Model save

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 3.8278
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.2
+- learning_rate: 0.01
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
@@ -46,17 +46,14 @@ 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_ratio: 0.05
-- num_epochs: 4
-- mixed_precision_training: Native AMP
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0           | 1.0   | 778  | nan             |
-| 0.0           | 2.0   | 1557 | nan             |
-| 0.0           | 3.0   | 2336 | nan             |
-| 0.0           | 4.0   | 3112 | nan             |
+| 4.0872        | 1.0   | 778  | 4.0301          |
+| 4.0179        | 2.0   | 1556 | 3.8278          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fa8f41c892282fcbaa8ea776e07347713eb8378d1065ee86d888d7dfb057fd
+oid sha256:6e8fd5691c34e0ed9899ecbf3cf542c43775cdf3472addaeae1d520526e0694b
 size 12595704

runs/Mar17_03-30-27_49ba99224e28/events.out.tfevents.1710646302.49ba99224e28.266.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:969930c79d13b3fbb7752a1f01b1b49babc8381d25e7e585d6260ee635d9a43d
-size 168598
+oid sha256:ab4ed1990dda6327080cacd13142ffb2e99890da47815f1b5e906494bd83f879
+size 333381