End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1215
+- Loss: 0.1581
 
 ## Model description
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_steps: 20
-- num_epochs: 3
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -52,37 +52,15 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:----:|:---------------:|
 | 2.5643        | 0.09  | 10   | 2.3573          |
 | 2.1608        | 0.18  | 20   | 1.8527          |
-| 1.6246        | 0.27  | 30   | 1.2651          |
-| 1.1395        | 0.36  | 40   | 0.8357          |
-| 0.7126        | 0.45  | 50   | 0.3825          |
-| 0.3575        | 0.54  | 60   | 0.1921          |
-| 0.2196        | 0.63  | 70   | 0.1514          |
-| 0.181         | 0.73  | 80   | 0.1415          |
-| 0.1696        | 0.82  | 90   | 0.1371          |
-| 0.1653        | 0.91  | 100  | 0.1335          |
-| 0.1636        | 1.0   | 110  | 0.1309          |
-| 0.1508        | 1.09  | 120  | 0.1295          |
-| 0.1551        | 1.18  | 130  | 0.1285          |
-| 0.1516        | 1.27  | 140  | 0.1276          |
-| 0.1569        | 1.36  | 150  | 0.1266          |
-| 0.1464        | 1.45  | 160  | 0.1261          |
-| 0.1428        | 1.54  | 170  | 0.1258          |
-| 0.1502        | 1.63  | 180  | 0.1245          |
-| 0.1417        | 1.72  | 190  | 0.1242          |
-| 0.1392        | 1.81  | 200  | 0.1237          |
-| 0.1434        | 1.9   | 210  | 0.1231          |
-| 0.1433        | 1.99  | 220  | 0.1227          |
-| 0.1432        | 2.08  | 230  | 0.1225          |
-| 0.1397        | 2.18  | 240  | 0.1222          |
-| 0.1395        | 2.27  | 250  | 0.1220          |
-| 0.1415        | 2.36  | 260  | 0.1218          |
-| 0.1401        | 2.45  | 270  | 0.1215          |
-| 0.1372        | 2.54  | 280  | 0.1216          |
-| 0.1366        | 2.63  | 290  | 0.1215          |
-| 0.1405        | 2.72  | 300  | 0.1215          |
-| 0.1431        | 2.81  | 310  | 0.1213          |
-| 0.1384        | 2.9   | 320  | 0.1215          |
-| 0.1415        | 2.99  | 330  | 0.1215          |
+| 1.6271        | 0.27  | 30   | 1.2732          |
+| 1.1558        | 0.36  | 40   | 0.8683          |
+| 0.7761        | 0.45  | 50   | 0.5042          |
+| 0.4741        | 0.54  | 60   | 0.2558          |
+| 0.2937        | 0.63  | 70   | 0.1866          |
+| 0.2332        | 0.73  | 80   | 0.1681          |
+| 0.2203        | 0.82  | 90   | 0.1613          |
+| 0.2151        | 0.91  | 100  | 0.1585          |
+| 0.2205        | 1.0   | 110  | 0.1581          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1691b2dc086b243f7155de83e57af1a010f29458ff26c991b88027733713f22c
-size 19662074
+oid sha256:325df7d360197551530f014df5d7a6a8081d88dbc9e71b045a47608931db45b7
+size 176950922

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9092bcae3e3916a9e0d8a6ae56955603e6e1b7b1a2367bffa63369359bd4744d
+oid sha256:d58ac79adc23d7bd5059a587ba73179ff6b1a0e92622c916d1ee6dfd31c29b8d
 size 5716791816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4981b52d143c6c46f035d0ebb1644563cb2d43dedf0524971abb9fe48f0a5d5
+oid sha256:eba2dc94e9f8acd945898980e1cb41e15da5dfa604b8f25655292a6d289e26e2
 size 5112