Model save

README.md

@@ -4,8 +4,6 @@ license: llama3.2
 base_model: meta-llama/Llama-3.2-1B
 tags:
 - generated_from_trainer
-datasets:
-- squad
 model-index:
 - name: squad_llama_finetuned
   results: []
@@ -16,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squad_llama_finetuned
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the squad dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
 
 ## Model description
 
@@ -35,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.1
-- train_batch_size: 128
+- learning_rate: 0.0001
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 8.0
+- num_epochs: 2.0
 
 ### Training results
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:166a3f8222942ad5e6905d66a3abc6acecf47ad0f97ce169dd046bde64805eeb
+oid sha256:9610a91f572a539616da5e76b84a2abcc4965ef66870d01af52495aa8c99cf30
 size 4943299944

runs/Dec23_02-32-12_xgpi4/events.out.tfevents.1734892402.xgpi4.6301.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9916562cec82a1549ae27dd9d32c8b33cf8f8b118b6e920b8930d29e54cad84
-size 9948
+oid sha256:6954b6f236dc3c1cfefae9d6d5b3d92ea47252c82ee7de39af7378586b50750b
+size 10302