Run 4. Outer Step 57. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601665,
-    5601670,
-    5601675,
-    5601679,
-    5601684
+    5601689,
+    5601693,
+    5601698,
+    5601702,
+    5601707
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfddec09962146f7ed472ecc632ef0614722fda862419cfcda08cab4bd6914a9
+oid sha256:cb8be9d4aaef1ef477b2fd728aa4d1e41221a59a8f4beec6a41ce6bc3646bd97
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ad95f7af5ef625719ecd255a675260a6767fb09f38d0b20ac13d202939ad826
+oid sha256:cad7f6d2e06bc7e3d8f471d45b25f1e3a0bbf75b737478485b5a5ac946389d3f
 size 4040701744