Run 4. Outer Step 32. Inner Step 35.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5543807,
-    5543809,
-    5543811,
-    5543813,
-    5543815,
-    5543817,
-    5543820
+    5543823,
+    5543826,
+    5543828,
+    5543831,
+    5543834
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5542700,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a640d801401ba7b873e58591436c325c57ca5cedad60b45936a4e8ab2bde75c7
+oid sha256:c0ba1da8a80795502228b23acf21462d660f9c6b20b68d71a546487172e9b401
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988a0306983cfec59fd23d51b3322b787ad3422800cad1dec0ccc8584a577a6d
+oid sha256:c9ba87acef3af0a9417c1d74bebbdc6599f3e0d9b3bdde889049a66e3e4a370d
 size 4040701744