steps_per_second": 0.539
+      "train_runtime": 3.6978,
+      "train_samples_per_second": 1.082,
+      "train_steps_per_second": 0.541
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44abf6bddfd5d7836f37390e3afbc197b8b3e255d4d6f11b5503a993162c912c
-size 5816
+oid sha256:b76b89590b4283663f6123b2fae64b633e0a190e3c061cbd5f383c145e8974e5
+size 5880