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 [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1474
+- Loss: 0.1184
 
 ## 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: 60
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -51,16 +51,38 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
 | 2.238         | 0.09  | 10   | 1.8587          |
-| 1.7567        | 0.18  | 20   | 1.5411          |
-| 1.2688        | 0.27  | 30   | 0.8329          |
-| 0.5198        | 0.36  | 40   | 0.2499          |
-| 0.1877        | 0.45  | 50   | 0.1580          |
-| 0.1639        | 0.54  | 60   | 0.1526          |
-| 0.1475        | 0.63  | 70   | 0.1475          |
+| 1.7567        | 0.18  | 20   | 1.5410          |
+| 1.2688        | 0.27  | 30   | 0.8328          |
+| 0.52          | 0.36  | 40   | 0.2500          |
+| 0.1873        | 0.45  | 50   | 0.1579          |
+| 0.1639        | 0.54  | 60   | 0.1524          |
+| 0.1473        | 0.63  | 70   | 0.1475          |
 | 0.1626        | 0.73  | 80   | 0.1470          |
-| 0.1406        | 0.82  | 90   | 0.1481          |
-| 0.1536        | 0.91  | 100  | 0.1477          |
-| 0.1551        | 1.0   | 110  | 0.1474          |
+| 0.1408        | 0.82  | 90   | 0.1486          |
+| 0.1533        | 0.91  | 100  | 0.1471          |
+| 0.1552        | 1.0   | 110  | 0.1467          |
+| 0.1413        | 1.09  | 120  | 0.1467          |
+| 0.1674        | 1.18  | 130  | 0.1451          |
+| 0.1393        | 1.27  | 140  | 0.1416          |
+| 0.1528        | 1.36  | 150  | 0.1378          |
+| 0.1332        | 1.45  | 160  | 0.1366          |
+| 0.1323        | 1.54  | 170  | 0.1349          |
+| 0.1313        | 1.63  | 180  | 0.1329          |
+| 0.1418        | 1.72  | 190  | 0.1308          |
+| 0.1385        | 1.81  | 200  | 0.1281          |
+| 0.1316        | 1.9   | 210  | 0.1258          |
+| 0.1264        | 1.99  | 220  | 0.1262          |
+| 0.1228        | 2.08  | 230  | 0.1231          |
+| 0.1478        | 2.18  | 240  | 0.1223          |
+| 0.1188        | 2.27  | 250  | 0.1213          |
+| 0.1212        | 2.36  | 260  | 0.1210          |
+| 0.1242        | 2.45  | 270  | 0.1212          |
+| 0.1216        | 2.54  | 280  | 0.1201          |
+| 0.1234        | 2.63  | 290  | 0.1192          |
+| 0.1146        | 2.72  | 300  | 0.1186          |
+| 0.1167        | 2.81  | 310  | 0.1184          |
+| 0.1337        | 2.9   | 320  | 0.1184          |
+| 0.1276        | 2.99  | 330  | 0.1184          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855559f62eeeb569368897d7c355fb85fb9fbce1a2bf059dd3d5505c2dc2fa3d
+oid sha256:f770babf4e9ef607fd2e9a90d4f70fafafbf57cd6dadeddea2f04d48b17b18e5
 size 3712454

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5240c481e558ce405f7675528dade66e337817981c7bb8bf4e594113eda16d4
+oid sha256:86b70622f922359f82104a1fd30628f5dd6e3393245999d0ff5637ecad711ccd
 size 10028407656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7231fad177aff949de821abb7ad5ac9e0240249867db0666aa0a8a3830771b63
+oid sha256:8302f1121d7a20ea54948abc2ccb320a0341e410bcc51a5a0872f087bc98e1bd
 size 5112