Update README.md

README.md

@@ -126,7 +126,7 @@ The data was processed into fixed-size chunks of 512 tokens, respecting document
 
 ### Pre-training
 
-The model was pre-trained from scratch for **150,000 steps** on 8x NVIDIA A100 40GB GPUs, using BFloat16 (`bf16`) mixed-precision for stability and speed. The training took approximately **25 hours and 7 minutes** to complete.
+The model was pre-trained from scratch for **150,000 steps** on 8x NVIDIA H100 GPUs, using BFloat16 (`bf16`) mixed-precision for stability and speed. The training took approximately **25 hours and 7 minutes** to complete.
 
 The key hyperparameters used were:
 - **Learning Rate**: 2e-4 (0.0002) with a linear warmup of 9,000 steps
@@ -144,7 +144,7 @@ The key hyperparameters used were:
 The model achieved the following performance metrics:
 - **Final Training Loss**: 0.7479
 - **Final Evaluation Loss**: 0.69405
-- **Training Infrastructure**: 8x NVIDIA H100 80GB GPUs
+- **Training Infrastructure**: 8x NVIDIA H100 GPUs
 - **Total Training Steps**: 150,000
 - **Total Training Time**: 25 hours 7 minutes
 - **Train/Validation Split**: 95%/5%
@@ -222,7 +222,7 @@ The model shows stable convergence across both languages:
 - **Model Size**: ~125M parameters
 - **Architecture**: RoBERTa-base (12 layers, 12 attention heads)
 - **Languages**: Greek (el) + English (en)
-- **Training Time**: 25 hours 7 minutes on 8x A100 GPUs
+- **Training Time**: 25 hours 7 minutes on 8x H100 GPUs
 - **Dataset Size**: 26GB bilingual legal corpus
 - **Language Ratio**: 60.3% Greek, 39.7% English
 - **Memory Requirements**: Efficient base architecture suitable for production deployment