ninagroot/Llama-360Mtest

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: 7.0688
+- Loss: 6.5980
 
 ## Model description
 
@@ -41,22 +41,25 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 15
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 9.6377        | 0.57  | 1    | 9.6302          |
-| 9.4525        | 1.71  | 3    | 9.4287          |
-| 8.7163        | 2.86  | 5    | 8.9832          |
-| 7.8128        | 4.0   | 7    | 8.3895          |
-| 7.4521        | 4.57  | 8    | 8.1403          |
-| 6.9301        | 5.71  | 10   | 7.7375          |
-| 6.5872        | 6.86  | 12   | 7.4260          |
-| 6.2594        | 8.0   | 14   | 7.2005          |
-| 6.073         | 8.57  | 15   | 7.0688          |
+| 9.6138        | 0.57  | 1    | 9.6268          |
+| 9.4594        | 1.71  | 3    | 9.4257          |
+| 8.7153        | 2.86  | 5    | 8.9917          |
+| 7.7997        | 4.0   | 7    | 8.3919          |
+| 7.4748        | 4.57  | 8    | 8.1416          |
+| 6.9795        | 5.71  | 10   | 7.7509          |
+| 6.6277        | 6.86  | 12   | 7.4589          |
+| 6.2995        | 8.0   | 14   | 7.2322          |
+| 6.1166        | 8.57  | 15   | 7.1325          |
+| 5.7999        | 9.71  | 17   | 6.9254          |
+| 5.4888        | 10.86 | 19   | 6.6730          |
+| 5.3856        | 11.43 | 20   | 6.5980          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9c21db99fcd97e1ecf5b7c802156a6a9f884d5bc607d7db3cfec7d95179624
+oid sha256:1a28d5ff4b352756a95bff49f21aa02925143e768fa85267275560477094dec1
 size 1408774432

runs/Apr17_10-07-02_gcn7.local.snellius.surf.nl/events.out.tfevents.1713341231.gcn7.local.snellius.surf.nl.1399995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8061c12bb7fa786406e663ea8fe245e892bf776404972a2731f6c2ea3d25ee80
+size 12241

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab47956e03301f319c490c7a433eb881c15373168f14ed294725b34da173253
+oid sha256:b05e54949eb8fdf41cb0d84830786d09439c7ac5c5cc32ac399ebef740d18dd5
 size 4984