Run 3. Outer Step 11. Inner Step 184.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5442701,
-    5442705,
-    5442709,
-    5442713,
-    5442716
+    5442744,
+    5442748,
+    5442752,
+    5442755,
+    5442759
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 182,
+  "inner_step": 184,
   "inner_steps": 0,
   "last_allreduce_block": 5422706,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0cbf7ed7d05aa15a63a7982ff798d2accc155e21755ebbada4152474111ce0
+oid sha256:86f562b06223b7edbab240a203e4f1b1252540f8ef6b0891df10e51c04e21420
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e1d921430eab3aeaea69a063706b1f4406e03df9e52cb6fc76208d0463f7d5b
+oid sha256:4391b0f87cb5f56b78f3ed470c172531f486ea2a0be4f5fbd76cf6d1bc2a155b
 size 4040701744