Outer Step 0. Inner Step 218. Batch Size 300

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5132663,
-    5132667,
-    5132672,
-    5132676,
-    5132680,
-    5132684,
-    5132688,
-    5132693,
-    5132697,
-    5132702
+    5132731,
+    5132736,
+    5132740,
+    5132745,
+    5132751,
+    5132756,
+    5132760,
+    5132765,
+    5132772,
+    5132782
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 209,
+  "inner_step": 218,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72efe1369201a77b750479a305b53e516ee8232d5a8bc16d2a467e34f835245
+oid sha256:296de18df47c4fda771d4843e2ebe252a92440dcf44f2923018a69b7ff381d89
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d91d602df95e355e5ff531f828a84627665f4c0ecfb2489d82a3026619bb32
+oid sha256:c20ec94b93732efb37f6e2b2617a1a2db670006760b017a3d3e5cf79c762bc41
 size 4040701744