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: 7.8932
+- Loss: 7.2750
 
 ## Model description
 
@@ -32,7 +32,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.5e-05
+- learning_rate: 0.0025
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.91  | 2    | 8.6479          |
-| No log        | 1.83  | 4    | 8.4904          |
-| No log        | 2.74  | 6    | 8.2210          |
-| No log        | 3.66  | 8    | 7.8932          |
+| No log        | 0.91  | 2    | 7.9754          |
+| No log        | 1.83  | 4    | 8.3820          |
+| No log        | 2.74  | 6    | 7.3030          |
+| No log        | 3.66  | 8    | 7.2750          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef99e97a863ebce585c1c84efaab757fec393186083b4356a9fc4384275d19b3
+oid sha256:4a31042b3f2f75ff763b29c7efc5775194dfa6daaf6e8667503f739e55ed0d66
 size 2747934496

runs/Mar20_14-24-36_gcn59.local.snellius.surf.nl/events.out.tfevents.1710941085.gcn59.local.snellius.surf.nl.1204565.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0b0c3b070e7182d2903f3193bc7f05c00fb136cca2dc08d8ccf22c3e1cf6d3
+size 5847

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35591c7695e714ec7e4b52fead15e42af784f528c556b78cb5ea6ccbc7cd998
+oid sha256:c2e0ba9cc652b9679de4450d828169451120f45fe0b3458e219a4f217af043a6
 size 4728