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: 0.1488
+- Loss: 0.1291
 
 ## Model description
 
@@ -43,24 +43,46 @@ 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
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.2512        | 0.09  | 10   | 1.9189          |
-| 1.9251        | 0.18  | 20   | 1.9020          |
-| 1.8763        | 0.27  | 30   | 1.7975          |
-| 1.7047        | 0.36  | 40   | 1.5334          |
-| 1.3481        | 0.45  | 50   | 1.0845          |
-| 0.903         | 0.54  | 60   | 0.4961          |
-| 0.3472        | 0.63  | 70   | 0.2086          |
-| 0.1915        | 0.73  | 80   | 0.1576          |
-| 0.1476        | 0.82  | 90   | 0.1530          |
-| 0.1554        | 0.91  | 100  | 0.1492          |
-| 0.1582        | 1.0   | 110  | 0.1488          |
+| 2.2513        | 0.09  | 10   | 1.9189          |
+| 1.9252        | 0.18  | 20   | 1.9019          |
+| 1.8761        | 0.27  | 30   | 1.7972          |
+| 1.7045        | 0.36  | 40   | 1.5332          |
+| 1.348         | 0.45  | 50   | 1.0846          |
+| 0.9036        | 0.54  | 60   | 0.4970          |
+| 0.3466        | 0.63  | 70   | 0.2054          |
+| 0.1888        | 0.73  | 80   | 0.1562          |
+| 0.1458        | 0.82  | 90   | 0.1490          |
+| 0.1531        | 0.91  | 100  | 0.1478          |
+| 0.1561        | 1.0   | 110  | 0.1477          |
+| 0.142         | 1.09  | 120  | 0.1474          |
+| 0.1687        | 1.18  | 130  | 0.1463          |
+| 0.1426        | 1.27  | 140  | 0.1451          |
+| 0.1577        | 1.36  | 150  | 0.1434          |
+| 0.1386        | 1.45  | 160  | 0.1419          |
+| 0.136         | 1.54  | 170  | 0.1397          |
+| 0.135         | 1.63  | 180  | 0.1385          |
+| 0.1489        | 1.72  | 190  | 0.1377          |
+| 0.146         | 1.81  | 200  | 0.1349          |
+| 0.1367        | 1.9   | 210  | 0.1340          |
+| 0.1347        | 1.99  | 220  | 0.1338          |
+| 0.1317        | 2.08  | 230  | 0.1318          |
+| 0.1554        | 2.18  | 240  | 0.1309          |
+| 0.1285        | 2.27  | 250  | 0.1308          |
+| 0.1328        | 2.36  | 260  | 0.1310          |
+| 0.1354        | 2.45  | 270  | 0.1305          |
+| 0.1324        | 2.54  | 280  | 0.1301          |
+| 0.1362        | 2.63  | 290  | 0.1297          |
+| 0.1257        | 2.72  | 300  | 0.1293          |
+| 0.1274        | 2.81  | 310  | 0.1291          |
+| 0.1472        | 2.9   | 320  | 0.1291          |
+| 0.1405        | 2.99  | 330  | 0.1291          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40fda2a319f933566ba1593015ee7e536b6ce2abfd4a60524acd9c30f46ae5d2
+oid sha256:ee30b78400056d8af3b957f7a0b61752bfe446a18e2e3207a87d7e86272170fb
 size 29712986

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c50a5392796b194b35873fb0eebe36bb720da9115155922bb88b26c9c8412af
+oid sha256:bdc9abe000350eb349b01f61c82c3d886a42ae40c4159e0743691861611c7479
 size 10054288712

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea142492aa8133699d6586dc85bd072c25bea25ddcbb3c6fef1eb1fe3209626
+oid sha256:ef9f096df3cd030ee0a7d3bc0128100280109ac15716f20c2e1966de21c9c042
 size 5112