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: 0.1477
+- Loss: 0.1472
 
 ## 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:
 | 1.5052        | 0.36  | 40   | 0.9945          |
 | 0.6052        | 0.45  | 50   | 0.2390          |
 | 0.2304        | 0.54  | 60   | 0.1544          |
-| 0.1665        | 0.63  | 70   | 0.1505          |
-| 0.163         | 0.73  | 80   | 0.1519          |
-| 0.1445        | 0.82  | 90   | 0.1508          |
-| 0.1542        | 0.91  | 100  | 0.1477          |
-| 0.158         | 1.0   | 110  | 0.1477          |
+| 0.1666        | 0.63  | 70   | 0.1506          |
+| 0.1633        | 0.73  | 80   | 0.1514          |
+| 0.1444        | 0.82  | 90   | 0.1481          |
+| 0.1551        | 0.91  | 100  | 0.1476          |
+| 0.1575        | 1.0   | 110  | 0.1517          |
+| 0.1455        | 1.09  | 120  | 0.1483          |
+| 0.1724        | 1.18  | 130  | 0.1493          |
+| 0.1558        | 1.27  | 140  | 0.1484          |
+| 0.1604        | 1.36  | 150  | 0.1473          |
+| 0.1432        | 1.45  | 160  | 0.1488          |
+| 0.1446        | 1.54  | 170  | 0.1467          |
+| 0.1463        | 1.63  | 180  | 0.1470          |
+| 0.1554        | 1.72  | 190  | 0.1506          |
+| 0.1595        | 1.81  | 200  | 0.1480          |
+| 0.1462        | 1.9   | 210  | 0.1475          |
+| 0.1449        | 1.99  | 220  | 0.1494          |
+| 0.1464        | 2.08  | 230  | 0.1473          |
+| 0.1671        | 2.18  | 240  | 0.1473          |
+| 0.1437        | 2.27  | 250  | 0.1472          |
+| 0.1448        | 2.36  | 260  | 0.1478          |
+| 0.1508        | 2.45  | 270  | 0.1477          |
+| 0.152         | 2.54  | 280  | 0.1475          |
+| 0.1547        | 2.63  | 290  | 0.1476          |
+| 0.1447        | 2.72  | 300  | 0.1474          |
+| 0.1448        | 2.81  | 310  | 0.1472          |
+| 0.1646        | 2.9   | 320  | 0.1472          |
+| 0.1567        | 2.99  | 330  | 0.1472          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d971dcdbdde12f39542e688e73ebcd8d3781108356d8c948a7f78c7f118bdd85
+oid sha256:329b1b08b27c1ec1d939c796cdc755b50b97cc391878225f6f06e7d06bf4a05a
 size 16876874

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f6f970f415c5e170be2f319750aa9c461b83613e56ff385584509f00bf4e44
+oid sha256:c7f1bc1e663ee8f06160aebbda8749f9eb143e26bd8b3169e5d96997efdd5756
 size 4723882944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8264817482c3dd630db2758e3883b886893925c778041b46514c91d0ffc22c8d
+oid sha256:8d4a72c31beb152583a99a2eb14de3c74402c6810bb1006b1c38d9426ac36985
 size 5112