Run 4. Outer Step 57. Inner Step 3.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5600949,
-    5600957,
-    5600964,
-    5600972,
-    5600979
+    5600987,
+    5600994,
+    5601001,
+    5601007,
+    5601015
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e395107f2c4e7af0dfe3d54fdccf403cd7b158b0c191749df37fe4909139d4
+oid sha256:e40542e01f31106b1e3dbb28f3e9d77b8ad67a7cc1f2a3e7d557adae76d4f0e9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1988ad677b04e53c07004656b86a6bdf112456adcc8df0a3403fd8697f289bc
+oid sha256:8af3850be21d85bdbad58d36643a93fa3246b81c2119cc0bc42bf3db0ddfebd0
 size 4040701744