ninagroot/GPT2-705Mtest

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3957
+- Loss: 3.3670
 
 ## Model description
 
@@ -48,26 +48,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 6.8482        | 1.0   | 3    | 6.7767          |
-| 6.6139        | 2.0   | 6    | 6.7200          |
-| 6.1004        | 3.0   | 9    | 5.9262          |
-| 5.3501        | 4.0   | 12   | 5.3733          |
-| 4.8747        | 5.0   | 15   | 5.3984          |
-| 4.6359        | 6.0   | 18   | 5.0054          |
-| 4.3812        | 7.0   | 21   | 4.7312          |
-| 4.6025        | 8.0   | 24   | 4.5374          |
-| 4.2898        | 9.0   | 27   | 4.3775          |
-| 4.0776        | 10.0  | 30   | 4.1677          |
-| 3.7065        | 11.0  | 33   | 3.9331          |
-| 3.6237        | 12.0  | 36   | 3.9337          |
-| 3.291         | 13.0  | 39   | 3.6885          |
-| 3.3561        | 14.0  | 42   | 3.6150          |
-| 3.0743        | 15.0  | 45   | 3.5141          |
-| 2.9327        | 16.0  | 48   | 3.5830          |
-| 2.8184        | 17.0  | 51   | 3.5404          |
-| 2.6606        | 18.0  | 54   | 3.4424          |
-| 2.5535        | 19.0  | 57   | 3.4270          |
-| 2.6434        | 20.0  | 60   | 3.3957          |
+| 7.1756        | 1.0   | 3    | 6.9042          |
+| 6.1675        | 2.0   | 6    | 6.3449          |
+| 5.7804        | 3.0   | 9    | 6.3931          |
+| 5.2494        | 4.0   | 12   | 5.4048          |
+| 6.6975        | 5.0   | 15   | 5.1851          |
+| 4.6238        | 6.0   | 18   | 4.8536          |
+| 4.2481        | 7.0   | 21   | 4.5554          |
+| 4.3098        | 8.0   | 24   | 4.4614          |
+| 4.2767        | 9.0   | 27   | 4.3181          |
+| 3.8758        | 10.0  | 30   | 4.0861          |
+| 3.6487        | 11.0  | 33   | 4.0584          |
+| 3.5787        | 12.0  | 36   | 4.0018          |
+| 3.2524        | 13.0  | 39   | 3.6528          |
+| 3.3737        | 14.0  | 42   | 3.5917          |
+| 2.9767        | 15.0  | 45   | 3.5833          |
+| 2.8963        | 16.0  | 48   | 3.4609          |
+| 2.7871        | 17.0  | 51   | 3.4205          |
+| 2.5712        | 18.0  | 54   | 3.4339          |
+| 2.4756        | 19.0  | 57   | 3.3536          |
+| 2.5522        | 20.0  | 60   | 3.3670          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70368fd29ae0e80df24bde7a3029c101a4d567b647d40e1f78708a33dbb36104
+oid sha256:0565ae4544063cc150469255da4179787f4afc1aaf0ebca9654e28721560c5e2
 size 2748401440

runs/Apr19_15-21-22_gcn49.local.snellius.surf.nl/events.out.tfevents.1713532892.gcn49.local.snellius.surf.nl.822259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5568477b05d2da5d9548efa3979f967d6a33f82beff83a532c995c151b3d2236
+size 22765

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c3508d430997a20e2686fc06cdc52d97fc5c4a01f6b8b9baba32b2274fca639
+oid sha256:ee85b6dcba8d14e1bbed220d99da4393f2b0d3791a740585d6c114d1175aa3e5
 size 4984