Model save

README.md

@@ -15,8 +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: 1.0556
-- Mse: 1.0556
+- Loss: 0.8311
+- Mse: 0.8311
 
 ## Model description
 
@@ -36,20 +36,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
 | 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 |
+| No log        | 1.0   | 146  | 1.5425          | 1.5425 |
+| No log        | 2.0   | 292  | 1.2182          | 1.2182 |
+| No log        | 3.0   | 438  | 1.2270          | 1.2270 |
+| 1.7883        | 4.0   | 584  | 1.0496          | 1.0496 |
+| 1.7883        | 5.0   | 730  | 1.0828          | 1.0828 |
+| 1.7883        | 6.0   | 876  | 0.9050          | 0.9050 |
+| 0.9949        | 7.0   | 1022 | 0.8451          | 0.8451 |
+| 0.9949        | 8.0   | 1168 | 0.9760          | 0.9760 |
+| 0.9949        | 9.0   | 1314 | 0.8303          | 0.8303 |
+| 0.9949        | 10.0  | 1460 | 0.8311          | 0.8311 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce495dc76764ccada1fe6e034578cbb5f7891b35e8de3e4bf225e4994158712
+oid sha256:508fea612b726ecff74e507df844af1d4b8015132b27bf97c5fcf83f5042929a
 size 595246640