Update README.md

README.md

@@ -123,7 +123,9 @@ Please see [the BLOOM training README](https://github.com/bigscience-workshop/bi
 
 * ALiBI positional encodings (see [paper](https://arxiv.org/pdf/2108.12409.pdf)), with GeLU activation functions
 
-* 6.3B billion parameters:
+* 7,069,016,064 parameters:
+
+    * 1,027,604,480 embedding parameters
 
     * 30 layers, 32 attention heads
 
@@ -167,17 +169,7 @@ Please see [the BLOOM training README](https://github.com/bigscience-workshop/bi
 #### **Training**
 
  
-_In progress._
-
-Current training logs: [Tensorboard link](https://huggingface.co/tensorboard/bigscience/tr11-176B-ml-logs/)
-
-- Checkpoint size:
-    
-    - Bf16 weights: 329GB
-    
-    - Full checkpoint with optimizer states: 2.3TB
-
-- Training throughput: About 150 TFLOP per GPU per second
+Training logs: [Tensorboard link](https://huggingface.co/tensorboard/bigscience/tr11c-2B5-logs)
 
 - Number of epochs: 1 (*current target*)
 
@@ -185,7 +177,7 @@ Current training logs: [Tensorboard link](https://huggingface.co/tensorboard/big
     
     - Started 11th March, 2022 11:42am PST
 
-    - Estimated end: 5th July, 2022
+    - Ended 5th July, 2022
 
 - Estimated cost of training: Equivalent of $2-5M in cloud computing (including preliminary experiments)