Run 4. Outer Step 33. Inner Step 26.

config.json

@@ -268,18 +268,22 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544781,
-    5544784,
-    5544787,
-    5544790,
-    5544793
+    5544797,
+    5544800,
+    5544803,
+    5544806,
+    5544809,
+    5544811,
+    5544813,
+    5544815,
+    5544817
   ],
   "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": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c22669ee9369ff0715c7d0995f34f601f48420415ab9714c13183381be9cd4
+oid sha256:01961e65d3168c6f03b5c6b6c8da24fed6435562dbae7ae9cbcdbfcc2aa8afbb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdaa35574d26f8f90bf77ea989942abe9224ee886a700e616fb365b5f2ae78c9
+oid sha256:e5f164d63ea932d937d09785013b69a9df53638c87f8b8cd4548022d100f357b
 size 4040701744