Run 3. Outer Step 5. Inner Step 261.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5384421,
-    5384424,
-    5384428,
-    5384432,
-    5384436
+    5384461,
+    5384465,
+    5384469,
+    5384472,
+    5384476
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 259,
+  "inner_step": 261,
   "inner_steps": 0,
   "last_allreduce_block": 5378990,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381b4bd98b78d9f9577136d344b29d758ff8074057e9eb30013fdb24af1255eb
+oid sha256:ce1d62c4052bf517973ad294ef71fa354b710a018f83716c643c5688840da9c8
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:356de244c87481d20bbe8a16cc38fe617c76b0503b752980d30b3fde7296baa4
+oid sha256:0144f0671ed13c72366dfe3e6f7ec73866e7913e4f9e376b987bd800d8d30178
 size 4040701744