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: 3.1957
+- Loss: 3.2009
 
 ## Model description
 
@@ -41,15 +41,16 @@ 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: 2
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.9197        | 1.0   | 209  | 3.3808          |
-| 2.0333        | 2.0   | 418  | 3.1957          |
+| 2.9075        | 1.0   | 210  | 3.3783          |
+| 1.7841        | 2.0   | 420  | 3.2031          |
+| 0.9611        | 3.0   | 630  | 3.2009          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a263859149ed36cd50a20cc374caebf3b4b32d1f239c0eb72d7c1fcfcd6f9e4
+oid sha256:59ad553e073602086265868ee976391542d2c79bd6b9a676bda55cc75035c179
 size 1570992472

runs/Apr05_14-39-02_gcn72.local.snellius.surf.nl/events.out.tfevents.1712320752.gcn72.local.snellius.surf.nl.1635303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecdd7100687078458cf561cb0743dd361bab7110fa120505b8bef1591108898
+size 12246

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07aa53559e7559dcf5b543706386de4874e9d1efd399a11d92168894e1fc0145
+oid sha256:391459dd6269ecbb83dba9c883903f96777586da6a2d64ed6471804569bbd266
 size 4984