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: 3.4506
+- Loss: 3.1969
 
 ## Model description
 
@@ -41,18 +41,15 @@ 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: 100
-- num_epochs: 5
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9516        | 1.0   | 209  | 3.3956          |
-| 1.9227        | 2.0   | 419  | 3.2945          |
-| 0.8445        | 3.0   | 628  | 3.3858          |
-| 0.4503        | 4.0   | 838  | 3.4306          |
-| 0.3053        | 4.99  | 1045 | 3.4506          |
+| 2.9338        | 1.0   | 209  | 3.3718          |
+| 2.028         | 2.0   | 418  | 3.1969          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46728415e964286eb9441feb2f789d5698f56191d437f9830293d7802ab5069d
+oid sha256:0f1b20572ea29ad66a63acb1dd7a4a7c4a9e20326a1fcc0f4e791718bf084730
 size 1570992472

runs/Apr05_13-43-15_gcn31.local.snellius.surf.nl/events.out.tfevents.1712317405.gcn31.local.snellius.surf.nl.310277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc906fe180012bb66c52c6bff833420bb285edf650288dd9716fd114302ecb4
+size 9654

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c46f3d1c2bde132f56b5178ba19c80cb4d06e70e1cd978749f36c0cc0fb089
+oid sha256:fb112b00ed4c4a4ac2107213f98b0fbfd028d43559b0a6da5ffef6173e756d37
 size 4984