Run 4. Outer Step 65. Inner Step 26.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5648646,
-    5648676
+    5648710,
+    5648742
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 24,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5639485,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179ab96374af79df066f6e55e752ff7dbd7c0b0625e6343766d442eba7cb1e93
+oid sha256:51d28407a9dc6a557ea5c0823eb88a1fca7606ce0f27187a78e588d8633558d1
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da46fea9b0f860d971206b1295ef06f97b2d0ee3ce32ed4b0790158a1f9c0f22
+oid sha256:9f48f78301d6fefb96275fcc0cbdb03a21c4f631664a8929cdfec84e2bf15ba3
 size 4040701744