Run 4. Outer Step 3. Inner Step 134.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484720,
-    5484722,
-    5484724,
-    5484725,
-    5484727,
-    5484729,
-    5484731,
-    5484735,
-    5484737
+    5484740,
+    5484742,
+    5484744,
+    5484745,
+    5484748
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 133,
+  "inner_step": 134,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643a1c25209eec86a495be779528a26080df50d638cb90a92d5e170d4c06fd35
+oid sha256:9c08439f9502967d84ce178d36a56ea86652d22d50787f51d8efdbca523dfc98
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f00f2892fa96eb378aa2eaa75db21d05fa1eecc7c73b82c8c754ed2cee82a67
+oid sha256:b2d51cffaa66ad929a4ea5e0c099360738f8ea5d36196e2a2fd91da881e876bc
 size 4040701744