Model save

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: facebook/esm2_t30_150M_UR50D
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: model_checkpoint
  results: []
@@ -17,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/esm2_t30_150M_UR50D](https://huggingface.co/facebook/esm2_t30_150M_UR50D) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3773
-- Accuracy: 0.8786
+- Loss: 1.0556
+- Mse: 1.0556
 
 ## Model description
 
@@ -47,16 +45,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4396 | 1.0 | 606 | 0.3541 | 0.8533 |
-| 0.3177 | 2.0 | 1212 | 0.3660 | 0.8656 |
-| 0.2331 | 3.0 | 1818 | 0.3773 | 0.8786 |
+| Training Loss | Epoch | Step | Validation Loss | Mse |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log | 1.0 | 291 | 1.3725 | 1.3725 |
+| 2.0438 | 2.0 | 582 | 1.1483 | 1.1483 |
+| 2.0438 | 3.0 | 873 | 1.0556 | 1.0556 |
 
 
 ### Framework versions
 
 - Transformers 4.39.3
-- Pytorch 2.2.2+cpu
+- Pytorch 2.2.1+cpu
 - Datasets 2.18.0
 - Tokenizers 0.15.2