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 [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1469
+- Loss: 0.1466
 
 ## 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
@@ -56,11 +56,33 @@ The following hyperparameters were used during training:
 | 0.164         | 0.36  | 40   | 0.1546          |
 | 0.1511        | 0.45  | 50   | 0.1503          |
 | 0.1892        | 0.54  | 60   | 0.1511          |
-| 0.1598        | 0.63  | 70   | 0.1480          |
-| 0.1618        | 0.73  | 80   | 0.1511          |
-| 0.1434        | 0.82  | 90   | 0.1488          |
-| 0.1541        | 0.91  | 100  | 0.1474          |
-| 0.1569        | 1.0   | 110  | 0.1469          |
+| 0.1599        | 0.63  | 70   | 0.1479          |
+| 0.1619        | 0.73  | 80   | 0.1522          |
+| 0.1444        | 0.82  | 90   | 0.1492          |
+| 0.1531        | 0.91  | 100  | 0.1480          |
+| 0.1561        | 1.0   | 110  | 0.1506          |
+| 0.1445        | 1.09  | 120  | 0.1471          |
+| 0.1713        | 1.18  | 130  | 0.1497          |
+| 0.1559        | 1.27  | 140  | 0.1478          |
+| 0.1598        | 1.36  | 150  | 0.1466          |
+| 0.143         | 1.45  | 160  | 0.1484          |
+| 0.144         | 1.54  | 170  | 0.1462          |
+| 0.1456        | 1.63  | 180  | 0.1464          |
+| 0.1548        | 1.72  | 190  | 0.1495          |
+| 0.1586        | 1.81  | 200  | 0.1473          |
+| 0.1459        | 1.9   | 210  | 0.1471          |
+| 0.1447        | 1.99  | 220  | 0.1486          |
+| 0.1457        | 2.08  | 230  | 0.1464          |
+| 0.1667        | 2.18  | 240  | 0.1467          |
+| 0.1431        | 2.27  | 250  | 0.1466          |
+| 0.1444        | 2.36  | 260  | 0.1474          |
+| 0.1507        | 2.45  | 270  | 0.1473          |
+| 0.1514        | 2.54  | 280  | 0.1468          |
+| 0.1538        | 2.63  | 290  | 0.1470          |
+| 0.1443        | 2.72  | 300  | 0.1467          |
+| 0.1444        | 2.81  | 310  | 0.1467          |
+| 0.1641        | 2.9   | 320  | 0.1466          |
+| 0.1564        | 2.99  | 330  | 0.1466          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3314f3cf4c79b57cfeb24879832312048861adf577b0a429f1e773cd8990e514
+oid sha256:b00fe028b30594f25659add475af388924bf838c71ec2c1c2895cab6e06f1ce0
 size 2108942

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d748465bf361ece564e0c9a4037abd5e0164639d348e9ca39de9cd37d884033
+oid sha256:d316031f209c515f929c61387b1d039b1eb579fa7659129554827ae624acc535
 size 4709168176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07fa8f30930fe61200434a5770d4ec8b32762775a0ef329e1d05f01043d2918a
+oid sha256:764dcb60c0a057eba114892634be68479ba92409b0c44e60e070a63282f0d21e
 size 5112