Outer Step 0. Inner Step 143. Batch Size 464

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5141404,
-    5141409,
-    5141413,
-    5141429,
-    5141444,
-    5141462,
-    5141474,
-    5141484,
-    5141491,
-    5141500
+    5141526,
+    5141539,
+    5141556,
+    5141566,
+    5141586,
+    5141593,
+    5141601,
+    5141606,
+    5141614,
+    5141624
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 137,
+  "inner_step": 143,
   "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 sha256:665b82fa91a1ee64f3de476480b8dcbb5a086b53f4750bf2c9f9cd678663ec14
+oid sha256:30f481cd786bfed42c62920e7dce3dfd82a3034446db3d7f7d2dee5ebcfc73ce
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1de7776c95ba55f926fdf0c2f63e804fb4ff581b5cfc43f6a63b175c68e2048
+oid sha256:bd9f4f6c779c6272e6cff57186d52b8ad4d9b6d279e5bc79d7a31b81b3f1f1ac
 size 4040701744