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

@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "dense",
     "v_proj",
-    "k_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM"

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.6518,
+    "train_runtime": 3.8632,
     "train_samples": 30567,
-    "train_samples_per_second": 1.095,
-    "train_steps_per_second": 0.548
+    "train_samples_per_second": 1.035,
+    "train_steps_per_second": 0.518
 }

runs/Mar19_15-20-44_Braylon/events.out.tfevents.1710822106.Braylon.5910.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940fa46460efe5abf9243054188485be32b689d1b7b3c83f22b49f50ab57bbb0
+size 5793

runs/Mar19_15-29-24_Braylon/events.out.tfevents.1710822629.Braylon.7846.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea209e0cc553f00dff670e131d0847b4c0932f4d4de810d76b3fa23d8cb8ef3
+size 5793

runs/Mar19_15-36-01_Braylon/events.out.tfevents.1710823013.Braylon.8956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd95d92d96bd3ca3bc694a017e4d17a2f283c74a575a97c3f1bbb8d9ecaadb1
+size 5793

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.6518,
+    "train_runtime": 3.8632,
     "train_samples": 30567,
-    "train_samples_per_second": 1.095,
-    "train_steps_per_second": 0.548
+    "train_samples_per_second": 1.035,
+    "train_steps_per_second": 0.518
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 2.5006682335515507e-05,
-      "train_runtime": 3.6518,
-      "train_samples_per_second": 1.095,
-      "train_steps_per_second": 0.548
+      "train_runtime": 3.8632,
+      "train_samples_per_second": 1.035,
+      "train_steps_per_second": 0.518
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f93ed8083c90193aad25b1d03bfb42a33c9e715fb8e775056b6ba46679aab4e8
+oid sha256:2bea30d2328fa268e48dfefdedb4ad633adb32f734195805087cb25fee78fe2d
 size 5880