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 [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5249
+- Loss: 0.5388
 
 ## Model description
 
@@ -35,23 +35,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
-- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 148
 - num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.5205        | 1.0   | 297  | 0.5361          |
-| 0.5152        | 2.0   | 594  | 0.5311          |
-| 0.5068        | 3.0   | 891  | 0.5233          |
-| 0.4969        | 4.0   | 1188 | 0.5254          |
-| 0.4968        | 5.0   | 1485 | 0.5249          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5264        | 0.3367 | 100  | 0.5349          |
+| 0.5082        | 0.6734 | 200  | 0.5378          |
+| 0.5331        | 1.0101 | 300  | 0.5388          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d1495a639948b9760adb4329c75c686fbb74f0553f1eaba09d708e8360ba8b
+oid sha256:c517630a9748ae8cb03d3ebe6aeafeda4aa49f5fa28e0e0890d0bf00d7649311
 size 598445936