Run 4. Outer Step 64. Inner Step 0.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5645416,
-    5645445
+    5645474,
+    5645503
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e936dec1fcfb5e0c36d838b56d36e5f1eae396e0ec20fe5f1ed5cc985f27d30b
+oid sha256:887424a9f8c49ceae9f9165f90c7567796f264c5b50c4c59c621d599bfac1016
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed953d0a193b61a0e898f1f3d464a5e21b1543e0eafe8242e171fd5e5bc24474
+oid sha256:73b142478039582211854e6b2165fbf192fc134a7b331e95f1de8a45d01fc0a1
 size 4040701744