Outer Step 1. Inner Step 1599. Batch Size 356

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184025,
-    5184029,
-    5184033,
-    5184037,
-    5184042,
-    5184046,
-    5184050,
-    5184054,
-    5184058,
-    5184062
+    5184091,
+    5184096,
+    5184100,
+    5184104,
+    5184108,
+    5184112,
+    5184117,
+    5184121,
+    5184125,
+    5184130
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1590,
+  "inner_step": 1599,
   "inner_steps": 0,
   "last_allreduce_block": 5160840,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d442e018fb58137a2a5c2fbb709be02fca05964a46a475eb2aa9118bdc5c849
+oid sha256:3011b599a456bc42956c80eb96ab261d22c428b1ab74f217b6fcc6611fed5557
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec79a7b6e799e70bdbcc2d47e40edb8d107ff577d51d638069cc51a411e945bd
+oid sha256:afe676ef4a8cecab68adf401e4a41bf66a3a3474c6c840da5ed3f90dc2e48403
 size 4040701744