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: 5.4056
+- Loss: 5.2910
 
 ## Model description
 
@@ -48,29 +48,29 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 9.6096        | 0.57  | 1    | 9.6357          |
-| 7.977         | 1.71  | 3    | 9.0764          |
-| 8.1366        | 2.86  | 5    | 8.6105          |
-| 8.0848        | 4.0   | 7    | 7.9018          |
-| 7.453         | 4.57  | 8    | 7.6342          |
-| 7.8712        | 5.71  | 10   | 7.9612          |
-| 6.8203        | 6.86  | 12   | 7.2844          |
-| 6.5424        | 8.0   | 14   | 8.1115          |
-| 7.2256        | 8.57  | 15   | 7.3713          |
-| 6.3967        | 9.71  | 17   | 6.8166          |
-| 6.0655        | 10.86 | 19   | 6.7260          |
-| 5.7827        | 12.0  | 21   | 6.4126          |
-| 5.6576        | 12.57 | 22   | 6.3180          |
-| 5.3613        | 13.71 | 24   | 6.1895          |
-| 5.1989        | 14.86 | 26   | 6.1551          |
-| 4.9434        | 16.0  | 28   | 5.8908          |
-| 4.7459        | 16.57 | 29   | 5.8423          |
-| 4.5211        | 17.71 | 31   | 5.8593          |
-| 4.6584        | 18.86 | 33   | 5.6543          |
-| 4.2589        | 20.0  | 35   | 5.4347          |
-| 4.1651        | 20.57 | 36   | 5.5395          |
-| 4.0289        | 21.71 | 38   | 5.4804          |
-| 3.7381        | 22.86 | 40   | 5.4056          |
+| 9.7067        | 0.57  | 1    | 9.7226          |
+| 8.0571        | 1.71  | 3    | 9.2898          |
+| 8.3374        | 2.86  | 5    | 8.5986          |
+| 7.5982        | 4.0   | 7    | 7.8459          |
+| 7.2482        | 4.57  | 8    | 7.8008          |
+| 6.9285        | 5.71  | 10   | 7.3997          |
+| 6.4908        | 6.86  | 12   | 8.3017          |
+| 6.3109        | 8.0   | 14   | 6.9692          |
+| 6.2177        | 8.57  | 15   | 6.9043          |
+| 5.9262        | 9.71  | 17   | 6.5565          |
+| 5.6466        | 10.86 | 19   | 6.4155          |
+| 5.3065        | 12.0  | 21   | 6.1934          |
+| 5.1914        | 12.57 | 22   | 6.0177          |
+| 4.9555        | 13.71 | 24   | 6.0827          |
+| 4.7476        | 14.86 | 26   | 5.8534          |
+| 4.6724        | 16.0  | 28   | 5.7760          |
+| 4.4796        | 16.57 | 29   | 5.6058          |
+| 4.2379        | 17.71 | 31   | 5.4230          |
+| 4.1798        | 18.86 | 33   | 5.4227          |
+| 3.9092        | 20.0  | 35   | 5.3294          |
+| 3.8306        | 20.57 | 36   | 5.2938          |
+| 3.735         | 21.71 | 38   | 5.5156          |
+| 3.4544        | 22.86 | 40   | 5.2910          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a2d100a1a3be4bf8519261a106a7aea635b67e042bcd819993a82ac7e93db2
+oid sha256:0bbe64cdd1fd57e3973cc244d9926375ebc01e1d458a14e400e45939441ddfc5
 size 2796386080

runs/Apr17_14-30-23_gcn10.local.snellius.surf.nl/events.out.tfevents.1713357035.gcn10.local.snellius.surf.nl.3796627.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9ca5185347da1ec47e04458b55269d305bede1c4357f58f9c8bdea17c11933
+size 19424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfe31b75f88558bd33846db38efc9009d2f80309d7b98e9e90c2b2a308b7600
+oid sha256:3d61ff082ec6c42f1e6bcb30e984b2a470071df3df92a3b469ceb01b0d1cf6f3
 size 4984