Run 4. Outer Step 34. Inner Step 2.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546859,
-    5546863,
-    5546867,
-    5546872,
-    5546876
+    5546881,
+    5546885,
+    5546889,
+    5546894,
+    5546898
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 1,
+  "inner_step": 2,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb105ddb21b58b26952b9c11f0cc5b84d2009230f6ac3e10783b69e1cfa7eca8
+oid sha256:06fa8c49756b028373687795a7f1291963c1323d4b285bdc5cd60b68ee8df19f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df7893ea83ad84dc79b6da94012223f84f93552de9573a18a71c0aa3bee8471
+oid sha256:35479827094581c16f7baf06ba6ead5d36202763a87b88a05e3e7973e7265d42
 size 4040701744