Run 4. Outer Step 52. Inner Step 8.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575265,
-    5575268,
-    5575270,
-    5575272,
-    5575274
+    5575276,
+    5575279,
+    5575281,
+    5575284,
+    5575287
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 7,
+  "inner_step": 8,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4a480aaf14bf5d95dcdef614a3c98b6bc7dd31c4f9bfdb07d42a5c561b0b94
+oid sha256:075032580702bba5f4bb7477cb23545d51ce82c257d776f978e57b30fc0909bc
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3da6ae1c83bed831fd7a32789c45ab5b30d7b11679151c39e23af1d034e06e5
+oid sha256:ef1700ffee7abbcb58123507aea62d570ce748b5c7127988bd983ad886ad7508
 size 4040701744