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_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9934804bce5e2fbca6820593fa6db937d8f1a0e24233f993236a18d8ce6acfbb
+oid sha256:c99237b61ddbcc12b02ca16d9318ff7a9125e77add338ae7faccac130d33f3ad
 size 41977616

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.33,
-    "train_loss": 0.0029907251009717584,
-    "train_runtime": 8.1822,
+    "epoch": 2.0,
+    "train_loss": 0.0011036931537091732,
+    "train_runtime": 3.0822,
     "train_samples": 30567,
-    "train_samples_per_second": 2.2,
-    "train_steps_per_second": 0.244
+    "train_samples_per_second": 0.649,
+    "train_steps_per_second": 0.649
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.33,
-    "train_loss": 0.0029907251009717584,
-    "train_runtime": 8.1822,
+    "epoch": 2.0,
+    "train_loss": 0.0011036931537091732,
+    "train_runtime": 3.0822,
     "train_samples": 30567,
-    "train_samples_per_second": 2.2,
-    "train_steps_per_second": 0.244
+    "train_samples_per_second": 0.649,
+    "train_steps_per_second": 0.649
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3333333333333333,
+  "epoch": 2.0,
   "eval_steps": 100,
   "global_step": 2,
   "is_hyper_param_search": false,
@@ -11,11 +11,11 @@
     {
       "epoch": 1.0,
       "learning_rate": 5e-06,
-      "logits/chosen": 1.010143756866455,
-      "logits/rejected": 0.6943762302398682,
-      "logps/chosen": -162.5532989501953,
-      "logps/rejected": -165.59518432617188,
-      "loss": 0.0045,
+      "logits/chosen": 0.785413920879364,
+      "logits/rejected": 0.9495257139205933,
+      "logps/chosen": -93.63787078857422,
+      "logps/rejected": -77.81773376464844,
+      "loss": 0.0011,
       "rewards/accuracies": 0.0,
       "rewards/chosen": 0.0,
       "rewards/margins": 0.0,
@@ -23,13 +23,13 @@
       "step": 1
     },
     {
-      "epoch": 1.33,
+      "epoch": 2.0,
       "step": 2,
       "total_flos": 0.0,
-      "train_loss": 0.0029907251009717584,
-      "train_runtime": 8.1822,
-      "train_samples_per_second": 2.2,
-      "train_steps_per_second": 0.244
+      "train_loss": 0.0011036931537091732,
+      "train_runtime": 3.0822,
+      "train_samples_per_second": 0.649,
+      "train_steps_per_second": 0.649
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b0c0e98c2107e656523ce58ba178549db02437fab37205bc665050802862a9
+oid sha256:22abc2e60df559c1c10cf59282f459875a7647c8d066a3c469953dc85674676a
 size 5880