End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3715
+- Loss: 4.6061
 
 ## Model description
 
@@ -41,19 +41,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.9187        | 0.2667 | 200  | 3.7701          |
-| 0.9322        | 0.5333 | 400  | 3.8297          |
-| 0.9511        | 0.8    | 600  | 3.8804          |
-| 0.8337        | 1.0667 | 800  | 4.2631          |
-| 0.4772        | 1.3333 | 1000 | 4.3414          |
-| 0.5198        | 1.6    | 1200 | 4.3616          |
-| 0.5438        | 1.8667 | 1400 | 4.3715          |
+| 0.2744        | 0.2667 | 200  | 3.9036          |
+| 0.3205        | 0.5333 | 400  | 3.9461          |
+| 0.3397        | 0.8    | 600  | 4.1281          |
+| 0.328         | 1.0667 | 800  | 4.3542          |
+| 0.229         | 1.3333 | 1000 | 4.3238          |
+| 0.2537        | 1.6    | 1200 | 4.4181          |
+| 0.2656        | 1.8667 | 1400 | 4.4773          |
+| 0.2381        | 2.1333 | 1600 | 4.4933          |
+| 0.2086        | 2.4    | 1800 | 4.4857          |
+| 0.2258        | 2.6667 | 2000 | 4.5592          |
+| 0.2313        | 2.9333 | 2200 | 4.6061          |
 
 
 ### Framework versions