Run 4. Outer Step 52. Inner Step 30.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575937,
-    5575939,
-    5575941,
-    5575944,
-    5575947,
-    5575950,
-    5575953
+    5575956,
+    5575957,
+    5575960,
+    5575961,
+    5575961
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 29,
+  "inner_step": 30,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70e132d9f9cd66f9488911a08997f8419fcc8c44b577d731ab15cee66ab3248
+oid sha256:5c1778bed751c2b6d5c9ac9e88fbf1d510312dd5f996823393cea14580e06c5a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b260dead0b93c9fe4826be0eba8bc0dacb370149ea55e955c6db6970a224cb05
+oid sha256:0c288825815729a3b459b92b1311bdfe90032c2eafc79430141c6d419933874a
 size 4040701744