Model save

README.md

@@ -2,10 +2,7 @@
 license: mit
 base_model: microsoft/Phi-3-small-8k-instruct
 tags:
-- alignment-handbook
 - generated_from_trainer
-datasets:
-- AmberYifan/spin-v
 model-index:
 - name: phi3-spin-zephyr-data
   results: []
@@ -16,15 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi3-spin-zephyr-data
 
-This model is a fine-tuned version of [microsoft/Phi-3-small-8k-instruct](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) on the AmberYifan/spin-v dataset.
+This model is a fine-tuned version of [microsoft/Phi-3-small-8k-instruct](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1748
-- Rewards/real: -6.0641
-- Rewards/generated: -21.7894
-- Rewards/accuracies: 0.9443
-- Rewards/margins: 15.7252
-- Logps/generated: -509.3286
-- Logps/real: -313.0280
+- Loss: 0.1643
+- Rewards/real: -4.3165
+- Rewards/generated: -36.8197
+- Rewards/accuracies: 0.9626
+- Rewards/margins: 32.5032
+- Logps/generated: -659.6320
+- Logps/real: -295.5523
 - Logits/generated: -inf
 - Logits/real: -inf
 
@@ -62,7 +59,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
 |:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
-| 0.2945        | 0.64  | 500  | 0.1748          | -6.0641      | -21.7894          | 0.9443             | 15.7252         | -509.3286       | -313.0280  | -inf             | -inf        |
+| 0.3303        | 0.32  | 500  | 0.2003          | -4.8459      | -23.8426          | 0.9371             | 18.9967         | -529.8613       | -300.8461  | -inf             | -inf        |
+| 0.0933        | 0.64  | 1000 | 0.1598          | -4.6590      | -34.8525          | 0.9610             | 30.1935         | -639.9600       | -298.9768  | -inf             | -inf        |
+| 0.2065        | 0.96  | 1500 | 0.1643          | -4.3165      | -36.8197          | 0.9626             | 32.5032         | -659.6320       | -295.5523  | -inf             | -inf        |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6284351689954493,
-    "train_runtime": 6560.8804,
-    "train_samples": 25000,
-    "train_samples_per_second": 3.81,
-    "train_steps_per_second": 0.119
+    "train_loss": 0.42768371397759275,
+    "train_runtime": 16836.7545,
+    "train_samples": 50000,
+    "train_samples_per_second": 2.97,
+    "train_steps_per_second": 0.093
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efa10e64d5859b0237937a454e8d0e674af6517f71086f2e7e98bc3147fe71c
+oid sha256:4d2f34344b3f845374bd0eacb6371b7d83544a4d2c0d700d41c79a9b8acbd813
 size 4832943104

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac4af61d8a50b24b2a0451b0d0d8d681f445298adb99946728417f8ea8a5f8c
+oid sha256:3b406d4b4abb0ab8def821820a778510ec2101601576296a3500370984f1c0d5
 size 4799608224

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cbc2426e9fb18df7c282f39a9fd4f5523abf48457b84c80ecdc7b84bf172b63
+oid sha256:5a3142a41839ca7e6a4a8f5041514b14710370172619404fd630af6b94ec3d13
 size 4799608240

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856cab213b70e9a43d567a410c8964012fdc3434091381c99187734430660556
+oid sha256:292b1c6b6cc1e92b4e0a1e1aadc9d4c222af8ecdba677dda2afadc990b1fd700
 size 352437304

runs/Jul25_17-12-28_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1721942132.gilbreth-j001.rcac.purdue.edu.261418.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7673a7b5503af583322470d0c20eb639908de807333f372de69385802bdafef
-size 104161
+oid sha256:949793e977ea7ce2d23b7191162eb29e29eeca5e82e56df05a20a5d165328401
+size 108301

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6284351689954493,
-    "train_runtime": 6560.8804,
-    "train_samples": 25000,
-    "train_samples_per_second": 3.81,
-    "train_steps_per_second": 0.119
+    "train_loss": 0.42768371397759275,
+    "train_runtime": 16836.7545,
+    "train_samples": 50000,
+    "train_samples_per_second": 2.97,
+    "train_steps_per_second": 0.093
 }