Outer Step 1. Inner Step 1619. Batch Size 40

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184159,
-    5184163,
-    5184168,
-    5184171,
-    5184176,
-    5184180,
-    5184183,
-    5184189,
-    5184193,
-    5184198
+    5184230,
+    5184234,
+    5184238,
+    5184242,
+    5184246,
+    5184251,
+    5184255,
+    5184259,
+    5184263,
+    5184267
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1609,
+  "inner_step": 1619,
   "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:becfc8d3f75a809e09c1d79d860a7e225fad63ffc136cd6b4e1b7d9d13ad9be1
+oid sha256:487d2f3f4b2a69af29ae417b3cd0f4d376b3033d74e53dc9a989c0a70e77e36e
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b87add0912f7603983cde0d5c8b574fa744fd44dc1b6e60ebc988ff230610a
+oid sha256:df8bfa0fc630f31c92e99ab7f7d1f14cc8743c3c0f8b5af9758d36ad9ac97bdc
 size 4040701744