Update README.md

README.md

@@ -41,7 +41,7 @@ These proxy models are intended for ML researchers and engineers working on:
 
 | Variant | Parameters | Layers | Checkpoint Size |
 |---|---|---|---|
-| 62M | 62 million | 32 | ~735 MB |
+| 62M | 62 million | 32 | ~837 MB |
 | 350M | 350 million | 32 | ~4.5 GB |
 
 Note: Checkpoint sizes include optimizer state and RNG state, suitable for continued pre-training. <br>
@@ -100,7 +100,7 @@ This AI model can be embedded as an Application Programming Interface (API) call
 
 | Variant | Training Iterations | Training Tokens | Training Nodes | Checkpoint |
 |---|---|---|---|---|
-| 62M | 2,500,000 | 10T | 8 | `iter_2500000/mp_rank_00/model_optim_rng.pt` |
+| 62M | 2,499,000 | 10T | 8 | `iter_2499000/mp_rank_00/model_optim_rng.pt` |
 | 350M | 2,384,053 | 10T | 16 | `iter_2384053/mp_rank_00/model_optim_rng.pt` |
 
 Both are v1.0 releases. <br>