End of training

README.md

@@ -4,6 +4,8 @@ license: mit
 base_model: microsoft/DialoGPT-small
 tags:
 - generated_from_trainer
+datasets:
+- empathetic_dialogues
 model-index:
 - name: testing
   results: []
@@ -14,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # testing
 
-This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on the empathetic_dialogues dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.8036
+- Loss: 1.7011
 
 ## Model description
 
@@ -41,18 +43,20 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 10
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.3846 | 5    | 3.8458          |
-| No log        | 0.7692 | 10   | 2.8036          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 13   | 1.8261          |
+| No log        | 2.0   | 26   | 1.7528          |
+| No log        | 3.0   | 39   | 1.7011          |
 
 
 ### Framework versions
 
 - Transformers 4.48.2
 - Pytorch 2.5.1+cu124
+- Datasets 3.2.0
 - Tokenizers 0.21.0