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",
+    "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": 3.847,
+    "train_runtime": 3.7537,
     "train_samples": 30567,
-    "train_samples_per_second": 1.04,
-    "train_steps_per_second": 0.52
+    "train_samples_per_second": 1.066,
+    "train_steps_per_second": 0.533
 }

runs/Mar19_14-21-21_Braylon/events.out.tfevents.1710818544.Braylon.25528.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea2cd333f115200af440f7fbea0e6a856f19e25ef0ad0bf9d16632fbaa29150
+size 5793

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.847,
+    "train_runtime": 3.7537,
     "train_samples": 30567,
-    "train_samples_per_second": 1.04,
-    "train_steps_per_second": 0.52
+    "train_samples_per_second": 1.066,
+    "train_steps_per_second": 0.533
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 2.5006682335515507e-05,
-      "train_runtime": 3.847,
-      "train_samples_per_second": 1.04,
-      "train_steps_per_second": 0.52
+      "train_runtime": 3.7537,
+      "train_samples_per_second": 1.066,
+      "train_steps_per_second": 0.533
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf62b93288a194f7d4d2dfd4aaf12ca439e2e1603ae3d1a2895510d43a52f6c
+oid sha256:218ae2b9e2109310749c64a5c1a5cf80f14386bd0fe5ee2f0333e4d214c438e7
 size 5880