Outer Step 0. Inner Step 178. Batch Size 344

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156353,
-    5156357,
-    5156362,
-    5156365,
-    5156371,
-    5156376,
-    5156381,
-    5156385,
-    5156390,
-    5156396
+    5156429,
+    5156434,
+    5156440,
+    5156444,
+    5156450,
+    5156454,
+    5156460,
+    5156464,
+    5156470,
+    5156476
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 170,
+  "inner_step": 178,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f300d3dfd37af51ccf109265f4d559c075c8951adab2099a92694cc42167c325
+oid sha256:bdd5f3c3eb2e801a2fbc0cb61a4b3c7a25acbf34800bd3a80cdd9da6f1e78046
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf09aa3909428596439b47228957625c0c96e637ca0ab5167a84b0bbae4f5f2
+oid sha256:52d753e88ca8085b15628470bfa99214979949185d674c3ba338c88d76ecadac
 size 4040701744