Outer Step 1. Inner Step 2462. Batch Size 440

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5184614,
-    5184619,
-    5184625,
-    5184630,
-    5184635,
-    5184640,
-    5184645,
-    5184651,
-    5184656,
-    5184661
+    5184700,
+    5184705,
+    5184710,
+    5184715,
+    5184720,
+    5184726,
+    5184731,
+    5184735,
+    5184740,
+    5184745
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2453,
+  "inner_step": 2462,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cc9201dc49940d98f0cfcd9ce77891ac9a32467300dd8bf0b4db13513505fe
+oid sha256:638d41888d3a14dca092447fc3004682b87d9540f66aaf5e623485571ac85dee
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd68f051270aa7c0afa20a55ebfedc4ac8816bb6c600242791d33ad2a99356f8
+oid sha256:14868afcca0094aa6e471c86866f3d56f4448425b03902d7304311385cc1c8b0
 size 4040701744