Run 4. Outer Step 57. Inner Step 28.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601713,
-    5601717,
-    5601722,
-    5601726,
-    5601731
+    5601736,
+    5601740,
+    5601746,
+    5601750,
+    5601754
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "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 sha256:89d9af51573033e8c7f878ccd353679df5cfa3abac80ddcccb326d0d421ab9cc
+oid sha256:3b8877990c6c3f2049b66cb54c958230543fd86c268211f912f87f41afda8f55
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1b94ffbcc48f8b2bc35ba28f12b7fc7dad1ff3423c527f4bf80b177d760370
+oid sha256:5908dad09a4b14acead1280aa021445b94e90bb9194413f8611b5a83d456ae95
 size 4040701744