Run 4. Outer Step 28. Inner Step 42.

config.json

@@ -268,23 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5538418,
-    5538420,
-    5538423,
-    5538424,
-    5538424,
-    5538426,
-    5538428,
-    5538430,
-    5538432,
-    5538434
+    5538436,
+    5538438,
+    5538441,
+    5538443,
+    5538445
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5537093,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdfd8faffb73077505ef8612dd6120c9a2af87f5da30b6a56ad15c584ae90a53
+oid sha256:c50853c08d240586a09d33b092e0659de651c5495217f0ed3cbce5ad66d9c70e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6f522b73517302ca582bd754e1a81379b1cfd08b9ddeeb3e2eacc0d52ba919
+oid sha256:c11f4a3c2700b9084b9ebb7763260520ff6299bd8ff56ac538725132ab8851e7
 size 4040701744