Outer Step 0. Inner Step 221. Batch Size 0

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5142940,
-    5142946,
-    5142951,
-    5142962,
-    5142969,
-    5142979,
-    5142988,
-    5142994,
-    5143007,
-    5143013
+    5143048,
+    5143056,
+    5143064,
+    5143073,
+    5143080,
+    5143087,
+    5143094,
+    5143103,
+    5143114,
+    5143121
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 213,
+  "inner_step": 221,
   "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 sha256:9b7aefdeaf2a6c320964ebfdf3db19aad80a8fd2e6316181aa4d8f88feb61a61
+oid sha256:4f8ddcb12cc34fd4459bfc5adf8f730c483cc9eb78053a40d9da8ae396dac352
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f43a46c6840f3ce9411f29daaf0284f378e3cbe71d82bc8e3431e7da24b18e
+oid sha256:3905c477d9b8bb9ec00a88d8d5cbee67f898523d75e35334ccdf7ae7d678b180
 size 4040701744