Update README.md

README.md

@@ -71,9 +71,11 @@ The training data was pre-processed with a `PreTrainedTokenizerFast()` trained o
 
 - **Batch size:** 64
 - **Gradient accumulation steps:** 4
-- **Training regime:** fp16
-- **Learning rate:** 0.001
-- **Optimizer:** AdamW
+- **Mixed precision:** fp16, native amp
+- **Learning rate:** 0.0025
+- **LR Scheduler:** Cosine
+- **Learning rate scheduler warmup:** 0.1
+- **Optimizer:** AdamW with betas=(0.9,0.95) and epsilon=1e-08
 - **Number of epochs:** 50
 
 More configuration (options) can be found in the [`conf`](https://github.com/hogru/MolReactGen/tree/main/src/molreactgen/conf) directory of the repository.
@@ -97,8 +99,14 @@ Please see the slides / the poster mentioned above.
 
 ## Technical Specifications
 
-#### Hardware
+### Framework versions
+
+- Transformers 4.27.1
+- Pytorch 1.13.1
+- Datasets 2.10.1
+- Tokenizers 0.13.2
+
+### Hardware
 
 - Local PC running Ubuntu 22.04
 - NVIDIA GEFORCE RTX 3080Ti (12GB)
-