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

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "dense",
+    "k_proj",
     "v_proj",
-    "k_proj"
+    "dense"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 0.00012263256940059364,
-    "train_runtime": 3.8629,
+    "train_runtime": 3.7437,
     "train_samples": 30567,
-    "train_samples_per_second": 2.071,
-    "train_steps_per_second": 0.518
+    "train_samples_per_second": 2.137,
+    "train_steps_per_second": 0.534
 }

runs/Mar20_15-12-38_Braylon/events.out.tfevents.1710908018.Braylon.19468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645774e1d72fb68a948b46a67ff88368da4ec5765642049fdadfc97e2f75b1c4
+size 5781

runs/Mar20_15-21-50_Braylon/events.out.tfevents.1710908570.Braylon.20841.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379ae1f9190a5ef337bdc71b3bb86d89d8d65a263278e0f09d0451edd43e9611
+size 5781

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 0.00012263256940059364,
-    "train_runtime": 3.8629,
+    "train_runtime": 3.7437,
     "train_samples": 30567,
-    "train_samples_per_second": 2.071,
-    "train_steps_per_second": 0.518
+    "train_samples_per_second": 2.137,
+    "train_steps_per_second": 0.534
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 0.00012263256940059364,
-      "train_runtime": 3.8629,
-      "train_samples_per_second": 2.071,
-      "train_steps_per_second": 0.518
+      "train_runtime": 3.7437,
+      "train_samples_per_second": 2.137,
+      "train_steps_per_second": 0.534
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fca69eac0262d902ba424d982cb3ba424dccecdb6630d61a9ba966634160653
+oid sha256:847f533bc89f9d338b1ac8582481af2541de0a6ac0653e2f20034922c526abf7
 size 5816