Outer Step 2. Inner Step 222. Batch Size 268

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5074566,
-    5074571,
-    5074575,
-    5074580,
-    5074584
+    5074597,
+    5074601,
+    5074605,
+    5074609,
+    5074613
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 218,
+  "inner_step": 222,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c608e857755cf624e8fcb684336d2bd44a5666f4e8e7e6a0682fd57c73db0141
+oid sha256:e3123da1791f4048e1ec6ffbc51eb2322bc226fdb0ed41a674f1c30c95286b2b
 size 4040701744