Outer Step 0. Inner Step 23. Batch Size 100

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5063144,
-    5063148,
-    5063152,
-    5063156,
-    5063160
+    5063180,
+    5063184,
+    5063188,
+    5063191,
+    5063195
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 23,
   "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:a83193d088ea0f351667556bd22f7a176a5cf2a063c0551cb9df2850f68ac657
+oid sha256:944c26f0c97e97b455004ac76da49af8c72b832343179490d5566846274dd2c9
 size 4040701744